This repository contains code, datasets and models corresponding to the following publication:

Neural density functional theory of liquid-gas phase coexistence
Florian Sammüller, Matthias Schmidt, and Robert Evans; arXiv:2408.15835.

Working in a virtual environment is recommended. Set one up with python -m venv .venv, activate it with source .venv/bin/activate and install the required packages with pip install -r requirements.txt. To use a GPU with Tensorflow/Keras, refer to the corresponding section in the installation guide at https://www.tensorflow.org/install/pip.

Simulation data can be found in data and trained models are located in models. A sample script for thermal training of a neural functional from scratch is given in learn.py. Utilities for making predictions with trained neural functionals are given in utils.py, see also predict.py for how to calculate self-consistent density profiles.

The reference data has been generated with grand canonical Monte Carlo simulations using MBD.