Evidential deep learning for interatomic potentials

Machine learning interatomic potentials have been widely used to facilitate large-scale molecular simulations with accuracy comparable to ab initio methods. To ensure the reliability of the simulation, the training dataset is iteratively expanded through active learning, where uncertainty serves as a critical indicator for identifying and collecting out-of-distribution data. However, existing uncertainty quantification methods tend to involve either expensive computations or compromise prediction accuracy. Here we show an evidential deep learning framework for interatomic potentials with a physics-inspired design. Our method provides uncertainty quantification without significant computational overhead or decreased prediction accuracy, consistently outperforming other methods across a variety of datasets. Furthermore, we demonstrate applications in exploring diverse atomic configurations, using examples including water and universal potentials. These results highlight the potential of our method as a robust and efficient alternative for uncertainty quantification in molecular simulations.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2025-12-20
DOI
https://doi.org/10.1038/s41467-025-67663-y
Citations
1
Primary Topic
Machine Learning in Materials Science
Type
article
Field-Weighted Citation Impact
0.52

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Evidential deep learning for interatomic potentials

Jianfeng Ma, Taoyong Cui, Chenyu Tang, Yuqiang Li et al.
1 citations
Nature Communications
Machine Learning in Materials Science
0.52
article

Evidential deep learning for interatomic potentials

Jianfeng Ma, Taoyong Cui, Chenyu Tang, Yuqiang Li, Mao Su, Wanli Ouyang, Xiang Gao, Shufei Zhang, Han Xu, Dongzhan Zhou, Xingao Gong
article en
1 citations

Abstract

Machine learning interatomic potentials have been widely used to facilitate large-scale molecular simulations with accuracy comparable to ab initio methods. To ensure the reliability of the simulation, the training dataset is iteratively expanded through active learning, where uncertainty serves as a critical indicator for identifying and collecting out-of-distribution data. However, existing uncertainty quantification methods tend to involve either expensive computations or compromise prediction accuracy. Here we show an evidential deep learning framework for interatomic potentials with a physics-inspired design. Our method provides uncertainty quantification without significant computational overhead or decreased prediction accuracy, consistently outperforming other methods across a variety of datasets. Furthermore, we demonstrate applications in exploring diverse atomic configurations, using examples including water and universal potentials. These results highlight the potential of our method as a robust and efficient alternative for uncertainty quantification in molecular simulations.

Nature CommunicationsVol. 17(1)
Chinese University of Hong Kong (HK), Fudan University (CN), ShanghaiTech University (CN), Beijing Academy of Artificial Intelligence (CN), Shenzhen Institutes of Advanced Technology (CN), State Key Laboratory of Chemical Engineering (CN), Shanghai Artificial Intelligence Laboratory (CN), State Key Laboratory of Surface Physics, Zhejiang University (CN)
National Natural Science Foundation of China, National Science and Technology Major Project
Openalex Percentile: Top 29%
Machine Learning in Materials Science
0.52
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.