Bayesian optimization(BO)is an indispensable tool to optimize objective functions that either do not have known functional forms or are expensive to evaluate.Currently,optimal experimental design is always conducted w...Bayesian optimization(BO)is an indispensable tool to optimize objective functions that either do not have known functional forms or are expensive to evaluate.Currently,optimal experimental design is always conducted within the workflow of BO leading to more efficient exploration of the design space compared to traditional strategies.This can have a significant impact on modern scientific discovery,in particular autonomous materials discovery,which can be viewed as an optimization problem aimed at looking for the maximum(or minimum)point for the desired materials properties.The performance of BO-based experimental design depends not only on the adopted acquisition function but also on the surrogate models that help to approximate underlying objective functions.In this paper,we propose a fully autonomous experimental design framework that uses more adaptive and flexible Bayesian surrogate models in a BO procedure,namely Bayesian multivariate adaptive regression splines and Bayesian additive regression trees.They can overcome the weaknesses of widely used Gaussian process-based methods when faced with relatively high-dimensional design space or non-smooth patterns of objective functions.Both simulation studies and real-world materials science case studies demonstrate their enhanced search efficiency and robustness.展开更多
Muskmelon(Cucumis melo L.)is one of the important horticultural crops of the Cucurbitaceae family.Global production of melon fruits was approximately 27 million tons,with the United States production yielding 616,050 ...Muskmelon(Cucumis melo L.)is one of the important horticultural crops of the Cucurbitaceae family.Global production of melon fruits was approximately 27 million tons,with the United States production yielding 616,050 tons(FAO 2018).Melon is diploid(2n=24)and has an approximate genome size of 450 Mbp(Arumuganathan and Earle 1991).A high-quality reference genome of melon(DHL92 v4.0)covers 358 Mbp pseudomolecules(Castanera et al.2019).展开更多
基金B.K.M.,A.B.,and D.P.acknowledge support by NSF through Grant No.NSF CCF-1934904(TRIPODS)T.Q.K.acknowledges the NSF through Grant No.NSF-DGE-1545403+1 种基金X.Q.and R.A.acknowledge NSF through Grants Nos.1835690 and 2119103(DMREF)The authors also acknowledge Texas A&M’s Vice President for Research for partial support through the X-Grants program.Dr.Prashant Singh(Ames Laboratory)is acknowledged for his DFT calculations of SFE in FCC HEAs.Dr.Anjana Talapatra and Dr.Shahin Boluki are acknowledged for facilitating the BMA Code.DFT calculations of the SFEs were conducted with the computing resources provided by Texas A&M High Performance Research Computing.
文摘Bayesian optimization(BO)is an indispensable tool to optimize objective functions that either do not have known functional forms or are expensive to evaluate.Currently,optimal experimental design is always conducted within the workflow of BO leading to more efficient exploration of the design space compared to traditional strategies.This can have a significant impact on modern scientific discovery,in particular autonomous materials discovery,which can be viewed as an optimization problem aimed at looking for the maximum(or minimum)point for the desired materials properties.The performance of BO-based experimental design depends not only on the adopted acquisition function but also on the surrogate models that help to approximate underlying objective functions.In this paper,we propose a fully autonomous experimental design framework that uses more adaptive and flexible Bayesian surrogate models in a BO procedure,namely Bayesian multivariate adaptive regression splines and Bayesian additive regression trees.They can overcome the weaknesses of widely used Gaussian process-based methods when faced with relatively high-dimensional design space or non-smooth patterns of objective functions.Both simulation studies and real-world materials science case studies demonstrate their enhanced search efficiency and robustness.
基金Open access funding provided by Shanghai Jiao Tong Universityfunded by the United States Department of Agriculture-NIFA-SCRI-2017-51181-26834 through the National Center of Excellence for Melon at the Vegetable and Fruit Improvement Center of Texas A&M University.
文摘Muskmelon(Cucumis melo L.)is one of the important horticultural crops of the Cucurbitaceae family.Global production of melon fruits was approximately 27 million tons,with the United States production yielding 616,050 tons(FAO 2018).Melon is diploid(2n=24)and has an approximate genome size of 450 Mbp(Arumuganathan and Earle 1991).A high-quality reference genome of melon(DHL92 v4.0)covers 358 Mbp pseudomolecules(Castanera et al.2019).
