Anuj Karpatne

Hi, I am an Associate Professor in the Department of Computer Science at Virginia Tech (VT) where I lead the Knowledge-guided Machine Learning (KGML) Lab. I joined VT in 2018 as an Assistant Professor and received tenure in 2023. Before that, I was a PhD student at the University of Minnesota working with Prof. Vipin Kumar on understanding climate change using data-driven approaches. This exposed me to problems in science where there is a wealth of scientific knowledge available to be incorporated in machine learning (ML) algorithms to go beyond "black-box" applications of ML in science, giving rise to a new field of knowledge-guided ML (KGML).

My research vision is to establish KGML as a thriving area of research that serves as a nucleus for foundational innovations in AI/ML to produce scientifically grounded, explainable, and generalizable solutions, driven by inter-disicplinary problems in science that impact society. My lab has contributed several themes of research in KGML for incorporating scientific knowledge in ML including knowledge-guided (KG)-Loss Functions, KG-Neural Architectures, KG-Pretraining, and Hybrid-Science-ML Modeling (see Publications for a categorization of papers in each theme). This has been possible thanks to the amazing set of collaborators I have been fortunate to work with from diverse scientific disciplines including physics (fluid dynamics, quantum mechanics, and electromagnetism), environmental sciences (aquatic sciences, remote sensing, and geophysics), and biology (organismal biology, virology, and mechanobiology) with generous support from NSF (see Funding for a list of awards and collaborators).

To learn more about my research, please visit the KGML-Lab Website.