Machine Learning for Soft and Hard Materials

This session invites submissions on experimental and computational research that aims to understand and design materials and related processes using data-driven methods. Data-driven approaches include, but are not limited to, high-throughput screening, machine learning, data mining, meta-analysis, accelerated simulation techniques, and model prediction based on data. We strongly encourage abstracts that integrate data science with classical or quantum simulation and experimental approaches for materials design and property prediction. Submissions must clearly articulate the impact of data science on the materials problem of interest to be considered.