摘要
Bayesian optimization(BO)has been leveraged for guiding autonomous and high-throughput experiments in materials science.However,few have evaluated the efficiency of BO across a broad range of experimental materials domains.In this work,we quantify the performance of BO with a collection of surrogate model and acquisition function pairs across five diverse experimental materials systems.By defining acceleration and enhancement metrics for materials optimization objectives,we find that surrogate models such as Gaussian Process(GP)with anisotropic kernels and Random Forest(RF)have comparable performance in BO,and both outperform the commonly used GP with isotropic kernels.GP with anisotropic kernels has demonstrated the most robustness,yet RF is a close alternative and warrants more consideration because it is free from distribution assumptions,has smaller time complexity,and requires less effort in initial hyperparameter selection.We also raise awareness about the benefits of using GP with anisotropic kernels in future materials optimization campaigns.
基金
Q.L.acknowledges generous funding from TOTAL S.A.research grant funded through MITei for supporting his research.A.E.G.,K.A.B.thank Google LLC,the Boston University Dean’s Catalyst Award,The Boston University Rafik B.Hariri Institute for Computing and Computational Science and Engineering,and NSF(CMMI-1661412)for support in this work and studies generating crossed barrel dataset.A.T.,Z.L.,S.S.,T.B.acknowledge support from DARPA under Contract No.HR001118C0036
TOTAL S.A.research grant funded through MITei,US National Science Foundation grant CBET-1605547
the Skoltech NGP program for research generating Perovskite dataset.Z.R.and T.B.are supported by the National Research Foundation,Prime Minister’s Office,Singapore under its Campus for Research Excellence and Technological Enterprise(CREATE)programthrough the Singapore Massachusetts Institute of Technology(MIT)Alliance for Research and Technology’s Low Energy Electronic Systems research program.J.D.,B.M.thank AFOSR Grant 19RHCOR089 for supporting their work in generating the AutoAM dataset
D.B.,K.H.acknowledge funding from the Accelerated Materials Development for Manufacturing Program at A*STAR via the AME Programmatic Fund by the Agency for Science,Technology,and Research under Grant No.A1898b0043 and A*STAR Graduate Academy’s SINGA programme for producing P3HT/CNT dataset
F.M.B.,S.K.acknowledge support from the Accelerated Materials Development for Manufacturing Program at A*STAR via the AME Programmatic Fund by the Agency for Science,Technology and Research under Grant No.A1898b0043.
