Understanding Climate Impacts on Vegetation with Gaussian Processes in Granger Causality

TL;DR

This paper introduces a novel nonlinear Granger causality method using Gaussian processes to analyze climate impacts on vegetation, providing sharper spatial insights from 30 years of satellite and climate data.

Contribution

It generalizes kernel Granger causality with Gaussian processes, explicitly modeling variable cross-relations and offering tighter performance bounds.

Findings

Identified clear Granger causal links from precipitation and soil moisture to vegetation greenness.

Enhanced spatial resolution of climate-vegetation causal footprints.

Method outperforms previous GC approaches in accuracy and interpretability.

Abstract

Global warming is leading to unprecedented changes in our planet, with great societal, economical and environmental implications, especially with the growing demand of biofuels and food. Assessing the impact of climate on vegetation is of pressing need. We approached the attribution problem with a novel nonlinear Granger causal (GC) methodology and used a large data archive of remote sensing satellite products, environmental and climatic variables spatio-temporally gridded over more than 30 years. We generalize kernel Granger causality by considering the variables cross-relations explicitly in Hilbert spaces, and use the covariance in Gaussian processes. The method generalizes the linear and kernel GC methods, and comes with tighter bounds of performance based on Rademacher complexity. Spatially-explicit global Granger footprints of precipitation and soil moisture on vegetation greenness are identified more sharply than previous GC methods.