Prediction of chemical properties using neural network.
This project uses NN implemented by tensorflow to predict chemical properties of numerical fingerprints retrieved from atomic structures using dscribe.
All wrapped up in an user-friendly web app environment of streamlit.
Quick way to get your hand on the ChemPropsAI service is to use our Streamlit app to play around with example data.
As a quick example, we will run the online service use historical load data to fit new model and get prediction
- To start the service, open Streamlit app
- Import the example data
- The service silently fits your model
- Select descriptor (X) and property (y)
- Submit your query
- Download the model pressing "Download model" for later use
Note: If the app is sleeping, you can build it by pressing the big red button on screen.
Feel free to contribute in any way you like, we're always open to new ideas and approaches.
- Feel welcome to open an issue if you think you've spotted a bug or a performance issue.