Ab-initio Random Structure Searching (AIRSS) and machine learning: Applications in energy storage systems
Abstract
In this talk, I will present how the simple but elegant method Ab-initio Random Structure Searching (AIRSS) is used to make more accurate predictions of important energy storage metrics such as hydrogen storage capacity of solid-state hydrogen storage materials, and specific energy capacity and open circuit voltage for metal-ion batteries. I will also discuss the important limitations of the method, and how machine learning can significantly help in making the method more powerful and computationally less expensive for larger systems.