Divide-and-conquer potentials enable scalable and accurate predictions of forces and energies in atomistic systems-Reference-Cited by-同舟云学术

Divide-and-conquer potentials enable scalable and accurate predictions of forces and energies in atomistic systems

Published:2024 Issue:1 Volume:3 Page:113-121
ISSN:2635-098X
Container-title:Digital Discovery
language:en
Short-container-title:Digital Discovery

Author:

Zeni Claudio¹²,Anelli Andrea³⁴,Glielmo Aldo²⁵^ORCID,de Gironcoli Stefano²,Rossi Kevin⁴⁶^ORCID

Affiliation:

1. Microsoft Research, Cambridge, UK

2. Physics Area, International School for Advanced Studies, Trieste, Italy

3. Roche, Pharma Research and Early Development, Therapeutic Modalities, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd, Grenzacherstrasse 124, 4070, Basel, Switzerland

4. Institute of Materials, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland

5. Bank of Italy, Italy

6. Department of Materials Science and Engineering, Delft University of Technology, 2628 CD, Delft, The Netherlands

Abstract

A divide-and-conquer strategy - where small datasets are extracted from a larger one and utilised to train multiple models, which are then carefully combined for prediction - provides an avenue for accurate machine learning potentials.

Funder

Horizon 2020 Framework Programme

Publisher

Royal Society of Chemistry (RSC)

Link

http://pubs.rsc.org/en/content/articlepdf/2024/DD/D3DD00155E

Reference54 articles.

1. Neural network interatomic potential for the phase change material GeTe

2. An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2

3. ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost

4. Deep learning study of tyrosine reveals that roaming can lead to photodamage

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Geometric deep learning-guided Suzuki reaction conditions assessment for applications in medicinal chemistry;RSC Medicinal Chemistry;2024