DeePKS-kit: a package for developing machine learning-based chemically accurate energy and density functional models

TL;DR

DeePKS-kit is an open-source software package that facilitates the development of machine learning-based energy and density functional models in quantum chemistry, integrating PyTorch and PySCF for customizable and accurate simulations.

Contribution

It introduces DeePKS-kit, a new software tool that simplifies creating machine learning models for quantum chemistry, supporting DeePHF and DeePKS methods with practical examples.

Findings

Supports development of chemically accurate models

Integrates with PyTorch and PySCF for flexibility

Provides example for water clusters

Abstract

We introduce DeePKS-kit, an open-source software package for developing machine learning based energy and density functional models. DeePKS-kit is interfaced with PyTorch, an open-source machine learning library, and PySCF, an ab initio computational chemistry program that provides simple and customized tools for developing quantum chemistry codes. It supports the DeePHF and DeePKS methods. In addition to explaining the details in the methodology and the software, we also provide an example of developing a chemically accurate model for water clusters.