The Camille and Henry Dreyfus Foundation announces eight award recipients of the 2022 program forĀ Machine Learning in the Chemical Sciences and Engineering, totaling $800,019. The Foundation anticipates that these projects will contribute new fundamental chemical insight and innovation in the field.


Connor G. Bischak, University of Utah
Uncovering Structure-Function Relationships in Organic Mixed Conductors: High-Throughput Electrochemistry Guided by Machine Learning


Stephen Leffler Buchwald
, Massachusetts Institute of Technology
Active Scientific Machine Learning of Chemical Reaction Networks and Chemical Reactivity in Transition Metal Catalysis


Robert A. DiStasio Jr., Cornell University
Semi-Local Density Fingerprints for Machine Learning Molecular Properties, Intra-/Inter-Molecular Interactions, and Chemical Reactions


Julia Dshemuchadse, Cornell University
Discovery of New Self-Assembled Crystal Structures for Materials Design


Boris Kozinsky, Harvard University
Learning Non-Local Functionals and Equivariant Models for Reactive Dynamics


Wenhao Sun, University of Michigan
Machine-Learning Classification of Materials Synthesizability


Mark E. Tuckerman, New York University
Machine Learning the Theorems of Density Functional Theory


Gregory A. Voth, University of Chicago
Physics-Constrained Machine Learning for Reactive Molecular Dynamics