The properties of electrons in matter are of fundamental importance.They give rise to virtually all material properties and determine the physics at play in objects ranging from semiconductor devices to the interior o...The properties of electrons in matter are of fundamental importance.They give rise to virtually all material properties and determine the physics at play in objects ranging from semiconductor devices to the interior of giant gas planets.Modeling and simulation of such diverse applications rely primarily on density functional theory(DFT),which has become the principal method for predicting the electronic structure of matter.While DFT calculations have proven to be very useful,their computational scaling limits them to small systems.We have developed a machine learning framework for predicting the electronic structure on any length scale.It shows up to three orders of magnitude speedup on systems where DFT is tractable and,more importantly,enables predictions on scales where DFT calculations are infeasible.Our work demonstrates how machine learning circumvents a long-standing computational bottleneck and advances materials science to frontiers intractable with any current solutions.展开更多
Advances in machine learning(ML)have enabled the development of interatomic potentials that promise the accuracy of first principles methods and the low-cost,parallel efficiency of empirical potentials.However,ML-base...Advances in machine learning(ML)have enabled the development of interatomic potentials that promise the accuracy of first principles methods and the low-cost,parallel efficiency of empirical potentials.However,ML-based potentials struggle to achieve transferability,i.e.,provide consistent accuracy across configurations that differ from those used during training.In order to realize the promise of ML-based potentials,systematic and scalable approaches to generate diverse training sets need to be developed.This work creates a diverse training set for tungsten in an automated manner using an entropy optimization approach.Subsequently,multiple polynomial and neural network potentials are trained on the entropy-optimized dataset.A corresponding set of potentials are trained on an expert-curated dataset for tungsten for comparison.The models trained to the entropy-optimized data exhibited superior transferability compared to the expert-curated models.Furthermore,the models trained to the expert-curated set exhibited a significant decrease in performance when evaluated on out-of-sample configurations.展开更多
基金This work was in part supported by the Center for Advanced Systems Understanding(CASUS)which is financed by Germany’s Federal Ministry of Education and Research(BMBF)and by the Saxon state government out of the State budget approved by the Saxon State Parliament.
文摘The properties of electrons in matter are of fundamental importance.They give rise to virtually all material properties and determine the physics at play in objects ranging from semiconductor devices to the interior of giant gas planets.Modeling and simulation of such diverse applications rely primarily on density functional theory(DFT),which has become the principal method for predicting the electronic structure of matter.While DFT calculations have proven to be very useful,their computational scaling limits them to small systems.We have developed a machine learning framework for predicting the electronic structure on any length scale.It shows up to three orders of magnitude speedup on systems where DFT is tractable and,more importantly,enables predictions on scales where DFT calculations are infeasible.Our work demonstrates how machine learning circumvents a long-standing computational bottleneck and advances materials science to frontiers intractable with any current solutions.
基金The development of the entropy maximization method and the generation of the training data was supported by the Exascale Computing Project(17-SC-20-SC),a collaborative effort of the U.SDepartment of Energy Office of Science and the National Nuclear Security Administration.The training of the various MLIAP models and the comparative performance analysis was supported by the U.S.Department of Energy,Office of Fusion Energy Sciences(OFES)under Field Work Proposal Number 20-023149+1 种基金Sandia National Laboratories is a multimission laboratory managed and operated by National Technology&Engineering Solutions of Sandia,LLC,a wholly owned subsidiary of Honeywell International Inc.,for the U.S.Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525Los Alamos National Laboratory is operated by Triad National Security LLC,for the National Nuclear Security administration of the U.S.DOE under Contract No.89233218CNA0000001.
文摘Advances in machine learning(ML)have enabled the development of interatomic potentials that promise the accuracy of first principles methods and the low-cost,parallel efficiency of empirical potentials.However,ML-based potentials struggle to achieve transferability,i.e.,provide consistent accuracy across configurations that differ from those used during training.In order to realize the promise of ML-based potentials,systematic and scalable approaches to generate diverse training sets need to be developed.This work creates a diverse training set for tungsten in an automated manner using an entropy optimization approach.Subsequently,multiple polynomial and neural network potentials are trained on the entropy-optimized dataset.A corresponding set of potentials are trained on an expert-curated dataset for tungsten for comparison.The models trained to the entropy-optimized data exhibited superior transferability compared to the expert-curated models.Furthermore,the models trained to the expert-curated set exhibited a significant decrease in performance when evaluated on out-of-sample configurations.
