INVITED: Artificial intelligence (AI) methods for extracting materials knowledge from rich data sets

Over the past four decades, computational modeling and simulation have complemented experimental efforts to inform our understanding of materials structure, processing, and properties. More recently, the tools of artificial intelligence (AI) – a broad term comprising data science, machine learning (ML), neural network computing, computer vision (CV), and other technologies – open new avenues for extracting information from high-dimensional materials data. The AI modeling process involves numerically encoding the relevant data and then selecting ML tools based on the characteristics of the data set and the desired outcome. Examples of this process for structural, mechanical, and visual data will be presented. Case studies will present results that range from advanced methods for microstructural segmentation and characterization to prediction of microstructural evolution and material properties. The ultimate goal is to develop AI as a new tool for information extraction and knowledge generation in materials science.