Recent years have seen significant advancements in artificial intelligence (AI) and machine learning (ML), evidenced by their empirical success. However, many scientific applications still rely on traditional statistical methods for several reasons. One issue is the data inefficiency of ML models, which is a universal challenge across scientific domains due to the high costs to collect high quality data. Additionally, ML models often struggle to produce generalizable results and are difficult to interpret, commonly referred to as “black box” models. My research focuses on addressing these challenges. Indeed, scientific applications always motivate and inspire new AI models and algorithms. Broadly, I am interested in developing ML methodologies that can provide accurate, reliable, and trustworthy solutions to scientific problems and support decision making in critical domains. I am a firm believer in “AI for Science and Science for AI.”
- AI Mentor: Yixin Wang, Statistics, LSA
- Science Mentor: Bryan Goldsmith, Chemical Engineering, College of Engineering
- Research Theme: Causal reasoning in materials science