A Perspective on Gaussian Processes for Earth Observation

TL;DR

This paper reviews the use of Gaussian processes in Earth observation, highlighting their advantages in uncertainty quantification and multimodal data integration, while discussing future challenges and directions for physics-aware modeling.

Contribution

It provides a comprehensive perspective on Gaussian processes in EO, emphasizing their current capabilities and outlining future research challenges for physics-informed models.

Findings

GPs offer accurate estimates with uncertainty quantification.

They effectively integrate multimodal and multitemporal data.

Challenges include developing physics-aware, causal inference models.

Abstract

Earth observation (EO) by airborne and satellite remote sensing and in-situ observations play a fundamental role in monitoring our planet. In the last decade, machine learning and Gaussian processes (GPs) in particular has attained outstanding results in the estimation of bio-geo-physical variables from the acquired images at local and global scales in a time-resolved manner. GPs provide not only accurate estimates but also principled uncertainty estimates for the predictions, can easily accommodate multimodal data coming from different sensors and from multitemporal acquisitions, allow the introduction of physical knowledge, and a formal treatment of uncertainty quantification and error propagation. Despite great advances in forward and inverse modelling, GP models still have to face important challenges that are revised in this perspective paper. GP models should evolve towards data-driven physics-aware models that respect signal characteristics, be consistent with elementary laws of physics, and move from pure regression to observational causal inference.