2021/03/25 by Tian Xie, Xie, Tian, Victor Bapst +13
Physics and Astronomy · #FOS: Physical sciences #Materials Science (cond-mat.mtrl-sci) #cond-mat.mtrl-sci
paper · pdf · doi:10.48550/arxiv.2103.13795
22 pages, preprint
arxiv created 2021/03/25 · arxiv updated 2021/03/26
Machine Learning (ML) has the potential to accelerate discovery of new materials and shed light on useful properties of existing materials. A key difficulty when applying ML in Materials Science is that experimental datasets of material properties tend to be small. In this work we show how material descriptors can be learned from the structures present in large scale datasets of material simulations; and how these descriptors can be used to improve the prediction of an experimental property, the energy of formation of a solid. The material descriptors are learned by training a Graph Neural Network to regress simulated formation energies from a material's atomistic structure. Using these learned features for experimental property predictions outperforms existing methods that are based solely on chemical composition. Moreover, we find that the advantage of our approach increases as the generalization requirements of the task are made more stringent, for example when limiting the amount of training data or when generalizing to unseen chemical spaces.