Atomistic Materials Informatics:from First Principles to Machine Learning Methods

This comprehensive course delves into the intersection of machine learning (ML) and atomistic materials engineering, offering a powerful approach to materials modeling that addresses the limitations of traditional methods such as Density Functional Theory (DFT). Designed for undergraduate and postgraduate students as well as researchers and business professionals with limited technical backgrounds, the course spans twelve on-line lectures. The course starts with exploration of the application of ML algorithms across the entire materials lifecycle – from discovery and development to production, testing, application, and recycling. It further covers the theoretical foundations of ML techniques and their applications, using cutting-edge tools and frameworks to analyze atomistic data, construct linear atomistic models, and develop machine learning interatomic potential (MLIP) models using Density Functional Theory calculations as a source of data. Through case studies and real-world examples, participants will gain insights into the transformative impact of machine learning on materials science, preparing them for future opportunities and challenges in this interdisciplinary field.