2026-10-13T20:02:30Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33774487 2026-09-15T07:15:37Z category_4 category_146 category_19 category_21 category_272 category_45 category_734 category_931 category_106 category_133 portal_63 item_type_3 month_year_09_2026

Learning Interpretable Activity Descriptors Directly from Measurement Features in Heterogeneous Catalysis Yoshiki Hasukawa (20456262) Fernando Garcia-Escobar (14835006) Lauren Takahashi (3107373) Keisuke Takahashi (1409992) Biochemistry Space Science Pharmacology Biotechnology Environmental Sciences not elsewhere classified Sociology Biological Sciences not elsewhere classified Information Systems not elsewhere classified Science Policy Plant Biology revealing complex factors heterogeneous characterization data conventionally interpreted individually multidimensional measurement space measurement informatics provides experimental measurement data combining complementary measurement catalytic activity prediction 2 </ sub catalytic activity measurement features learning analysis interactions associated evaluated systematically derived descriptors Conventional catalyst informatics largely relies on composition-based descriptors for catalytic activity prediction. In this study, heterogeneous characterization data are integrated into a multidimensional measurement space and transformed into measurement-derived descriptors for machine-learning analysis. This shift from composition-based to measurement-centered catalyst informatics enables characterization information that is conventionally interpreted individually to be evaluated systematically and quantitatively in combination, providing a framework for describing the activity landscape across catalytic states. Importantly, combining complementary measurement-derived descriptors enables highly accurate prediction of CO₂ conversion while revealing complex factors and interactions associated with catalytic activity. Thus, measurement informatics provides a rational framework for extracting interpretable structure–activity relationships from experimental measurement data. 2026-09-15T00:00:00Z Dataset Dataset 10.1021/acs.jpclett.6c02053.s001 https://figshare.com/articles/dataset/Learning_Interpretable_Activity_Descriptors_Directly_from_Measurement_Features_in_Heterogeneous_Catalysis/33774487 CC BY-NC 4.0