End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems

Linfeng Zhang; Jiequn Han; Han Wang; Wissam A. Saidi; Roberto Car; Weinan E

End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems

Linfeng Zhang, Jiequn Han, Han Wang, Wissam A. Saidi, Roberto Car, Weinan E

Research output: Contribution to journal › Conference article › peer-review

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 of 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.

Original language	English (US)
Pages (from-to)	4436-4446
Number of pages	11
Journal	Advances in Neural Information Processing Systems
Volume	2018-December
State	Published - 2018
Event	32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada Duration: Dec 2 2018 → Dec 8 2018

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

@article{82e463d22b5a4d52ac8f62989503daf0,

title = "End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems",

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 of 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.",

author = "Linfeng Zhang and Jiequn Han and Han Wang and Saidi, {Wissam A.} and Roberto Car and Weinan E",

note = "Publisher Copyright: {\textcopyright} 2018 Curran Associates Inc..All rights reserved.; 32nd Conference on Neural Information Processing Systems, NeurIPS 2018 ; Conference date: 02-12-2018 Through 08-12-2018",

year = "2018",

language = "English (US)",

volume = "2018-December",

pages = "4436--4446",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Neural information processing systems foundation",

}

TY - JOUR

T1 - End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems

AU - Zhang, Linfeng

AU - Han, Jiequn

AU - Wang, Han

AU - Saidi, Wissam A.

AU - Car, Roberto

AU - E, Weinan

PY - 2018

Y1 - 2018

N2 - 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 of 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.

AB - 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 of 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.

UR - http://www.scopus.com/inward/record.url?scp=85064839298&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064839298&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85064839298

SN - 1049-5258

VL - 2018-December

SP - 4436

EP - 4446

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - 32nd Conference on Neural Information Processing Systems, NeurIPS 2018

Y2 - 2 December 2018 through 8 December 2018

ER -

End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this