P.S. Dutta, A. Koneru, D. Sanpui, A. Chandra, H. Chan, S. Manna, S. Banik, T.D. Loeffler, S.K.R.S. Sankaranarayanan
University of Illinois at Chicago,
Keywords: machine learning, materials discovery, inverse design
Summary:The ever-increasing power of modern supercomputers, along with the availability of highly scalable atomistic simulation codes, has begun to revolutionize predictive modeling of materials. In this talk, I will present some of our group’s recent work on the use of machine learning (ML) to seamlessly bridge the electronic, atomistic and mesoscopic scales for materials modeling. Our automated ML framework aims to bridge the significant gulf that exists between the handful of research groups that develop new interatomic potential models (often requiring several years of effort) and the increasingly large user community from academia and industry that applies these models. Our ML approach showed marked success in developing force fields for a wide range of materials from metals, oxides, nitrides, hetero-interfaces to two-dimensional (2-D) materials and even water (arguably the most difficult system to capture from a molecular perspective). This talk will also briefly discuss our ongoing efforts to integrate such cheap yet accurate models with (a) AI techniques to perform inverse design and construct metastable phase diagrams of materials (b) Deep learning to improve spatiotemporal resolutions of ultrafast X-ray imaging and (c) perform inverse design of materials and devices with user desired properties.