Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/PV-Lab/BayesProcess
Physics informed Bayesian network + autoencoder for matching process / variable / performance in solar cells.
https://github.com/PV-Lab/BayesProcess
Last synced: about 2 months ago
JSON representation
Physics informed Bayesian network + autoencoder for matching process / variable / performance in solar cells.
- Host: GitHub
- URL: https://github.com/PV-Lab/BayesProcess
- Owner: PV-Lab
- License: mit
- Created: 2019-07-09T04:43:23.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2021-08-18T14:30:54.000Z (over 3 years ago)
- Last Synced: 2024-10-29T20:59:49.123Z (2 months ago)
- Language: Jupyter Notebook
- Size: 78.5 MB
- Stars: 30
- Watchers: 6
- Forks: 6
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- open-sustainable-technology - BayesProcess - A Python package for Physics informed Bayesian network inference using neural network surrogate model for matching process / variable / performance in solar cells. (Renewable Energy / Photovoltaics and Solar Energy)
README
## Description
BayesProcess is a python package for Physics informed Bayesian network inference using neural network surrogate model for matching process / variable / performance in solar cells.
## Installation
To install, just clone the following repository:
pip install -r requirements.txt
https://github.com/PV-Lab/BayesProcess.git
## Usage
run `surrogate_model.py` , with the given datasets to create the neural network surrogate for numerical PDE solver.
run `Bayes.py` with the saved surrogate model. This performs Bayesian network inference to map the process variable (Temperature) to material descriptors.
The package contains the following module and scripts:| Module | Description |
| ------------- | ------------------------------ |
| `JV_surrogate.py` | Script for training neural network JV surrogate model |
| `Bayes.py` | Script for Bayesian inference using MCMC |
| `requirements.txt` | required packages |## Authors
"Danny" Zekun Ren and Felipe Oviedo