In pursuit of scientific discovery,vast collections of unstructured structural and functional images are acquired;however,only an infinitesimally small fraction of this data is rigorously analyzed,with an even smaller...In pursuit of scientific discovery,vast collections of unstructured structural and functional images are acquired;however,only an infinitesimally small fraction of this data is rigorously analyzed,with an even smaller fraction ever being published.One method to accelerate scientific discovery is to extract more insight from costly scientific experiments already conducted.Unfortunately,data from scientific experiments tend only to be accessible by the originator who knows the experiments and directives.Moreover,there are no robust methods to search unstructured databases of images to deduce correlations and insight.Here,we develop a machine learning approach to create image similarity projections to search unstructured image databases.To improve these projections,we develop and train a model to include symmetry-aware features.As an exemplar,we use a set of 25,133 piezoresponse force microscopy images collected on diverse materials systems over five years.We demonstrate how this tool can be used for interactive recursive image searching and exploration,highlighting structural similarities at various length scales.This tool justifies continued investment in federated scientific databases with standardized metadata schemas where the combination of filtering and recursive interactive searching can uncover synthesis-structure-property relations.We provide a customizable open-source package(https://github.com/m3-learning/Recursive_Symmetry_Aware_Materials_Microstructure_Explorer)of this interactive tool for researchers to use with their data.展开更多
基金T.N.M.N.acknowledges primary support from the Nano/Human Interfaces Presidential Initiative and secondary support from National Science Foundation under grant TRIPODS+X:RES-1839234Y.G.,J.C.A.,S.Q.,and K.S.F.acknowledge primary support from National Science Foundation under grant TRIPODS+X:RES-1839234We graciously acknowledge all experimentalists who were involved in collecting the data used in this study.Contributors include Prof.Lane Martin and Ramamoorthy Ramesh.We want to recognize all trainees that took part in collecting this data,including Liv Dedon,Shishir Pandya,Anoop Damodaran,Sahar Saremi,Anoop Damodaran,Zhuhang Chen,Ran Gao,Shang-lin Hsu,Julia Mundy,Arvind Dasgupta,Gabe Velarde,Xiaoyan Lu,Sujit Das,Ajay Yadav,Bhagwati Prasad,James Clarkson,David Pesquera,Jieun Kim,Megha Acharya,Suraj Cheema,Eduardo Lupi,Wenbo Zhao,Lei Zhang,Margaret McCarter,Hongling Hu,and Derek Meyers.
文摘In pursuit of scientific discovery,vast collections of unstructured structural and functional images are acquired;however,only an infinitesimally small fraction of this data is rigorously analyzed,with an even smaller fraction ever being published.One method to accelerate scientific discovery is to extract more insight from costly scientific experiments already conducted.Unfortunately,data from scientific experiments tend only to be accessible by the originator who knows the experiments and directives.Moreover,there are no robust methods to search unstructured databases of images to deduce correlations and insight.Here,we develop a machine learning approach to create image similarity projections to search unstructured image databases.To improve these projections,we develop and train a model to include symmetry-aware features.As an exemplar,we use a set of 25,133 piezoresponse force microscopy images collected on diverse materials systems over five years.We demonstrate how this tool can be used for interactive recursive image searching and exploration,highlighting structural similarities at various length scales.This tool justifies continued investment in federated scientific databases with standardized metadata schemas where the combination of filtering and recursive interactive searching can uncover synthesis-structure-property relations.We provide a customizable open-source package(https://github.com/m3-learning/Recursive_Symmetry_Aware_Materials_Microstructure_Explorer)of this interactive tool for researchers to use with their data.
