Data-Driven Subgrid-Scale Modeling - Stability, Extrapolation, & Interpretation

Explore data-driven subgrid-scale modeling techniques in this 39-minute conference talk by Pedram Hassanzadeh at the Kavli Institute for Theoretical Physics. Delve into the challenges of stability, extrapolation, and interpretation in climate modeling as part of the Machine Learning for Climate KITP conference. Gain insights into how big data and machine learning algorithms are revolutionizing climate science, enabling detailed analysis of multi-scale processes encompassing physical, chemical, and biological realms. Discover how these advanced techniques are enhancing our ability to make informed predictions about future climate changes at regional and local scales. Learn about the potential for descriptive inference to drive new theories and validate existing ones in climate science. Understand the importance of interdisciplinary collaboration in addressing key climate change problems and advancing our understanding of the Earth system.