While machine learning has emerged in recent years as a useful tool for the rapid prediction of materials properties,generating sufficient data to reliably train models without overfitting is often impractical.Towards...While machine learning has emerged in recent years as a useful tool for the rapid prediction of materials properties,generating sufficient data to reliably train models without overfitting is often impractical.Towards overcoming this limitation,we present a general framework for leveraging complementary information across different models and datasets for accurate prediction of data-scarce materials properties.Our approach,based on a machine learning paradigm called mixture of experts,outperforms pairwise transfer learning on 14 of 19 materials property regression tasks,performing comparably on four of the remaining five.The approach is interpretable,model-agnostic,and scalable to combining an arbitrary number of pre-trained models and datasets to any downstream property prediction task.We anticipate the performance of our framework will further improve as better model architectures,new pre-training tasks,and larger materials datasets are developed by the community.展开更多
We develop an automated high-throughput workflow for calculating lattice dynamical properties from first principles including those dictated by anharmonicity.The pipeline automatically computes interatomic force const...We develop an automated high-throughput workflow for calculating lattice dynamical properties from first principles including those dictated by anharmonicity.The pipeline automatically computes interatomic force constants(IFCs)up to 4th order from perturbed training supercells,and uses the IFCs to calculate lattice thermal conductivity,coefficient of thermal expansion,and vibrational free energy and entropy.It performs phonon renormalization for dynamically unstable compounds to obtain real effective phonon spectra at finite temperatures and calculates the associated free energy corrections.The methods and parameters are chosen to balance computational efficiency and result accuracy,assessed through convergence testing and comparisons with experimental measurements.Deployment of this workflow at a large scale would facilitate materials discovery efforts toward functionalities including thermoelectrics,contact materials,ferroelectrics,aerospace components,as well as general phase diagram construction.展开更多
基金This material is based upon work supported by the National Science Foundation under Grant Nos.1922758,2118201,and 2106825It utilizes computational resources supported by the National Science Foundation’s Major Research Instrumentation program(Grant No.1725729)the Delta research computing project(Grant No.2005572).
文摘While machine learning has emerged in recent years as a useful tool for the rapid prediction of materials properties,generating sufficient data to reliably train models without overfitting is often impractical.Towards overcoming this limitation,we present a general framework for leveraging complementary information across different models and datasets for accurate prediction of data-scarce materials properties.Our approach,based on a machine learning paradigm called mixture of experts,outperforms pairwise transfer learning on 14 of 19 materials property regression tasks,performing comparably on four of the remaining five.The approach is interpretable,model-agnostic,and scalable to combining an arbitrary number of pre-trained models and datasets to any downstream property prediction task.We anticipate the performance of our framework will further improve as better model architectures,new pre-training tasks,and larger materials datasets are developed by the community.
基金supported by the Materials Project,funded by the U.S.Department of Energy under award DE-AC02-05CH11231(Materials Project program KC23MP)J.P.acknowledges the support from the U.S.Department of Energy,Office of Basic Energy Sciences,Early Career Research Program+1 种基金J.W.L.and J.P.also acknowledge funding by the Transformational Tools and Technologies(TTT)project of the Aeronautics Research Mission Directorate(ARMD)at the National Aeronautics and SpaceAdministration(NASA).A.M.G.was supported by EPSRC Fellowship EP/T033231/1This work used computational resources of the National Energy Research Scientific Computing Center(NERSC),a Department of Energy Office of Science User Facility supported by the Office of Science of the U.S.Department of Energy under Contract No.DE-AC02-05CH11231.
文摘We develop an automated high-throughput workflow for calculating lattice dynamical properties from first principles including those dictated by anharmonicity.The pipeline automatically computes interatomic force constants(IFCs)up to 4th order from perturbed training supercells,and uses the IFCs to calculate lattice thermal conductivity,coefficient of thermal expansion,and vibrational free energy and entropy.It performs phonon renormalization for dynamically unstable compounds to obtain real effective phonon spectra at finite temperatures and calculates the associated free energy corrections.The methods and parameters are chosen to balance computational efficiency and result accuracy,assessed through convergence testing and comparisons with experimental measurements.Deployment of this workflow at a large scale would facilitate materials discovery efforts toward functionalities including thermoelectrics,contact materials,ferroelectrics,aerospace components,as well as general phase diagram construction.
