(389e) Keynote Talk: Modern Data Analytics to Accelerate the Design of Advanced Materials

We will discuss three critical aspects of applying a machine learning approach to accelerate the design of advanced materials for energy applications: 1) consistently measured, relevant experimental data with known pedigree, 2) in-depth scientific features that can be correlated with target properties, and 3) training of surrogate machine learning models. We will present examples of predicting mechanical properties and oxidation response of high-temperature alloys, thermochemistry of complex oxides, and melt-pool microstructure of single-track by the additive manufacturing process.

The research was sponsored by the LDRD Program of Oak Ridge National Laboratory and the Department of Energy, Vehicle Technologies Office, Propulsion Materials Program.