Back to Search
Start Over
Collaboration on Machine-Learned Potentials with IPSuite: A Modular Framework for Learning-on-the-Fly
- Source :
- The Journal of Physical Chemistry - Part B; April 2024, Vol. 128 Issue: 15 p3662-3676, 15p
- Publication Year :
- 2024
-
Abstract
- The field of machine learning potentials has experienced a rapid surge in progress, thanks to advances in machine learning theory, algorithms, and hardware capabilities. While the underlying methods are continuously evolving, the infrastructure for their deployment has lagged. The community, due to these rapid developments, frequently finds itself split into groups built around different implementations of machine-learned potentials. In this work, we introduce IPSuite, a Python-driven software package designed to connect different methods and algorithms from the comprehensive field of machine-learned potentials into a single platform while also providing a collaborative infrastructure, helping ensure reproducibility. Furthermore, the data management infrastructure of the IPSuitecode enables simple model sharing and deployment in simulations. Currently, IPSuitesupports six state-of-the-art machine learning approaches for the fitting of interatomic potentials as well as a variety of methods for the selection of training data, running of ab initiocalculations, learning-on-the-fly strategies, model evaluation, and simulation deployment.
Details
- Language :
- English
- ISSN :
- 15206106 and 15205207
- Volume :
- 128
- Issue :
- 15
- Database :
- Supplemental Index
- Journal :
- The Journal of Physical Chemistry - Part B
- Publication Type :
- Periodical
- Accession number :
- ejs65947665
- Full Text :
- https://doi.org/10.1021/acs.jpcb.3c07187