BoltzmaNN: Predicting effective pair potentials and equations of state using neural networks

BoltzmaNN is a machine learning approach based on artificial neural networks for predicting equations of state and for structural coarse-graining.
A detailed description of the method can be found in our research paper.
The trained models and example scripts are available on our git repository.
BoltzmaNN is also available as a web application. The tool for predicting the equation of state can be found here, while the tool for computing effective pair potentials can be found here.


This work was funded by the German Research Foundation (DFG) through project number 233630050 - TRR 146.
Arash Nikoubashman further acknowledges financial support provided by the DFG through project number NI 1487/2-1and NI 1487/2-2.

For more information contact the authors Fabian Berressem or Arash Nikoubashman.