|About this Abstract
||2018 TMS Annual Meeting & Exhibition
||Computational Method and Experimental Approaches for Model Development and Validation, Uncertainty Quantification, and Stochastic Predictions
||Machine Learning Based Atomistic Force Fields
||Rampi Ramprasad, Venkatesh Botu, Rohit Batra, James Chapman , Huan Doan Tran
|On-Site Speaker (Planned)
A general strategy to create machine learning (ML) based atomistic force fields is outlined. In contrast to conventional force fields, ML force fields can be systematically improved by adding progressively new training data (representing new atomic environments). Our ML scheme involves (1) preparing a big reference dataset of atomic environments and forces with sufficiently low noise, e.g., using density functional theory or higher-level methods, (2) utilizing a generalizable class of structural fingerprints for representing atomic environments, (3) optimally selecting diverse and non-redundant training datasets from the reference data, and (4) suitable learning approaches to predict atomic forces directly (and rapidly) from atomic configurations. From the atomistic forces, accurate potential energies can then be obtained by appropriate integration along a reaction coordinate or along a molecular dynamics trajectory. The concept is demonstrated for the case of Al, including extensive tests and molecular dynamics studies of diverse phenomena.
||Planned: Supplemental Proceedings volume