Christopher Earls

Christopher J. Earls is the J. Preston Levis Professor of Engineering in the School of Civil and Environmental Engineering at Cornell University. He serves as a faculty member in the Complex Systems and Engineering concentration. Earls earned his B.S. in Civil Engineering from Virginia Tech in 1990, M.S. in Civil Engineering from Virginia Tech in 1992, and Ph.D. in Civil Engineering from the University of Minnesota in 1995. His research is concerned with developing novel mathematical and computational approaches that enable deep understanding of natural and engineered systems. Practical challenges involving the principled treatment of uncertainty, sparse sensing, and intrinsic complexity motivate his work. Intellectual themes include applied mathematics, artificial intelligence, and scientific computing, with problems arising in engineering and applied science domains. He is particularly interested in Scientific Artificial Intelligence (SciAI) and inverse problems.

Earls has received several awards recognizing his excellence in teaching and research, including the James and Mary Tien Excellence in Teaching Award from the Cornell University College of Engineering in 2016, the Outstanding Young Alumni Award from The Charles E. Via Department of Civil and Environmental Engineering at Virginia Tech in 2004, the Outstanding Professor of the Year Award from the American Society of Civil Engineers Pittsburgh Section in 2001, the Peter S. Michie Outstanding Teacher Award from West Point in 1998, and the Ralph E. Powe Junior Faculty Enhancement Award from Oak Ridge Associated Universities in 2000. He is a lifetime member of the Society for Industrial and Applied Mathematics. Key publications include 'Data-driven discovery of Green’s functions with human-understandable deep learning' (Scientific Reports, 2022, with N. Boullé and A. Townsend), 'PDE-LEARN: Using deep learning to discover partial differential equations from noisy, limited data' (Neural Networks, 2024, with R. Stephany), 'On the inelastic failure of high strength steel I-shaped beams' (Journal of Constructional Steel Research, 1999), 'Model-based structural health monitoring of naval ship hulls' (Computer Methods in Applied Mechanics and Engineering, 2011, with C.J. Stull and P.S. Koutsourelakis), and recent papers on large language models such as 'Density estimation with LLMs: a geometric investigation of in-context learning trajectories' (ICLR, 2025) and 'LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law' (EMNLP, 2024).

Professional Email: earls@cornell.edu