Collaboration on Machine-Learned Potentials with IPSuite: A Modular Framework for Learning-on-the-Fly
The Journal of Physical Chemistry B · 18.04.2024 · 128 (15) · 3662-3676
DOI: 10.1021/acs.jpcb.3c07187 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Physical Chemistry B, online erschienen am 03.04.2024. Verfasst von Fabian Zills und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Computational Physics, University of Stuttgart, 70569 Stuttgart, Germany. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 110 Literaturangaben. Gefördert von: Deutsche Forschungsgemeinschaft, Ministerium f?r Wissenschaft, Forschung und Kunst Baden-W?rttemberg.
Abstract (Originalsprache)
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 IPSuite code enables simple model sharing and deployment in simulations. Currently, IPSuite supports 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 initio calculations, learning-on-the-fly strategies, model evaluation, and simulation deployment.
Autor:innen und Institutionen
- Institute for Computational Physics, University of Stuttgart, 70569 Stuttgart, Germany.
- Institute for Theoretical Chemistry, University of Stuttgart, 70569 Stuttgart, Germany.
ORCID-Profile: Fabian Zills, Moritz René Schäfer, Johannes Kästner, Christian Holm, Samuel Tovey
Förderung
- Deutsche Forschungsgemeinschaft
- Ministerium f?r Wissenschaft, Forschung und Kunst Baden-W?rttemberg
Zitieren
APA
Zills, F., Schäfer, M. R., Segreto, N., Kästner, J., Holm, C., & Tovey, S. (2024). Collaboration on Machine-Learned Potentials with IPSuite: A Modular Framework for Learning-on-the-Fly. The Journal of Physical Chemistry B, 128(15), 3662-3676. https://doi.org/10.1021/acs.jpcb.3c07187
Vancouver
Zills F, Schäfer MR, Segreto N, Kästner J, Holm C, Tovey S. Collaboration on Machine-Learned Potentials with IPSuite: A Modular Framework for Learning-on-the-Fly. The Journal of Physical Chemistry B. 2024;128(15):3662-3676. doi:10.1021/acs.jpcb.3c07187
BibTeX
@article{Zills2024,
author = {Zills, Fabian and Schäfer, Moritz René and Segreto, Nico and Kästner, Johannes and Holm, Christian and Tovey, Samuel},
title = {Collaboration on Machine-Learned Potentials with IPSuite: A Modular Framework for Learning-on-the-Fly},
journal = {The Journal of Physical Chemistry B},
year = {2024},
volume = {128},
number = {15},
pages = {3662--3676},
doi = {10.1021/acs.jpcb.3c07187}
}
EUVIMED