Theoretical and Computational Chemistry

Optimizing Fractional Compositions To Achieve Extraordinary Properties

Andrew Falkowski University of Utah


Traditional, data-driven materials discovery involves screening chemical systems with machine learning algorithms and selecting candidates that excel in a target property. The number of screening candidates grows infinitely large as the fractional resolution of compositions the number of included elements increases. The computational infeasibility and probability of overlooking a successful candidate grow likewise. Our approach shifts the optimization focus from model parameters to the fractions of each element in a composition. Using a pretrained network, CrabNet, and writing a custom loss function to govern a vector of element fractions, compositions can be optimized such that a predicted property is maximized or minimized. Single and multi-property optimization examples are presented that highlight the capabilities and robustness of this approach to inverse design.


Thumbnail image of CoCoCrab_Manuscript_v1.pdf
download asset CoCoCrab_Manuscript_v1.pdf 1 MB [opens in a new tab]

Supplementary weblinks