Hybrid & Causal Machine learning in the Earth sciences

Tuesday 16th January 2024 17:00 CET


Professor Gustau Camps-Valls


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 plausible, that are simple parsimonious, and mathematically tractable. While machine learning models excel as approximators, they often disregard fundamental physics laws, compromising consistency and confidence. To address these challenges, we propose exploring the interplay between domain knowledge and machine learning. Physics-aware and hybrid machine learning models are seen as necessary steps toward understanding the data-generating process, with causality offering significant advancements. I will discuss recent hybrid and causal machine learning methodologies to attain consistent and explainable results. This work outlines a collective, long-term AI agenda for developing algorithms that can discover knowledge in the Earth system.


Gustau Camps-Valls is a Full Professor in Electrical Engineering at the
Universitat de Valencia. He is an expert in machine learning
algorithms for geosciences and remote sensing data analysis, having
published extensively. He has a Ph.D. in Physics and is an IEEE
Distinguished Lecturer. He has received two European Research Council
(ERC) grants and holds a Hirsch’s index h=88 (Google Scholar). He is
also a Highly Cited Researcher since 2020. Gustau has achieved
significant recognition with numerous awards and honors, including IEEE
Fellow (2018), ELLIS Fellow (2019), Fellow of the European Academy of
Sciences (EurASc), the Academia Europeae (AE), and the Asia-Pacific
Artificial Intelligence Association (AAIA) all in 2021.



Meeting ID: 960 4989 6433
Passcode: 405011


More events