AM Seminar: Towards Rigorous Frameworks for Scientific Machine Learning: Theory and Applications for Multi-Scale Chaotic Dynamical Systems
Presenter: Ashesh Chattopadhyay
Staff Research Scientist, Palo Alto Research Center
Description: Despite consistent improvements in modern computing infrastructure, predicting the evolution of the states of multi-scale high-dimensional chaotic dynamical systems, such as the Earth’s weather, climate, large-scale engineering systems, and their extremes, such as extreme temperature, wildfire, flooding etc. remains a grand challenge in natural science and engineering. In recent times, with an influx in high-quality observations and high-fidelity simulations, data-driven methods, primarily fueled by the unprecedented success in deep learning, hold significant hope for modeling and predicting high dimensional multi-scale PDEs up to the smallest scales. However, off-the-shelf deep learning algorithms that have received significant success in the computer vision and the natural language communities cannot directly be applied to scientific problems. To that end, this talk would primarily revolve around building rigorous scientific machine learning frameworks at scale, wherein scientific priors/structure, inspired from physics and numerical methods, in the form of inductive bias, novel regularization, etc., can be baked into the deep learning architectures. We would explore different failure modes in the form of instabilities and their mitigation strategies in scientific machine learning models of PDEs, applications to data assimilation in high-dimensional chaotic systems, and finally build an “explanability” framework for out-of distribution generalization of deep hybrid (deep learning and numerical) models of multi-scale PDEs, grounded in physical and deep learning theory.
Bio: Ashesh Chattopadhyay is a staff research scientist at the Palo Alto Research Center in the Intelligent Systems Laboratory. His current research interests are at the intersection of deep learning theory, dynamical systems, and high-performance scientific computing, aimed at building scalable scientific machine learning frameworks for data assimilation and prediction of complex systems. He did his PhD in the department of Mechanical Engineering at Rice University in November 2022, where he worked on scientific machine learning for computational physics. During his PhD, he spent about a year and a half at Lawrence Berkeley National Laboratory, developing physics-constrained generative models for Earth system prediction. Prior to this, he got his master’s in computational science at the University of Texas, El Paso, where he worked on high-performance computing. He got his bachelor’s degree at the Indian Institute of Technology, Patna, India, in Mechanical Engineering, where he worked on computational geometry and optimization for fluid interface modeling.
Monday, January 23 at 12:00pm to 1:00pm
Engineering 2, E2 506
Engineering 2 1156 High Street, Santa Cruz, California 95064