Modeling lab
CH-315
Media
Media
Welcome to "Modeling lab"
Welcome to this course! Please bring your LAPTOP to all classes!
- General Announcements (Forum)
- Course Introduction (File)
- Group review (Questionnaire)
- Group List (File)
Computational Carpentry
In this module, we set up the computational environment and learn the basics of the Python programming language.
You will find a quiz at the end of the section to test your knowledge and you will need this knowledge to work on the other modules.
Modeling Adsorption of Gases in Porous Materials
In this module, we learn how to use molecular simulations to understand and predict adsorption in porous materials. In Part 1, we review the Classical Thermodynamics of adsorption and in Part 2 we look at the Statistical Thermodynamics and discuss how molecular simulations are done. In Part 3 we present a tutorial on the use of AiiDA lab.
- COURSE PLAN: Modeling Adsorption of Gases in Porous Materials (Page)
- Part 1 (Text and media area)
- 1.1 Classical Thermodynamics: Equilibrium (URL)
- 1.2 Classical Thermodynamics: Langmuir Isotherms (URL)
- 1.3 Classical Thermodynamics: Henry Coefficients (URL)
- 1.4 Classical Thermodynamics: Temperature dependence of the Henry Coefficients (URL)
- 1.5 Classical Thermodynamics: Heats of Adsorption (URL)
- Part 2The slides for this part (all the videos) ca... (Text and media area)
- 2.1 Statistical Thermodynamics and Molecular Simulation: introduction (URL)
- 2.2 Statistical Thermodynamics and Molecular Simul... (Text and media area)
- 2.2.1 Statistical Thermodynamics and Molecular Simulation: Basic Assumption (URL)
- 2.2.2 Statistical Thermodynamics and Molecular Simulation: equilibrium (URL)
- 2.3 Statistical Thermodynamics and Molecular ... (Text and media area)
- 2.3.1 Statistical Thermodynamics and Molecular Simulation: canonical ensemble (URL)
- 2.3.2 Statistical Thermodynamics and Molecular Simulation: NVT simulations (URL)
- 2.3.3 Statistical Thermodynamics and Molecular Simulation: grand-canonical ensemble (URL)
- 2.3.4 Statistical Thermodynamics and Molecular Simulation: μVT simulations (URL)
- 2.4 Statistical Thermodynamics and Molecular Simulation: (bonus) chemical potential from a simulation (URL)
- 2.5 Statistical Thermodynamics and Molecular Simul... (Text and media area)
- 2.5.1 Statistical Thermodynamics and Molecular Simulation: CO2 in MOF-74 (URL)
- 2.5.2 Statistical Thermodynamics and Molecular Simulation: Xe/Kr separations (URL)
- Part 3Molecular Simulation of Adsorption. (Text and media area)
- 3.1 Introduction to AiiDA and AiiDA lab (URL)
- 3.2 Overview of AiiDA lab interface (URL)
- 3.3 Overview of the AiiDA lab LSMO application (URL)
Machine Learning
In this module, we learn how to use machine learning to predict the gas adsorption in porous materials.
Note that the slides we will use in the in-person setting will be slightly different from the ones we used in the pre-recorded videos. If you follow the course in person you do not need to consider the slides you find after each video, you also do not need to watch the videos.
The preliminary version of the slides we will use in the in-person setting: _course/section/ml_lectures.pdf
You can find more details about the organization and syllabus in the course notebook.
- ML_lecture_2023 (File)
- Assignment (Text and media area)
- ProjectIn the ML module, you will upload only one ... (Text and media area)
- Project description and explanation of Supervised ML for Gas Adsorption in MOFs (Page)
- A simple example of machine learning in chemistry (Page)
- Part 0. Introduction to the module (Text and media area)
- 2.0. Introduction to the machine learning module (URL)
- 2.0 slides (File)
- 2.1. Types of machine learning (URL)
- 2.1 slides (File)
- Part 1. Supervised machine learning (Text and media area)
- 2.2. supervised machine learning workflow (URL)
- 2.2. slides (File)
- 2.3. featurisation (URL)
- 2.3 slides (File)
- 2.4. splitting data (URL)
- 2.4 slides (File)
- 2.5. regression (URL)
- 2.5 slides (File)
- 2.6. bias-variance trade-off (URL)
- 2.6 slides (File)
- 2.7. hyperparameters (URL)
- 2.7 slides (File)
- 2.8. kernel models (URL)
- 2.8 slides (File)
- 2.9. model interpretation (URL)
- 2.9 slides (File)
- 2.10. summary of supervised learning (URL)
- 2.11. Feature selection (Page)
- 2.12. Feature projection (Page)
- 2.13. Feature learning (Page)
- Part 2. Examples (Text and media area)
- 2.14. Applications of Supervised Machine Learning (Page)
Data in Chemistry and Electronic Lab Notebooks (Optional extra materials)
This module is completely optional. There is no need to watch any video or to do any quiz.