Virginia Tech®home

Seminar: Physics-guided Machine Learning: How Can Physics and Machine Learning Come Together to Accelerate Scientific Discovery?

Anuj Karpatne

Assistant Professor, Virginia Tech

Friday, April 19
11:15am - 12:30pm
100 Hancock Hall


This talk will introduce theory-guided data science, a novel paradigm of scientific discovery that leverages the unique ability of data science methods to automatically extract patterns and models from data, but without ignoring the treasure of knowledge accumulated in scientific theories. Theory-guided data science aims to fully capitalize the power of machine learning and data mining methods in scientific disciplines by deeply coupling them with models based on scientific theories. This talk will describe several ways in which scientific knowledge can be combined with data science methods in various scientific disciplines such as hydrology, climate science, aerospace, and chemistry. To demonstrate the value in combining physics with data science, the talk will also introduce a novel framework for combining deep learning methods with physics-based models, termed as physics-guided neural networks, and present some preliminary results of this framework for an application in lake temperature modeling. The talk will conclude with a discussion of future prospects in exploiting latest advances in deep learning for building the next generation of scientific models for dynamical systems, where theory-based and data science methods are used at an equal footing.


Anuj Karpatne is an Assistant Professor in the Department of Computer Science at Virginia Tech, where he develops data mining and machine learning methods to solve scientific and socially relevant problems. A key focus of Dr. Karpatne’s research is to advance a novel paradigm of research, termed theory-guided data science, that integrates scientific knowledge (or physics) with machine learning methods to accelerate scientific discovery. His research has been published at top-tier journals and conferences in computer science (such as SDM, ICDM, KDD, NeurIPS, IEEE TKDE, and ACM Computing Surveys) as well as leading journals from other disciplines (such as RSE, GRSM, and GEB). Dr. Karpatne is a co-author of the second edition of the leading textbook, "Introduction to Data Mining." He also serves as the review editor for "Data-driven Climate Sciences" in Frontiers in Big Data. In recognition of his inter-disciplinary research efforts in geosciences, Dr. Karpatne was named the Inaugural Research Fellow by the IS-GEO (Intelligent Systems for Geosciences) Research Coordination Network in 2018. He received his Ph.D. in Computer Science at the University of Minnesota in 2017 under the guidance of Prof. Vipin Kumar, and an Integrated M.Tech in Mathematics and Computing from the Indian Institute of Technology Delhi in 2011.