diff --git a/workflow_Tiankai_Li_Haogeng_Bai.ipynb b/workflow_Tiankai_Li_Haogeng_Bai.ipynb new file mode 100644 index 0000000000000000000000000000000000000000..1b5f5a50004eaf6f490f2dd1ae0cf65efa0c0b1d --- /dev/null +++ b/workflow_Tiankai_Li_Haogeng_Bai.ipynb @@ -0,0 +1,109 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "<img src=\"https://pad.gwdg.de/uploads/08e0f09e-ed2d-463f-8f92-e7ea3c661d18.png\" width=\"40%\">" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Computational Foundations of Digital Twin Technologies" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Bayesian Active Learning of Model Parameters to Increase Predictive Quality in Digital Twins of Flow-like Geohazards Main work packages\n", + "\n", + "## 1. Introduction to Bayesian Active Learning and Geohazard Prediction\n", + "- Overview of Bayesian active learning.\n", + "- Relevance in geohazard prediction and digital twin modeling.\n", + "\n", + "## 2. Deep Dive into the Article\n", + "- Analysis of Bayesian inference, Gaussian process emulation, active learning in the context of the article.\n", + "- Discussion on computational challenges and solutions.\n", + "\n", + "## 3. Practical Application and Tool Familiarization\n", + "- Hands-on session with PSimPy: Run predefined examples.\n", + "- Integration of Bayesian active learning in landslide modeling.\n", + "\n", + "## 4. Data Analysis and Model Calibration\n", + "- Replication of study scenarios from the article.\n", + "- Comparative analysis of posteriors for different observations.\n", + "- Impact of data error and observational types on model accuracy.\n", + "\n", + "## 5. Discussion and Critical Analysis\n", + "- Findings in the context of the article.\n", + "- Evaluation of Bayesian active learning approach effectiveness and limitations.\n", + "\n", + "\n", + "# Presentation on Bayesian Active Learning in Geohazard Prediction\n", + "\n", + "## Introduction\n", + "- Brief overview of Bayesian Active Learning.\n", + "- Its significance in geohazard prediction and modeling.\n", + "\n", + "## Article Insights\n", + "- Key concepts from the article on computational challenges in geohazard prediction.\n", + "- Solutions offered by Bayesian approaches.\n", + "\n", + "## Practical Session with PSimPy\n", + "- Demonstration of PSimPy for landslide modeling.\n", + "- Implementation of Bayesian Active Learning in practical scenarios.\n", + "\n", + "## Data Analysis and Results\n", + "- Analysis of different observational data types.\n", + "- Impact on model accuracy and predictions.\n", + "\n", + "## Critical Discussion\n", + "- Effectiveness and limitations of Bayesian Active Learning.\n", + "- Examples and insights from the article.\n", + "\n", + "## Conclusion\n", + "- Summary of findings.\n", + "- Future applications and potential advancements.\n", + "\n", + "## Q&A Session\n", + "- Open discussion and clarification of concepts.\n", + "\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "interpreter": { + "hash": "bb26e2ef932dc7666f98bbb35229998317c6141f0df4c346da4264046b0e9d5c" + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "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": "3.9.7" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +}