Materials design and characterization with small data

Luca Ghiringhelli, Karlsruhe Institute of Technology, Germany

The modeling of macroscopic properties of materials often require to accurately evaluate physical quantities at several time and length scales. Here we show how symbolic inference, i.e., the machine learning of simple analytical expressions that explain and generalize the available data, can effectively bridge physical scales. The focus is on learning models that are as simple as possible (but not simpler!), with as few as possible data points. I will demonstrate the application of the methods to the modeling of catalytic properties of materials, design of organic-photovoltaics, and more.