Title: Physics aware and Interpretable Machine Learning for the Earth Sciences.
Date & Time: 15 June 2021, 16:00 CET (10:00 EST).
Abstract:
Abstract: Most problems in Earth sciences aim to do inferences about the system, where accurate predictions are just a tiny part of the whole problem. Inferences mean understanding variables relations, deriving models that are physically interpretable, that are simple parsimonious, and mathematically tractable. Machine learning models alone are excellent approximators, but very often do not respect the most elementary laws of physics, like mass or energy conservation, so consistency and confidence are compromised. I will review the main challenges ahead in the field, and introduce several ways to live in the Physics and machine learning interplay that allow us (1) to encode differential equations from data, (2) constrain data-driven models with physics-priors and dependence constraints, (3) improve parameterizations, (4) emulate physical models, and (5) blend data-driven and process-based models. This is a collective long-term AI agenda towards developing and applying algorithms capable of discovering knowledge in the Earth system.
Speaker’s Bio:
Gustau Camps-Valls (IEEE Fellow’18, IEEE Distinguished lecturer, PhD in Physics) is currently a Full professor in Electrical Engineering and head of the Image and Signal Processing (ISP) group, http://isp.uv.es. He is interested in the development of machine learning algorithms for geosciences and remote sensing data analysis, and in particular the intersection between physics, statistical learning and causal inference. He is an author of around 250 journal papers, more than 300 conference papers, 20 international book chapters, and editor of 6 books on kernel methods and deep learning. He holds a Hirsch’s index h=75 (Google Scholar), entered the ISI list of Highly Cited Researchers in 2011, and Thomson Reuters ScienceWatch identified one of his papers on kernel-based analysis of hyperspectral images as a Fast Moving Front research. He received two European Research Council (ERC) grants: an ERC Consolidator grant on “Statistical learning for Earth observation data analysis” (2015) and an ERC Synergy grant on “Understanding and Modelling the Earth system with machine learning” (2019). In 2016 he was included in the prestigious IEEE Distinguished Lecturer program of the GRSS.
===========================================================================
The Association for AI in Science and Industry (www.aaisi.org).
The AI Colloquium -Invited Speech.
Participation is FREE and OPEN to all.
Prior REGISTRATION is required.
Registration Deadline: March 29, 2021.
Registration Link: To be announced.
===========================================================================
