Machine-learning of atomic-scale properties amounts to extracting correlations between structure, composition and the quantity that one wants to predict. Representing the input structure in a way that best reflects such correlations makes it possible to improve the accuracy of the model for a given amount of reference data. When using a description of the structures that is transparent and well-principled, optimizing the representation might reveal insights into the chemistry of the data set. Here we show how one can generalize the SOAP kernel to introduce a distance-dependent weight that accounts for the multi-scale nature of the interactions, and a description of correlations between chemical species. We show that this improves substantially the performance of ML models of molecular and materials stability, while making it easier to work with complex, multi-component systems and to extend SOAP to coarse-grained intermolecular potentials. The element correlations that give the best performing model show striking similarities with the conventional periodic table of the elements, providing an inspiring example of how machine learning can rediscover, and generalize, intuitive concepts that constitute the foundations of chemistry.
High-quality, high-information datasets for universal atomistic machine learning
École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);MPI for the Structure and Dynamics of Matter(马普物质结构与动力学研究所);University of Cambridge(剑桥大学);BASF SE(巴斯夫股份公司)
Deciphering the "chemical" nature of the exotic isotopes of Hydrogen by the MC-QTAIM analysis: The positively charged Muon and the Muonic Helium as new members of the Periodic Table
Machine learning potentials from transfer learning of periodic correlated electronic structure methods: Application to liquid water with AFQMC, CCSD, and CCSD(T)
Benchmarking short-range machine learning potentials for atomistic simulations of metal/electrolyte interfaces
Leiden Institute of Chemistry, Leiden University(莱顿大学化学研究所);State Key Laboratory of Physical Chemistry of Solid Surfaces, iChEM, College of Chemistry and Chemical Engineering, Xiamen University(厦门大学化学化工学院固体表面物理化学国家重点实验室);Department of Chemical Engineering, University of Michigan(密歇根大学化学工程系);School of Chemistry, Chemical Engineering and Biotechnology, Nanyang Technological University(南洋理工大学化学、化学工程与生物技术学院)
ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table
Department of Chemical Engineering, Massachusetts Institute of Technology(麻省理工学院化学工程系);Center for Computational Science and Engineering, Massachusetts Institute of Technology(麻省理工学院计算科学与工程中心);Institute for Theoretical Chemistry, University of Stuttgart(斯图加特大学理论化学研究所);Institute for Artificial Intelligence, University of Stuttgart(斯图加特大学人工智能研究所);Department of Chemistry, Massachusetts Institute of Technology(麻省理工学院化学系)