Gustau Camps-Valls

The Earth is a complex, multivariate and dynamic network system. Machine learning (ML) offers many opportunities but also challenges to modeling and understanding it. We aim to discover variable relations, derive physically interpretable models, that are simple, parsimonious, and mathematically tractable. ML models alone are excellent approximators, but very often do not respect the most elementary laws of physics so consistency and confidence are often compromised. I will review recent advances in ML for vegetation monitoring from space, and developments in physics-aware machine learning, interpretable ML and causal discovery for Earth system sciences. This is a a collective Al agenda towards developing and applying algorithms capable of discovering knowledge in the Earth system.