Skip to yearly menu bar Skip to main content


Poster

End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems

Linfeng Zhang · Jiequn Han · Han Wang · Wissam Saidi · Roberto Car · Weinan E

Room 210 #78

Keywords: [ Supervised Deep Networks ] [ Regression ]


Abstract:

Machine learning models are changing the paradigm of molecular modeling, which is a fundamental tool for material science, chemistry, and computational biology. Of particular interest is the inter-atomic potential energy surface (PES). Here we develop Deep Potential - Smooth Edition (DeepPot-SE), an end-to-end machine learning-based PES model, which is able to efficiently represent the PES for a wide variety of systems with the accuracy of ab initio quantum mechanics models. By construction, DeepPot-SE is extensive and continuously differentiable, scales linearly with system size, and preserves all the natural symmetries of the system. Further, we show that DeepPot-SE describes finite and extended systems including organic molecules, metals, semiconductors, and insulators with high fidelity.

Live content is unavailable. Log in and register to view live content