Reproduce “A Perspective on Gaussian Processes for Earth Observation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Gustau Camps-Valls, Dino Sejdinovic, Jakob Runge, Markus Reichstein
The authors present a perspective on Gaussian processes for Earth observation, arguing that models should combine data with physical knowledge and move toward causal inference. They describe Gaussian-process retrievals and emulators, physics-aware models, and GP-based causal discovery, while noting computational and data challenges. The perspective reports no new experiments; observational causal methods may not determine direction without additional assumptions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.