A Δ-machine learning approach for force fields, illustrated by a CCSD(T) 4-body correction to the MB-pol water potential

Abstract

In this paper we proposed a Δ-machine learning approach to correct general many-body force fields. We illustrate this approach by adding a 4-body correction to the MB-pol water potential to bring it to a higher level of accuracy.

Document Details

Document Type
Pub Defense Publication
Publication Date
Jan 01, 2022
Source ID
10.1039/d2dd00057a

Entities

People

  • Apurba Nandi
  • Chen Qu
  • Joel Bowman
  • Paul Houston
  • Qi Yu
  • Riccardo Conte

Organizations

  • Army Research Office
  • Cornell University
  • Emory University
  • Georgia Tech
  • National Aeronautics and Space Administration
  • National Science Foundation
  • University of Milan
  • Yale University

Tags

Readers

  • Calculus or Mathematical Analysis
  • Distributed Systems and Data Platform Development
  • Quantum Chemistry

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks