diff --git a/01_GenerateMicrostructures.py b/01_GenerateMicrostructures.py
index 44179f03abb56159639bd0e506bb48ba1e6d17e9..5ccb797180c92629ca761299777b1a4b34af197a 100644
--- a/01_GenerateMicrostructures.py
+++ b/01_GenerateMicrostructures.py
@@ -5,7 +5,7 @@ import pandas as pd
 import os
 import shutil
 
-from gismo_export import AdditionalBlocks, export
+from gismo.gismo_export import AdditionalBlocks, export
 from gismo.GenerateMicrostructures_fun import generate
 
 EPS = 1e-8
diff --git a/04_TrainModels.py b/04_TrainModels.py
index 33775898c279ba69560b1ba32609388d24426dde..bd9b5a07e91e6d84ddc987955eb1400e5842df7b 100644
--- a/04_TrainModels.py
+++ b/04_TrainModels.py
@@ -20,11 +20,12 @@ for model_name in models:
     X_r_velocity, X_r_pressure = model.POD()
     model_velocity, model_pressure = model.train(X_r_velocity, X_r_pressure)
 
-    model.save_model(best_model_velocity, best_model_pressure, model_velocity_file=f'{model_name}/velocity_elbow.pkl', model_pressure_file=f'{model_name}/pressure_elbow.pkl')
+    model.save_model(model_velocity, model_pressure, model_velocity_file=f'{model_name}/velocity_elbow.pkl', model_pressure_file=f'{model_name}/pressure_elbow.pkl')
 
     # Search for the best number of POD modes concerning the rmse (root mean square error)
     # R = np.linspace(1, 25, 25, dtype=int)
-    R = np.linspace(1, 21, 21, dtype=int)
+    # R = np.linspace(1, 21, 21, dtype=int)
+    R = np.linspace(1, 21, 3, dtype=int)
 
     mae_velocity_best, mae_pressure_best = model.mae_test(model_velocity, model_pressure)
     mape_velocity_best, mape_pressure_best = model.mape_test(model_velocity, model_pressure)
@@ -35,30 +36,30 @@ for model_name in models:
     R_best = model.elbow_point(scaled=True)
 
     print(f'Finding the optimal number of nodes for model {model_name}')
-    # for R_ in R:
-    #     X_r_velocity, X_r_pressure = model.POD(R_velocity=R_, R_pressure=R_)
-    #     model_velocity, model_pressure = model.train(X_r_velocity, X_r_pressure)
-
-    #     mae_velocity_, mae_pressure_ = model.mae_test(model_velocity, model_pressure)
-    #     mape_velocity_, mape_pressure_ = model.mape_test(model_velocity, model_pressure)
-    #     rmse_velocity_, rmse_pressure_ = model.rmse_test(model_velocity, model_pressure)
-    #     max_error_velocity_, max_error_pressure_ = model.max_error_test(model_velocity, model_pressure)
-
-    #     if rmse_velocity_ < rmse_velocity_best:
-    #         best_model_velocity = model_velocity
-    #         mae_velocity_best = mae_velocity_
-    #         mape_velocity_best = mape_velocity_
-    #         rmse_velocity_best = rmse_velocity_
-    #         max_error_velocity_best = max_error_velocity_
-    #         R_best = (R_, R_best[1])
-
-    #     if rmse_pressure_ < rmse_pressure_best:
-    #         best_model_pressure = model_pressure
-    #         mae_pressure_best = mae_pressure_
-    #         mape_pressure_best = mape_pressure_
-    #         rmse_pressure_best = rmse_pressure_
-    #         max_error_pressure_best = max_error_pressure_
-    #         R_best = (R_best[0], R_)
+    for R_ in R:
+        X_r_velocity, X_r_pressure = model.POD(R_velocity=R_, R_pressure=R_)
+        model_velocity, model_pressure = model.train(X_r_velocity, X_r_pressure)
+
+        mae_velocity_, mae_pressure_ = model.mae_test(model_velocity, model_pressure)
+        mape_velocity_, mape_pressure_ = model.mape_test(model_velocity, model_pressure)
+        rmse_velocity_, rmse_pressure_ = model.rmse_test(model_velocity, model_pressure)
+        max_error_velocity_, max_error_pressure_ = model.max_error_test(model_velocity, model_pressure)
+
+        if rmse_velocity_ < rmse_velocity_best:
+            best_model_velocity = model_velocity
+            mae_velocity_best = mae_velocity_
+            mape_velocity_best = mape_velocity_
+            rmse_velocity_best = rmse_velocity_
+            max_error_velocity_best = max_error_velocity_
+            R_best = (R_, R_best[1])
+
+        if rmse_pressure_ < rmse_pressure_best:
+            best_model_pressure = model_pressure
+            mae_pressure_best = mae_pressure_
+            mape_pressure_best = mape_pressure_
+            rmse_pressure_best = rmse_pressure_
+            max_error_pressure_best = max_error_pressure_
+            R_best = (R_best[0], R_)
 
     model.save_model(best_model_velocity, best_model_pressure, model_velocity_file=f'{model_name}/velocity_{R_best[0]}.pkl', model_pressure_file=f'{model_name}/pressure_{R_best[1]}.pkl')
     model.save_model(best_model_velocity, best_model_pressure, model_velocity_file=f'{model_name}/velocity.pkl', model_pressure_file=f'{model_name}/pressure.pkl')
diff --git a/DataPostProcessing.ipynb b/DataPostProcessing.ipynb
deleted file mode 100644
index ea79fe274ce396ea6ee3b3ce019e25565a7e8876..0000000000000000000000000000000000000000
--- a/DataPostProcessing.ipynb
+++ /dev/null
@@ -1,219 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import pandas as pd\n",
-    "import matplotlib.pyplot as plt\n",
-    "from xml.etree import ElementTree as ET\n",
-    "from sklearn.linear_model import LinearRegression\n",
-    "from sklearn.preprocessing import StandardScaler, MinMaxScaler\n",
-    "import joblib"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Gets the number of files to be processed\n",
-    "df = pd.read_excel('../Data/HollowOctagon_Setup.xlsx').transpose()[0]\n",
-    "N_FILES_train = df['N_SIZES_TRAIN']\n",
-    "N_FILES_test = df['N_SIZES_TEST']\n",
-    "N_FILES = N_FILES_train + N_FILES_test"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load XML file to numpy array\n",
-    "def load_xml_to_numpy(file_path):\n",
-    "    # Parse the XML file\n",
-    "    tree = ET.parse(file_path)\n",
-    "    root = tree.getroot()\n",
-    "\n",
-    "    # Find the Matrix element\n",
-    "    matrix = root.find('.//Matrix')\n",
-    "\n",
-    "    # Extract the text, split by whitespace, and convert to floats\n",
-    "    data = np.array([np.float128(val) for val in matrix.text.split()])\n",
-    "\n",
-    "    return data"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Create empty matrizes\n",
-    "# ToDo: Implement\n",
-    "velocity_size = 3840\n",
-    "pressure_size = 1080\n",
-    "\n",
-    "velocity_matrix = np.empty((velocity_size, N_FILES), np.float32) # np.float16 does not work in np.linalg (SVD)\n",
-    "pressure_matrix = np.empty((pressure_size, N_FILES), np.float32)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/tmp/ipykernel_14166/1197258208.py:9: RuntimeWarning: overflow encountered in cast\n",
-      "  velocity_matrix[:,index] = load_xml_to_numpy(velocity_file)\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Assemble matrizes\n",
-    "# Testing\n",
-    "for index in range(N_FILES):\n",
-    "    file = f'index_{index}.xml'\n",
-    "\n",
-    "    velocity_file = f'../Data/GismoResults/Velocities/velocity_field_{file}'\n",
-    "    pressure_file = f'../Data/GismoResults/Pressure/pressure_field_{file}'\n",
-    "\n",
-    "    velocity_matrix[:,index] = load_xml_to_numpy(velocity_file)\n",
-    "    pressure_matrix[:,index] = load_xml_to_numpy(pressure_file)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Store assembled matrizes\n",
-    "np.savetxt('../Data/POD/VelocityMatrix_full.csv', velocity_matrix)\n",
-    "np.savetxt('../Data/POD/PressureMatrix_full.csv', pressure_matrix)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def remove_rows(matrix, atol=1e-8):\n",
-    "    i = 0\n",
-    "    while i < matrix.shape[0]:\n",
-    "        if np.allclose(matrix[i,:], 0, atol=atol):\n",
-    "            matrix = np.concatenate((matrix[:i,:], matrix[i+1:,:]), axis=0)\n",
-    "            continue\n",
-    "        i += 1\n",
-    "\n",
-    "    return matrix"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "velocity_matrix = remove_rows(velocity_matrix, atol=1e-4)\n",
-    "pressure_matrix = remove_rows(pressure_matrix, atol=1e-4)\n",
-    "# Filter nan and inf to be zero\n",
-    "velocity_matrix = np.nan_to_num(velocity_matrix, copy=False, nan=0.0, posinf=0.0, neginf=0.0)\n",
-    "pressure_matrix = np.nan_to_num(pressure_matrix, copy=False, nan=0.0, posinf=0.0, neginf=0.0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Scale input and store the scaler\n",
-    "scaler_velocity = StandardScaler()\n",
-    "scaler_pressure = StandardScaler()\n",
-    "\n",
-    "# ! Only scale the first column\n",
-    "scaler_velocity.fit(velocity_matrix[:,0].reshape(-1,1))\n",
-    "velocity_matrix_scaled = np.empty_like(velocity_matrix)\n",
-    "for i in range(velocity_matrix.shape[1]):\n",
-    "    velocity_matrix_scaled[:,i] = scaler_velocity.transform(velocity_matrix[:,i].reshape(-1,1)).reshape(-1)\n",
-    "\n",
-    "scaler_pressure.fit(pressure_matrix[:,0].reshape(-1,1))\n",
-    "pressure_matrix_scaled = np.empty_like(pressure_matrix)\n",
-    "for i in range(pressure_matrix.shape[1]):\n",
-    "    pressure_matrix_scaled[:,i] = scaler_pressure.transform(pressure_matrix[:,i].reshape(-1,1)).reshape(-1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['../Data/POD/scaler_pressure.pkl']"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Store the scaler\n",
-    "joblib.dump(scaler_velocity, '../Data/POD/scaler_velocity.pkl')\n",
-    "joblib.dump(scaler_pressure, '../Data/POD/scaler_pressure.pkl')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Store scaled matrizes\n",
-    "np.savetxt('../Data/POD/VelocityMatrix_scaled.csv', velocity_matrix_scaled)\n",
-    "np.savetxt('../Data/POD/PressureMatrix_scaled.csv', pressure_matrix_scaled)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "POD",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.10"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/POD.py b/POD.py
deleted file mode 100644
index 50f4fa497ef57d7f7da95c21cfa1b257bc07ce77..0000000000000000000000000000000000000000
--- a/POD.py
+++ /dev/null
@@ -1,57 +0,0 @@
-import numpy as np
-from sklearn.linear_model import LinearRegression
-
-def POD(results_matrix, param_matrix_train, R, method=LinearRegression(), return_SV=False):
-    # # Read parameter matrix
-    # parameter_matrix = pd.read_excel(parameter_path, index_col=0)
-    # parameter_matrix = parameter_matrix.to_numpy()
-
-    # Perform POD
-    U, S, V = np.linalg.svd(results_matrix)
-
-    U_r = U[:, :R]
-    S_r = np.diag(S[:R])
-    V_r = V[:R, :]
-
-    X_r = U_r @ (S_r @ V_r)
-
-    # Train regression model for reduced velocity matrix
-    model = method
-    model.fit(param_matrix_train, X_r)
-
-    if return_SV:
-        return model, S
-    return model
-
-
-
-def predict(model, input_param, scaler=None):
-    input_param = input_param.reshape(1,-1)
-
-    results = model.predict(input_param).reshape(-1,1)
-    if scaler is not None:
-        results = scaler.inverse_transform(results)
-
-    return results
-
-
-
-def verify(validation_matrix, input_param_matrix, model, scaler, scale_comparison=True):
-    L2 = []
-    Linfty = []
-    for i in range(input_param_matrix.shape[0]):
-        predicted = predict(model, input_param_matrix[i,:], scaler)
-
-        comparison = validation_matrix[:,i]
-        if scale_comparison:
-            comparison = scaler.inverse_transform(comparison.reshape(-1,1))
-
-        L2_ = np.mean((predicted - comparison) ** 2) / np.abs(np.mean(comparison))
-        L2.append(L2_)
-        Linfty_ = np.max(np.abs(predicted - comparison)) / np.abs(np.max(comparison))
-        Linfty.append(Linfty_)
-
-    L2 = np.array(L2)
-    Linfty = np.array(Linfty)
-
-    return L2, Linfty
diff --git a/POD_GaussianProcessRegressor.ipynb b/POD_GaussianProcessRegressor.ipynb
deleted file mode 100644
index 77d3b3905f3766b537396b2d4320c0aaa0ad1cd4..0000000000000000000000000000000000000000
--- a/POD_GaussianProcessRegressor.ipynb
+++ /dev/null
@@ -1,663 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import pandas as pd \n",
-    "import matplotlib.pyplot as plt\n",
-    "from sklearn.multioutput import MultiOutputRegressor\n",
-    "from sklearn.gaussian_process import GaussianProcessRegressor\n",
-    "# from models.GPR.my_gpr import myGaussianProcessRegressor as GaussianProcessRegressor\n",
-    "from sklearn.gaussian_process.kernels import RBF, WhiteKernel\n",
-    "from sklearn.metrics import max_error, r2_score, root_mean_squared_error, mean_absolute_percentage_error\n",
-    "import joblib\n",
-    "from scipy.optimize import differential_evolution\n",
-    "from POD import POD, predict, verify"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load the data\n",
-    "velocities_path = '../Data/POD/VelocityMatrix_scaled.csv'\n",
-    "pressure_path = '../Data/POD/PressureMatrix_scaled.csv'\n",
-    "\n",
-    "velocities = np.loadtxt(velocities_path)\n",
-    "pressure = np.loadtxt(pressure_path)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Divide the data into training and testing sets#\n",
-    "# Get training and data splits\n",
-    "df = pd.read_excel('../Data/HollowOctagon_Setup.xlsx').transpose()[0]\n",
-    "N_FILES_train = df['N_SIZES_TRAIN']\n",
-    "N_FILES_test = df['N_SIZES_TEST']\n",
-    "N_FILES = N_FILES_train + N_FILES_test\n",
-    "\n",
-    "# Get the training and testing data\n",
-    "velocities_train = velocities[:N_FILES_train]\n",
-    "velocities_test = velocities[N_FILES_train:]\n",
-    "pressure_train = pressure[:N_FILES_train]\n",
-    "pressure_test = pressure[N_FILES_train:]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load input parameters\n",
-    "input_path = '../Data/HollowOctagon_Sizes.xlsx'\n",
-    "input = pd.read_excel(input_path, index_col=0).to_numpy()\n",
-    "input_train = input[:N_FILES_train]\n",
-    "input_test = input[N_FILES_train:]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "(189, 3)"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "input.shape"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Define regression model and load scaler\n",
-    "alpha = 1e-9\n",
-    "input_size = input.shape[1]\n",
-    "kernel = 0.01 * RBF(length_scale=[0.1]*input_size, length_scale_bounds=(1e-2, 1e+2)) \\\n",
-    "                + WhiteKernel(noise_level=alpha, noise_level_bounds=(1e-10, 1e0))\n",
-    "regressor = GaussianProcessRegressor(kernel=kernel, normalize_y=False, n_restarts_optimizer=10)\n",
-    "method = MultiOutputRegressor(regressor)\n",
-    "return_SV = True # return singular values for the POD\n",
-    "scaler_velocities = joblib.load('../Data/POD/scaler_velocity.pkl')\n",
-    "scaler_pressure = joblib.load('../Data/POD/scaler_pressure.pkl')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Visualize the singular values"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1000x500 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "U_, S_velocities, V_ = np.linalg.svd(velocities_train)\n",
-    "U_, S_pressure, V_ = np.linalg.svd(pressure_train)\n",
-    "\n",
-    "fig, axs = plt.subplots(1, 2, figsize=(10, 5))\n",
-    "axs[0].plot(S_velocities)\n",
-    "axs[0].grid()\n",
-    "axs[0].set_title('Singular Values of Velocity Matrix')\n",
-    "axs[0].set_xlabel('Singular Value Index')\n",
-    "axs[0].set_ylabel('Singular Value')\n",
-    "axs[1].plot(S_pressure)\n",
-    "axs[1].grid()\n",
-    "axs[1].set_title('Singular Values of Pressure Matrix')\n",
-    "axs[1].set_xlabel('Singular Value Index')\n",
-    "axs[1].set_ylabel('Singular Value')\n",
-    "plt.show()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Verify model for different R-values"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def verify_model(model, input_, scaler_, test_data):\n",
-    "    relative_max_error = []\n",
-    "    root_mean_squared_error_list = []\n",
-    "    r2 = []\n",
-    "    for i in range(input_.shape[0]):\n",
-    "        predicted_values = model.predict(input_[i,:].reshape(1, -1)).reshape(-1,1)\n",
-    "        predicted_ = scaler_.inverse_transform(predicted_values)\n",
-    "\n",
-    "        comparison_ = scaler_.inverse_transform(test_data[i,:].reshape(1, -1)).reshape(-1,1)\n",
-    "\n",
-    "        max_error_ = max_error(comparison_, predicted_)\n",
-    "        relative_max_error_ = mean_absolute_percentage_error(comparison_, predicted_)\n",
-    "        rmse_ = root_mean_squared_error(comparison_, predicted_)\n",
-    "        r2_ = r2_score(comparison_, predicted_)\n",
-    "\n",
-    "        # max_error_list.append(max_error_)\n",
-    "        relative_max_error.append(relative_max_error_)\n",
-    "        root_mean_squared_error_list.append(rmse_)\n",
-    "        r2.append(r2_)\n",
-    "\n",
-    "    return np.array(relative_max_error).mean(), np.array(root_mean_squared_error_list).mean(), np.array(r2).mean()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "R = 10\n",
-    "# model_velocities, S_velocities = POD(velocities_train, input_train, R, method, return_SV)\n",
-    "\n",
-    "U, S, V = np.linalg.svd(velocities_train)\n",
-    "\n",
-    "U_r = U[:, :R]\n",
-    "S_r = np.diag(S[:R])\n",
-    "V_r = V[:R, :]\n",
-    "\n",
-    "X_r = U_r @ (S_r @ V_r)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "alpha = 1e-9\n",
-    "input_size = input.shape[1]\n",
-    "kernel = 0.01 * RBF(length_scale=[0.1]*input_size, length_scale_bounds=(1e-2, 1e+2)) \\\n",
-    "                + WhiteKernel(noise_level=alpha, noise_level_bounds=(1e-10, 1e0))\n",
-    "regressor = GaussianProcessRegressor(kernel=kernel, normalize_y=False, n_restarts_optimizer=10)\n",
-    "model = MultiOutputRegressor(regressor)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n"
-     ]
-    }
-   ],
-   "source": [
-    "model.fit(input_train, X_r)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:452: ConvergenceWarning: The optimal value found for dimension 0 of parameter k2__noise_level is close to the specified upper bound 1.0. Increasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 0 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n",
-      "/home/jan/miniconda3/envs/POD/lib/python3.12/site-packages/sklearn/gaussian_process/kernels.py:442: ConvergenceWarning: The optimal value found for dimension 2 of parameter k1__k2__length_scale is close to the specified lower bound 0.01. Decreasing the bound and calling fit again may find a better value.\n",
-      "  warnings.warn(\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Compute L2, Linfty and R2 value for the testing data on different number of modes\n",
-    "# R_vec = np.arange(1, 21)\n",
-    "R_vec = [5, 10, 15, 20]\n",
-    "# R_vec = [5, 10]\n",
-    "relative_max_error_velocities, relative_max_error_pressure = [], []\n",
-    "rmse_velocities, rmse_pressure = [], []\n",
-    "r2_velocities, r2_pressure = [], []\n",
-    "for R in R_vec:\n",
-    "    model_velocities, S_velocities = POD(velocities_train, input_train, R, method, return_SV)\n",
-    "    model_pressure, S_pressure = POD(pressure_train, input_train, R, method, return_SV)\n",
-    "\n",
-    "    relative_max_error_velocities_, rmse_velocities_, r2_velocities_ = verify_model(model_velocities, input_test, scaler_velocities, velocities_test)\n",
-    "    relative_max_error_pressure_, rmse_pressure_, r2_pressure_ = verify_model(model_pressure, input_test, scaler_pressure, pressure_test)\n",
-    "\n",
-    "    relative_max_error_velocities.append(relative_max_error_velocities_)\n",
-    "    rmse_velocities.append(rmse_velocities_)\n",
-    "    r2_velocities.append(r2_velocities_)\n",
-    "    relative_max_error_pressure.append(relative_max_error_pressure_)\n",
-    "    rmse_pressure.append(rmse_pressure_)\n",
-    "    r2_pressure.append(r2_pressure_)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "ValueError",
-     "evalue": "x and y must have same first dimension, but have shapes (20,) and (0,)",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[14], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m fig, axs \u001b[38;5;241m=\u001b[39m plt\u001b[38;5;241m.\u001b[39msubplots(\u001b[38;5;241m2\u001b[39m, \u001b[38;5;241m3\u001b[39m, figsize\u001b[38;5;241m=\u001b[39m(\u001b[38;5;241m15\u001b[39m, \u001b[38;5;241m10\u001b[39m))\n\u001b[0;32m----> 2\u001b[0m \u001b[43maxs\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m,\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplot\u001b[49m\u001b[43m(\u001b[49m\u001b[43mR_vec\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrelative_max_error_velocities\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m      3\u001b[0m axs[\u001b[38;5;241m0\u001b[39m,\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mgrid()\n\u001b[1;32m      4\u001b[0m axs[\u001b[38;5;241m0\u001b[39m,\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mset_xlabel(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mNumber of modes\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
-      "File \u001b[0;32m~/miniconda3/envs/POD/lib/python3.12/site-packages/matplotlib/axes/_axes.py:1779\u001b[0m, in \u001b[0;36mAxes.plot\u001b[0;34m(self, scalex, scaley, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1536\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m   1537\u001b[0m \u001b[38;5;124;03mPlot y versus x as lines and/or markers.\u001b[39;00m\n\u001b[1;32m   1538\u001b[0m \n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1776\u001b[0m \u001b[38;5;124;03m(``'green'``) or hex strings (``'#008000'``).\u001b[39;00m\n\u001b[1;32m   1777\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m   1778\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m cbook\u001b[38;5;241m.\u001b[39mnormalize_kwargs(kwargs, mlines\u001b[38;5;241m.\u001b[39mLine2D)\n\u001b[0;32m-> 1779\u001b[0m lines \u001b[38;5;241m=\u001b[39m [\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_lines(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;241m*\u001b[39margs, data\u001b[38;5;241m=\u001b[39mdata, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)]\n\u001b[1;32m   1780\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m line \u001b[38;5;129;01min\u001b[39;00m lines:\n\u001b[1;32m   1781\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39madd_line(line)\n",
-      "File \u001b[0;32m~/miniconda3/envs/POD/lib/python3.12/site-packages/matplotlib/axes/_base.py:296\u001b[0m, in \u001b[0;36m_process_plot_var_args.__call__\u001b[0;34m(self, axes, data, *args, **kwargs)\u001b[0m\n\u001b[1;32m    294\u001b[0m     this \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m args[\u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m    295\u001b[0m     args \u001b[38;5;241m=\u001b[39m args[\u001b[38;5;241m1\u001b[39m:]\n\u001b[0;32m--> 296\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_plot_args\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    297\u001b[0m \u001b[43m    \u001b[49m\u001b[43maxes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mthis\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mambiguous_fmt_datakey\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mambiguous_fmt_datakey\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/miniconda3/envs/POD/lib/python3.12/site-packages/matplotlib/axes/_base.py:486\u001b[0m, in \u001b[0;36m_process_plot_var_args._plot_args\u001b[0;34m(self, axes, tup, kwargs, return_kwargs, ambiguous_fmt_datakey)\u001b[0m\n\u001b[1;32m    483\u001b[0m     axes\u001b[38;5;241m.\u001b[39myaxis\u001b[38;5;241m.\u001b[39mupdate_units(y)\n\u001b[1;32m    485\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m x\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;241m!=\u001b[39m y\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m0\u001b[39m]:\n\u001b[0;32m--> 486\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mx and y must have same first dimension, but \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    487\u001b[0m                      \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhave shapes \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mx\u001b[38;5;241m.\u001b[39mshape\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m and \u001b[39m\u001b[38;5;132;01m{\u001b[39;00my\u001b[38;5;241m.\u001b[39mshape\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m    488\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m x\u001b[38;5;241m.\u001b[39mndim \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m2\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m y\u001b[38;5;241m.\u001b[39mndim \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m2\u001b[39m:\n\u001b[1;32m    489\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mx and y can be no greater than 2D, but have \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    490\u001b[0m                      \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mshapes \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mx\u001b[38;5;241m.\u001b[39mshape\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m and \u001b[39m\u001b[38;5;132;01m{\u001b[39;00my\u001b[38;5;241m.\u001b[39mshape\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
-      "\u001b[0;31mValueError\u001b[0m: x and y must have same first dimension, but have shapes (20,) and (0,)"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1500x1000 with 6 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "fig, axs = plt.subplots(2, 3, figsize=(15, 10))\n",
-    "axs[0,0].plot(R_vec, relative_max_error_velocities)\n",
-    "axs[0,0].grid()\n",
-    "axs[0,0].set_xlabel('Number of modes')\n",
-    "axs[0,0].set_ylabel('Relative max error')\n",
-    "axs[0,0].set_title('Relative max error for velocities')\n",
-    "axs[0,1].plot(R_vec, rmse_velocities)\n",
-    "axs[0,1].grid()\n",
-    "axs[0,1].set_xlabel('Number of modes')\n",
-    "axs[0,1].set_ylabel('RMSE')\n",
-    "axs[0,1].set_title('RMSE for velocities')\n",
-    "axs[0,2].plot(R_vec, r2_velocities)\n",
-    "axs[0,2].grid()\n",
-    "axs[0,2].set_xlabel('Number of modes')\n",
-    "axs[0,2].set_ylabel('R2')\n",
-    "axs[0,2].set_title('R2 for velocities')\n",
-    "\n",
-    "axs[1,0].plot(R_vec, relative_max_error_pressure)\n",
-    "axs[1,0].grid()\n",
-    "axs[1,0].set_xlabel('Number of modes')\n",
-    "axs[1,0].set_ylabel('Relative max error')\n",
-    "axs[1,0].set_title('Relative max error for pressure')\n",
-    "axs[1,1].plot(R_vec, rmse_pressure)\n",
-    "axs[1,1].grid()\n",
-    "axs[1,1].set_xlabel('Number of modes')\n",
-    "axs[1,1].set_ylabel('RMSE')\n",
-    "axs[1,1].set_title('RMSE for pressuree')\n",
-    "axs[1,2].plot(R_vec, r2_pressure)\n",
-    "axs[1,2].grid()\n",
-    "axs[1,2].set_xlabel('Number of modes')\n",
-    "axs[1,2].set_ylabel('R2')\n",
-    "axs[1,2].set_title('R2 for pressure')\n",
-    "fig.tight_layout()\n",
-    "fig.show()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "POD",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/POD_LinearRegression.ipynb b/POD_LinearRegression.ipynb
deleted file mode 100644
index 58529cdc181ffeda2f35d5dc777cd20d8fe9d5ba..0000000000000000000000000000000000000000
--- a/POD_LinearRegression.ipynb
+++ /dev/null
@@ -1,273 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import pandas as pd \n",
-    "import matplotlib.pyplot as plt\n",
-    "from sklearn.linear_model import LinearRegression\n",
-    "from sklearn.metrics import max_error, r2_score, root_mean_squared_error, mean_absolute_percentage_error\n",
-    "import joblib\n",
-    "from scipy.optimize import differential_evolution\n",
-    "from POD import POD, predict, verify"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load the data\n",
-    "velocities_path = '../Data/POD/VelocityMatrix_scaled.csv'\n",
-    "pressure_path = '../Data/POD/PressureMatrix_scaled.csv'\n",
-    "\n",
-    "velocities = np.loadtxt(velocities_path)\n",
-    "pressure = np.loadtxt(pressure_path)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Divide the data into training and testing sets#\n",
-    "# Get training and data splits\n",
-    "df = pd.read_excel('../Data/HollowOctagon_Setup.xlsx').transpose()[0]\n",
-    "N_FILES_train = df['N_SIZES_TRAIN']\n",
-    "N_FILES_test = df['N_SIZES_TEST']\n",
-    "N_FILES = N_FILES_train + N_FILES_test\n",
-    "\n",
-    "# Get the training and testing data\n",
-    "velocities_train = velocities[:N_FILES_train]\n",
-    "velocities_test = velocities[N_FILES_train:]\n",
-    "pressure_train = pressure[:N_FILES_train]\n",
-    "pressure_test = pressure[N_FILES_train:]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load input parameters\n",
-    "input_path = '../Data/HollowOctagon_Sizes.xlsx'\n",
-    "input = pd.read_excel(input_path, index_col=0).to_numpy()\n",
-    "input_train = input[:N_FILES_train]\n",
-    "input_test = input[N_FILES_train:]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Define regression model and load scaler\n",
-    "method = LinearRegression()\n",
-    "return_SV = True # return singular values for the POD\n",
-    "scaler_velocities = joblib.load('../Data/POD/scaler_velocity.pkl')\n",
-    "scaler_pressure = joblib.load('../Data/POD/scaler_pressure.pkl')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Visualize the singular values"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1000x500 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "U_, S_velocities, V_ = np.linalg.svd(velocities_train)\n",
-    "U_, S_pressure, V_ = np.linalg.svd(pressure_train)\n",
-    "\n",
-    "fig, axs = plt.subplots(1, 2, figsize=(10, 5))\n",
-    "axs[0].plot(S_velocities)\n",
-    "axs[0].grid()\n",
-    "axs[0].set_title('Singular Values of Velocity Matrix')\n",
-    "axs[0].set_xlabel('Singular Value Index')\n",
-    "axs[0].set_ylabel('Singular Value')\n",
-    "axs[1].plot(S_pressure)\n",
-    "axs[1].grid()\n",
-    "axs[1].set_title('Singular Values of Pressure Matrix')\n",
-    "axs[1].set_xlabel('Singular Value Index')\n",
-    "axs[1].set_ylabel('Singular Value')\n",
-    "plt.show()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Verify model for different R-values"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def verify_model(model, input_, scaler_, test_data):\n",
-    "    relative_max_error = []\n",
-    "    root_mean_squared_error_list = []\n",
-    "    r2 = []\n",
-    "    for i in range(input_.shape[0]):\n",
-    "        predicted_values = model.predict(input_[i,:].reshape(1, -1)).reshape(-1,1)\n",
-    "        predicted_ = scaler_.inverse_transform(predicted_values)\n",
-    "\n",
-    "        comparison_ = scaler_.inverse_transform(test_data[i,:].reshape(1, -1)).reshape(-1,1)\n",
-    "\n",
-    "        max_error_ = max_error(comparison_, predicted_)\n",
-    "        relative_max_error_ = mean_absolute_percentage_error(comparison_, predicted_)\n",
-    "        rmse_ = root_mean_squared_error(comparison_, predicted_)\n",
-    "        r2_ = r2_score(comparison_, predicted_)\n",
-    "\n",
-    "        # max_error_list.append(max_error_)\n",
-    "        relative_max_error.append(relative_max_error_)\n",
-    "        root_mean_squared_error_list.append(rmse_)\n",
-    "        r2.append(r2_)\n",
-    "\n",
-    "    return np.array(relative_max_error).mean(), np.array(root_mean_squared_error_list).mean(), np.array(r2).mean()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Compute L2, Linfty and R2 value for the testing data on different number of modes\n",
-    "R_vec = np.arange(1, 21)\n",
-    "# R_vec = [5, 10]\n",
-    "relative_max_error_velocities, relative_max_error_pressure = [], []\n",
-    "rmse_velocities, rmse_pressure = [], []\n",
-    "r2_velocities, r2_pressure = [], []\n",
-    "for R in R_vec:\n",
-    "    model_velocities, S_velocities = POD(velocities_train, input_train, R, method, return_SV)\n",
-    "    model_pressure, S_pressure = POD(pressure_train, input_train, R, method, return_SV)\n",
-    "\n",
-    "    relative_max_error_velocities_, rmse_velocities_, r2_velocities_ = verify_model(model_velocities, input_test, scaler_velocities, velocities_test)\n",
-    "    relative_max_error_pressure_, rmse_pressure_, r2_pressure_ = verify_model(model_pressure, input_test, scaler_pressure, pressure_test)\n",
-    "\n",
-    "    relative_max_error_velocities.append(relative_max_error_velocities_)\n",
-    "    rmse_velocities.append(rmse_velocities_)\n",
-    "    r2_velocities.append(r2_velocities_)\n",
-    "    relative_max_error_pressure.append(relative_max_error_pressure_)\n",
-    "    rmse_pressure.append(rmse_pressure_)\n",
-    "    r2_pressure.append(r2_pressure_)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/tmp/ipykernel_6138/3907870628.py:34: UserWarning: FigureCanvasAgg is non-interactive, and thus cannot be shown\n",
-      "  fig.show()\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1500x1000 with 6 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "fig, axs = plt.subplots(2, 3, figsize=(15, 10))\n",
-    "axs[0,0].plot(R_vec, relative_max_error_velocities)\n",
-    "axs[0,0].grid()\n",
-    "axs[0,0].set_xlabel('Number of modes')\n",
-    "axs[0,0].set_ylabel('Relative max error')\n",
-    "axs[0,0].set_title('Relative max error for velocities')\n",
-    "axs[0,1].plot(R_vec, rmse_velocities)\n",
-    "axs[0,1].grid()\n",
-    "axs[0,1].set_xlabel('Number of modes')\n",
-    "axs[0,1].set_ylabel('RMSE')\n",
-    "axs[0,1].set_title('RMSE for velocities')\n",
-    "axs[0,2].plot(R_vec, r2_velocities)\n",
-    "axs[0,2].grid()\n",
-    "axs[0,2].set_xlabel('Number of modes')\n",
-    "axs[0,2].set_ylabel('R2')\n",
-    "axs[0,2].set_title('R2 for velocities')\n",
-    "\n",
-    "axs[1,0].plot(R_vec, relative_max_error_pressure)\n",
-    "axs[1,0].grid()\n",
-    "axs[1,0].set_xlabel('Number of modes')\n",
-    "axs[1,0].set_ylabel('Relative max error')\n",
-    "axs[1,0].set_title('Relative max error for pressure')\n",
-    "axs[1,1].plot(R_vec, rmse_pressure)\n",
-    "axs[1,1].grid()\n",
-    "axs[1,1].set_xlabel('Number of modes')\n",
-    "axs[1,1].set_ylabel('RMSE')\n",
-    "axs[1,1].set_title('RMSE for pressuree')\n",
-    "axs[1,2].plot(R_vec, r2_pressure)\n",
-    "axs[1,2].grid()\n",
-    "axs[1,2].set_xlabel('Number of modes')\n",
-    "axs[1,2].set_ylabel('R2')\n",
-    "axs[1,2].set_title('R2 for pressure')\n",
-    "fig.tight_layout()\n",
-    "fig.show()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "POD",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/POD_RadialBasisFunctions.ipynb b/POD_RadialBasisFunctions.ipynb
deleted file mode 100644
index 3abd0e8e3758bc566c726c2fd331d34879c1df6e..0000000000000000000000000000000000000000
--- a/POD_RadialBasisFunctions.ipynb
+++ /dev/null
@@ -1,301 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import pandas as pd \n",
-    "import matplotlib.pyplot as plt\n",
-    "from sklearn.gaussian_process import GaussianProcessRegressor\n",
-    "from sklearn.gaussian_process.kernels import RBF\n",
-    "import scipy.interpolate\n",
-    "from sklearn.metrics import max_error, r2_score, root_mean_squared_error, mean_absolute_percentage_error\n",
-    "import joblib\n",
-    "from scipy.optimize import differential_evolution\n",
-    "from POD import POD, predict, verify"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load the data\n",
-    "velocities_path = '../Data/POD/VelocityMatrix_scaled.csv'\n",
-    "pressure_path = '../Data/POD/PressureMatrix_scaled.csv'\n",
-    "\n",
-    "velocities = np.loadtxt(velocities_path)\n",
-    "pressure = np.loadtxt(pressure_path)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Divide the data into training and testing sets#\n",
-    "# Get training and data splits\n",
-    "df = pd.read_excel('../Data/HollowOctagon_Setup.xlsx').transpose()[0]\n",
-    "N_FILES_train = df['N_SIZES_TRAIN']\n",
-    "N_FILES_test = df['N_SIZES_TEST']\n",
-    "N_FILES = N_FILES_train + N_FILES_test\n",
-    "\n",
-    "# Get the training and testing data\n",
-    "velocities_train = velocities[:N_FILES_train]\n",
-    "velocities_test = velocities[N_FILES_train:]\n",
-    "pressure_train = pressure[:N_FILES_train]\n",
-    "pressure_test = pressure[N_FILES_train:]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load input parameters\n",
-    "input_path = '../Data/HollowOctagon_Sizes.xlsx'\n",
-    "input = pd.read_excel(input_path, index_col=0).to_numpy()\n",
-    "input_train = input[:N_FILES_train]\n",
-    "input_test = input[N_FILES_train:]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "scaler_velocities = joblib.load('../Data/POD/scaler_velocity.pkl')\n",
-    "scaler_pressure = joblib.load('../Data/POD/scaler_pressure.pkl')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def POD(results_matrix, param_matrix_train, R, return_SV=False):\n",
-    "    # # Read parameter matrix\n",
-    "    # parameter_matrix = pd.read_excel(parameter_path, index_col=0)\n",
-    "    # parameter_matrix = parameter_matrix.to_numpy()\n",
-    "\n",
-    "    # Perform POD\n",
-    "    U, S, V = np.linalg.svd(results_matrix)\n",
-    "\n",
-    "    U_r = U[:, :R]\n",
-    "    S_r = np.diag(S[:R])\n",
-    "    V_r = V[:R, :]\n",
-    "\n",
-    "    X_r = U_r @ (S_r @ V_r)\n",
-    "\n",
-    "    # Train regression model for reduced velocity matrix\n",
-    "    model = scipy.interpolate.Rbf(*param_matrix_train.T, X_r, function='multiquadric', mode='N-D'), \n",
-    "    # model.fit(param_matrix_train, X_r)\n",
-    "\n",
-    "    if return_SV:\n",
-    "        return model, S\n",
-    "    return model"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Visualize the singular values"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 32,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1000x500 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "U_, S_velocities, V_ = np.linalg.svd(velocities_train)\n",
-    "U_, S_pressure, V_ = np.linalg.svd(pressure_train)\n",
-    "\n",
-    "fig, axs = plt.subplots(1, 2, figsize=(10, 5))\n",
-    "axs[0].plot(S_velocities)\n",
-    "axs[0].grid()\n",
-    "axs[0].set_title('Singular Values of Velocity Matrix')\n",
-    "axs[0].set_xlabel('Singular Value Index')\n",
-    "axs[0].set_ylabel('Singular Value')\n",
-    "axs[1].plot(S_pressure)\n",
-    "axs[1].grid()\n",
-    "axs[1].set_title('Singular Values of Pressure Matrix')\n",
-    "axs[1].set_xlabel('Singular Value Index')\n",
-    "axs[1].set_ylabel('Singular Value')\n",
-    "plt.show()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Verify model for different R-values"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def verify_model(model, input_, scaler_, test_data):\n",
-    "    relative_max_error = []\n",
-    "    root_mean_squared_error_list = []\n",
-    "    r2 = []\n",
-    "    for i in range(input_.shape[0]):\n",
-    "        predicted_values = model[0](*input_[i,:]).reshape(-1,1)\n",
-    "        predicted_ = scaler_.inverse_transform(predicted_values)\n",
-    "\n",
-    "        comparison_ = scaler_.inverse_transform(test_data[i,:].reshape(1, -1)).reshape(-1,1)\n",
-    "\n",
-    "        max_error_ = max_error(comparison_, predicted_)\n",
-    "        relative_max_error_ = mean_absolute_percentage_error(comparison_, predicted_)\n",
-    "        rmse_ = root_mean_squared_error(comparison_, predicted_)\n",
-    "        r2_ = r2_score(comparison_, predicted_)\n",
-    "\n",
-    "        # max_error_list.append(max_error_)\n",
-    "        relative_max_error.append(relative_max_error_)\n",
-    "        root_mean_squared_error_list.append(rmse_)\n",
-    "        r2.append(r2_)\n",
-    "\n",
-    "    return np.array(relative_max_error).mean(), np.array(root_mean_squared_error_list).mean(), np.array(r2).mean()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 62,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Compute L2, Linfty and R2 value for the testing data on different number of modes\n",
-    "R_vec = np.arange(1, 21)\n",
-    "# R_vec = [5, 10]\n",
-    "relative_max_error_velocities, relative_max_error_pressure = [], []\n",
-    "rmse_velocities, rmse_pressure = [], []\n",
-    "r2_velocities, r2_pressure = [], []\n",
-    "for R in R_vec:\n",
-    "    model_velocities = POD(velocities_train, input_train, R)\n",
-    "    model_pressure = POD(pressure_train, input_train, R)\n",
-    "\n",
-    "    relative_max_error_velocities_, rmse_velocities_, r2_velocities_ = verify_model(model_velocities, input_test, scaler_velocities, velocities_test)\n",
-    "    relative_max_error_pressure_, rmse_pressure_, r2_pressure_ = verify_model(model_pressure, input_test, scaler_pressure, pressure_test)\n",
-    "\n",
-    "    relative_max_error_velocities.append(relative_max_error_velocities_)\n",
-    "    rmse_velocities.append(rmse_velocities_)\n",
-    "    r2_velocities.append(r2_velocities_)\n",
-    "    relative_max_error_pressure.append(relative_max_error_pressure_)\n",
-    "    rmse_pressure.append(rmse_pressure_)\n",
-    "    r2_pressure.append(r2_pressure_)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 63,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/tmp/ipykernel_35108/3907870628.py:34: UserWarning: FigureCanvasAgg is non-interactive, and thus cannot be shown\n",
-      "  fig.show()\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1500x1000 with 6 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "fig, axs = plt.subplots(2, 3, figsize=(15, 10))\n",
-    "axs[0,0].plot(R_vec, relative_max_error_velocities)\n",
-    "axs[0,0].grid()\n",
-    "axs[0,0].set_xlabel('Number of modes')\n",
-    "axs[0,0].set_ylabel('Relative max error')\n",
-    "axs[0,0].set_title('Relative max error for velocities')\n",
-    "axs[0,1].plot(R_vec, rmse_velocities)\n",
-    "axs[0,1].grid()\n",
-    "axs[0,1].set_xlabel('Number of modes')\n",
-    "axs[0,1].set_ylabel('RMSE')\n",
-    "axs[0,1].set_title('RMSE for velocities')\n",
-    "axs[0,2].plot(R_vec, r2_velocities)\n",
-    "axs[0,2].grid()\n",
-    "axs[0,2].set_xlabel('Number of modes')\n",
-    "axs[0,2].set_ylabel('R2')\n",
-    "axs[0,2].set_title('R2 for velocities')\n",
-    "\n",
-    "axs[1,0].plot(R_vec, relative_max_error_pressure)\n",
-    "axs[1,0].grid()\n",
-    "axs[1,0].set_xlabel('Number of modes')\n",
-    "axs[1,0].set_ylabel('Relative max error')\n",
-    "axs[1,0].set_title('Relative max error for pressure')\n",
-    "axs[1,1].plot(R_vec, rmse_pressure)\n",
-    "axs[1,1].grid()\n",
-    "axs[1,1].set_xlabel('Number of modes')\n",
-    "axs[1,1].set_ylabel('RMSE')\n",
-    "axs[1,1].set_title('RMSE for pressuree')\n",
-    "axs[1,2].plot(R_vec, r2_pressure)\n",
-    "axs[1,2].grid()\n",
-    "axs[1,2].set_xlabel('Number of modes')\n",
-    "axs[1,2].set_ylabel('R2')\n",
-    "axs[1,2].set_title('R2 for pressure')\n",
-    "fig.tight_layout()\n",
-    "fig.show()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "POD",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/README.md b/README.md
index e786f7e0a899af0a5afc2b1ec7428a524f239f0c..d6663526f924e0aa81b4adcabad6c317db1ebd52 100644
--- a/README.md
+++ b/README.md
@@ -42,7 +42,7 @@ The used program is the `stokes_example` in `build/bin` and was moved to this re
 - Jan.Habscheid@rwth-aachen.de
 
 **Supervisor**
-- Mark Rieg
+- Mark Riegler
 - Computational Analysis of Technical Systems
 - RWTH Aachen University
 - riegler@cats.rwth-aachen.de
\ No newline at end of file
diff --git a/Results/gaussianProcessMod/OptimalSetup.npz b/Results/gaussianProcessMod/OptimalSetup.npz
index 55b2c6443f2ec4bda6eac12fa610a69c209c7675..6f7c7182a62004c5a70949d0d2536802c892fa2b 100644
Binary files a/Results/gaussianProcessMod/OptimalSetup.npz and b/Results/gaussianProcessMod/OptimalSetup.npz differ
diff --git a/Results/gaussianProcessMod/errors.npz b/Results/gaussianProcessMod/errors.npz
index f54b8b3cc008a9c279d2e9e32b99732946e9e8e1..6597a19e76a0e7a64c7fc98014f936d06bb37177 100644
Binary files a/Results/gaussianProcessMod/errors.npz and b/Results/gaussianProcessMod/errors.npz differ
diff --git a/Results/gaussianProcessMod/errors_boxplot.jpg b/Results/gaussianProcessMod/errors_boxplot.jpg
index 00c54c7d8f2f24483496fe73790d078c70e52d27..3c80558257567ef779a51858b6735e889e9d8797 100644
Binary files a/Results/gaussianProcessMod/errors_boxplot.jpg and b/Results/gaussianProcessMod/errors_boxplot.jpg differ
diff --git a/Results/gaussianProcessMod/sample0.jpg b/Results/gaussianProcessMod/sample0.jpg
index 134b388465e7c3bd425398f07811ad5912cf07a5..90ceb8ee37d2f547a5f0e07b9177765cfad3e6ce 100644
Binary files a/Results/gaussianProcessMod/sample0.jpg and b/Results/gaussianProcessMod/sample0.jpg differ
diff --git a/Results/gaussianProcessMod/sample0_zoom.jpg b/Results/gaussianProcessMod/sample0_zoom.jpg
index 935815420fbe429bec276ee864057a07638b37a3..9d35c490aae4ccd1bc9080104aec5ddab2ed664b 100644
Binary files a/Results/gaussianProcessMod/sample0_zoom.jpg and b/Results/gaussianProcessMod/sample0_zoom.jpg differ
diff --git a/Results/gaussianProcessMod/singular_values.jpg b/Results/gaussianProcessMod/singular_values.jpg
index b31f186763a8f27e09ac2986ee0884cf2b95ce74..f76f75413355c270d86dab778c5cc09afa957988 100644
Binary files a/Results/gaussianProcessMod/singular_values.jpg and b/Results/gaussianProcessMod/singular_values.jpg differ
diff --git a/Results/linregMod/OptimalSetup.npz b/Results/linregMod/OptimalSetup.npz
index a5720fd3c08a93ece74dfb453ba27e98968354b3..f43f445078fd09e3c09d896dc97457171c05e0cd 100644
Binary files a/Results/linregMod/OptimalSetup.npz and b/Results/linregMod/OptimalSetup.npz differ
diff --git a/Results/linregMod/errors.npz b/Results/linregMod/errors.npz
index 9679e183ffd8af69aed27e3d1f368fe10adecf68..6ef5324bb7d6638734626d70c09772479101d352 100644
Binary files a/Results/linregMod/errors.npz and b/Results/linregMod/errors.npz differ
diff --git a/Results/linregMod/errors_boxplot.jpg b/Results/linregMod/errors_boxplot.jpg
index a8f2b74f7e30e4b31e7521fa8f0e2c968a2a11a2..86754d0652ddb93cf69d0939e98f5bf9ace5d2c9 100644
Binary files a/Results/linregMod/errors_boxplot.jpg and b/Results/linregMod/errors_boxplot.jpg differ
diff --git a/Results/linregMod/sample0.jpg b/Results/linregMod/sample0.jpg
index 0efeae26fcc421e3f2be739a7d16170c11710051..54a95089b772c630520b68bef27c8e5191de9f3d 100644
Binary files a/Results/linregMod/sample0.jpg and b/Results/linregMod/sample0.jpg differ
diff --git a/Results/linregMod/sample0_zoom.jpg b/Results/linregMod/sample0_zoom.jpg
index ee4bf63791e39b04698a8c994904c62ac5d48b9c..29ddb0119dec6778f27d405a2e9c20ad4383b079 100644
Binary files a/Results/linregMod/sample0_zoom.jpg and b/Results/linregMod/sample0_zoom.jpg differ
diff --git a/Results/linregMod/singular_values.jpg b/Results/linregMod/singular_values.jpg
index 3bdd1131a32477da380b02de9f870622684b63a2..c509a68bab58533dd97fb8cd9d88206c756b642d 100644
Binary files a/Results/linregMod/singular_values.jpg and b/Results/linregMod/singular_values.jpg differ
diff --git a/Results/radialBasisMod/OptimalSetup.npz b/Results/radialBasisMod/OptimalSetup.npz
index 70f1b8703751c6161cdb41c9727986e92ea6f565..9f90599b8173c736ee1c5a74d1ca7625c3cc0b23 100644
Binary files a/Results/radialBasisMod/OptimalSetup.npz and b/Results/radialBasisMod/OptimalSetup.npz differ
diff --git a/Results/radialBasisMod/errors.npz b/Results/radialBasisMod/errors.npz
index 9ac5acf08bc8bc6f8b420a6dbd292b6656872571..21c1f484852878041419afe8401916a9fb70b8a3 100644
Binary files a/Results/radialBasisMod/errors.npz and b/Results/radialBasisMod/errors.npz differ
diff --git a/Results/radialBasisMod/errors_boxplot.jpg b/Results/radialBasisMod/errors_boxplot.jpg
index 74bec30adf26d82544b5dabfb38a168c8c411140..6a9b14ccad96827129ce744ee7ab1d0c309f28ca 100644
Binary files a/Results/radialBasisMod/errors_boxplot.jpg and b/Results/radialBasisMod/errors_boxplot.jpg differ
diff --git a/Results/radialBasisMod/sample0.jpg b/Results/radialBasisMod/sample0.jpg
index 0ccf1fa7b1f70de071b907283eb4501e686a8e4a..1b068d68906480ea90b9b31cad34bd7b0108df1c 100644
Binary files a/Results/radialBasisMod/sample0.jpg and b/Results/radialBasisMod/sample0.jpg differ
diff --git a/Results/radialBasisMod/sample0_zoom.jpg b/Results/radialBasisMod/sample0_zoom.jpg
index bcf52381922e4bac6c5e285e71cefbfeb48c6a86..53e2f877da18ff2b667478a2e05a60d05d3ffd1e 100644
Binary files a/Results/radialBasisMod/sample0_zoom.jpg and b/Results/radialBasisMod/sample0_zoom.jpg differ
diff --git a/Results/radialBasisMod/singular_values.jpg b/Results/radialBasisMod/singular_values.jpg
index 37910601abd79bcd496a42e50be33b7667c09cf9..e1b90e5348726462d7bafa2476034f86fb9420de 100644
Binary files a/Results/radialBasisMod/singular_values.jpg and b/Results/radialBasisMod/singular_values.jpg differ
diff --git a/gismo/GenerateMicrostructures_fun.py b/gismo/GenerateMicrostructures_fun.py
index a10c0a03cfa0a98b29171d2ab07b5510a95058c7..bcd7590076036b5c4cad1b6dfa0fec60f56c3855 100644
--- a/gismo/GenerateMicrostructures_fun.py
+++ b/gismo/GenerateMicrostructures_fun.py
@@ -3,7 +3,7 @@ import numpy as np
 import splinepy as sp
 import pandas as pd
 
-from gismo_export import AdditionalBlocks, export
+from gismo.gismo_export import AdditionalBlocks, export
 
 def generate(size_1, size_2, size_3, BOX_LENGTH, BOX_HEIGHT, EPS, INLET_BOUNDARY_ID, OUTLET_BOUNDARY_ID, knots_y, TILING, CLOSING_FACE, MICROTILE):
     # Define microstructure deformation function
diff --git a/gismo_export.py b/gismo/gismo_export.py
similarity index 100%
rename from gismo_export.py
rename to gismo/gismo_export.py
diff --git a/models/trained_models/gaussianProcessMod/pressure_6.pkl b/models/trained_models/gaussianProcessMod/pressure_6.pkl
deleted file mode 100644
index 975057ae93a9b2fba1fa0fd73ea86a23c9ce1290..0000000000000000000000000000000000000000
Binary files a/models/trained_models/gaussianProcessMod/pressure_6.pkl and /dev/null differ
diff --git a/models/trained_models/gaussianProcessMod/pressure_elbow.pkl b/models/trained_models/gaussianProcessMod/pressure_elbow.pkl
new file mode 100644
index 0000000000000000000000000000000000000000..09d2473146b41f38849b556f734c9ef768278d4b
Binary files /dev/null and b/models/trained_models/gaussianProcessMod/pressure_elbow.pkl differ
diff --git a/models/trained_models/gaussianProcessMod/velocity.pkl b/models/trained_models/gaussianProcessMod/velocity.pkl
index 816266fc0d4524eeae381312d3e2af76c38f833a..ec90580fd8d54985104b4b7d7461433932faac80 100644
Binary files a/models/trained_models/gaussianProcessMod/velocity.pkl and b/models/trained_models/gaussianProcessMod/velocity.pkl differ
diff --git a/models/trained_models/gaussianProcessMod/velocity_21.pkl b/models/trained_models/gaussianProcessMod/velocity_21.pkl
new file mode 100644
index 0000000000000000000000000000000000000000..ec90580fd8d54985104b4b7d7461433932faac80
Binary files /dev/null and b/models/trained_models/gaussianProcessMod/velocity_21.pkl differ
diff --git a/models/trained_models/gaussianProcessMod/velocity_8.pkl b/models/trained_models/gaussianProcessMod/velocity_8.pkl
deleted file mode 100644
index 7793a6ac2a3d20fba63233dd670fd762b15af0bd..0000000000000000000000000000000000000000
Binary files a/models/trained_models/gaussianProcessMod/velocity_8.pkl and /dev/null differ
diff --git a/models/trained_models/gaussianProcessMod/velocity_7.pkl b/models/trained_models/gaussianProcessMod/velocity_elbow.pkl
similarity index 100%
rename from models/trained_models/gaussianProcessMod/velocity_7.pkl
rename to models/trained_models/gaussianProcessMod/velocity_elbow.pkl
diff --git a/models/trained_models/linregMod/pressure.pkl b/models/trained_models/linregMod/pressure.pkl
index a09005c4123a47ef2c6716ba919efd6f7198f152..997399d941d49f131aed50da12a355230cfda2f3 100644
Binary files a/models/trained_models/linregMod/pressure.pkl and b/models/trained_models/linregMod/pressure.pkl differ
diff --git a/models/trained_models/linregMod/pressure_21.pkl b/models/trained_models/linregMod/pressure_21.pkl
new file mode 100644
index 0000000000000000000000000000000000000000..997399d941d49f131aed50da12a355230cfda2f3
Binary files /dev/null and b/models/trained_models/linregMod/pressure_21.pkl differ
diff --git a/models/trained_models/linregMod/pressure_4.pkl b/models/trained_models/linregMod/pressure_elbow.pkl
similarity index 100%
rename from models/trained_models/linregMod/pressure_4.pkl
rename to models/trained_models/linregMod/pressure_elbow.pkl
diff --git a/models/trained_models/linregMod/velocity.pkl b/models/trained_models/linregMod/velocity.pkl
index 8781e04795b263614db758d4bb98f37144e7e9c4..5d4a0a98a946bbc5e7f01512f4173fe7a04621e0 100644
Binary files a/models/trained_models/linregMod/velocity.pkl and b/models/trained_models/linregMod/velocity.pkl differ
diff --git a/models/trained_models/linregMod/velocity_21.pkl b/models/trained_models/linregMod/velocity_21.pkl
new file mode 100644
index 0000000000000000000000000000000000000000..5d4a0a98a946bbc5e7f01512f4173fe7a04621e0
Binary files /dev/null and b/models/trained_models/linregMod/velocity_21.pkl differ
diff --git a/models/trained_models/linregMod/velocity_7.pkl b/models/trained_models/linregMod/velocity_elbow.pkl
similarity index 100%
rename from models/trained_models/linregMod/velocity_7.pkl
rename to models/trained_models/linregMod/velocity_elbow.pkl
diff --git a/models/trained_models/radialBasisMod/pressure.pkl b/models/trained_models/radialBasisMod/pressure.pkl
index 3f0c79522255f16b785b7996bc14a7a5b9b11ba5..cd05971969aabd97b77097c80acecd0406cf9f9c 100644
Binary files a/models/trained_models/radialBasisMod/pressure.pkl and b/models/trained_models/radialBasisMod/pressure.pkl differ
diff --git a/models/trained_models/radialBasisMod/pressure_21.pkl b/models/trained_models/radialBasisMod/pressure_21.pkl
new file mode 100644
index 0000000000000000000000000000000000000000..cd05971969aabd97b77097c80acecd0406cf9f9c
Binary files /dev/null and b/models/trained_models/radialBasisMod/pressure_21.pkl differ
diff --git a/models/trained_models/radialBasisMod/pressure_4.pkl b/models/trained_models/radialBasisMod/pressure_elbow.pkl
similarity index 100%
rename from models/trained_models/radialBasisMod/pressure_4.pkl
rename to models/trained_models/radialBasisMod/pressure_elbow.pkl
diff --git a/models/trained_models/radialBasisMod/velocity_elbow.pkl b/models/trained_models/radialBasisMod/velocity_elbow.pkl
new file mode 100644
index 0000000000000000000000000000000000000000..15ce4e695f34c79a4c65b0f97dc5242b86c70c0e
Binary files /dev/null and b/models/trained_models/radialBasisMod/velocity_elbow.pkl differ