DDPS | Industrial Grade Scientific Machine Learning: Challenges and Opportunities by Santi Adavani

Description: There has been increasing interest in Scientific Machine Learning (SciML), which leverages advances in modern deep learning approaches to model complex engineered systems represented by partial differential equations (PDEs). This rapidly evolving research topic is of interest to both academia and industry. Although there has been a recent surge in publications and open source packages, there are several challenges for practitioners in the industry to apply this new paradigm to their respective domain-specific problems. In this talk, we will discuss the challenges that the industry is facing and opportunities for the research community to contribute to transition from traditional forward/inverse PDE solvers to SciML-based solvers for practical applications.

Bio: Santi Adavani is the CTO and co-founder of RocketML. As CTO, Santi drives the technology road map that includes the design and development of scientific machine learning solutions. Prior to RocketML, Santi worked as a Senior Data Scientist and AI product manager at Intel where he led the development of AI systems for automated data management for yield enhancement. He received a Ph.D. from the University of Pennsylvania, where he developed fast algorithms to solve partial differential equations (PDE) constrained optimization problems on supercomputers with applications in electro-cardiology.

LLNL-VIDEO-837987

#LLNL #DataScience #DataDrivenPhysicalSimulation