Angular and Shell-Aware Deep Potential Energy Model for Molecular Dynamics

Yuan Pu, Jiayang Yao, Haoxin Wang, Binwu Zhu, Yuyang Ye, Zhuolun He, Yian Wang, Bei YuOpenReview 2026 · Submission to ICLR 2026 · Rejected · OpenReview

Abstract

Angular information, especially involving the first and second coordination shells, is critical for accurately describing the potential energy surface (PES) in molecular systems. However, existing machine learning PES models either neglect this information or indiscriminately process it from all neighbors, blurring the critical contributions of distinct shells and compromising their predictive accuracy. In this work, we propose the Angular and Shell-Aware Deep Potential (ASDP), a novel architecture designed to overcome this limitation. Based on the DPA-1 attention mechanism, ASDP integrates a specialized encoding module that selectively processes angular information confined within the first two coordination shells. This shell-aware approach allows for a more physically meaningful representation of the local atomic environment. Experimental results show that by capturing crucial shell-specific angular dependencies, ASDP represents the PES of various molecular systems with the \textit{ab initio} quantum mechanics (QM) accuracy, outperforming many existing methods and offering a new direction for creating highly accurate and robust machine learning potentials. Our code can be found in \url{https://anonymous.4open.science/r/ASDP-ICLR-code}.
BibTeX
@misc{pu2026angular,
  author = {Yuan Pu and Jiayang Yao and Haoxin Wang and Binwu Zhu and Yuyang Ye and Zhuolun He and Yian Wang and Bei Yu},
  title = {{Angular and Shell-Aware Deep Potential Energy Model for Molecular Dynamics}},
  year = {2026},
  url = {https://openreview.net/forum?id=NOrdZNoOu0},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2026},
}
Figure