Aggregated Gaussian Processes with Multiresolution Earth Observation Covariates

TL;DR

This paper introduces a Gaussian process regression model that effectively integrates multiresolution covariates from satellite and weather data for spatial modeling, improving prediction accuracy and interpretability.

Contribution

The paper presents a novel additive kernel approach for Gaussian processes that efficiently aggregates multiresolution covariates, outperforming existing resolution-matching methods.

Findings

Enhanced predictive performance on simulated and crop yield datasets.

Better preservation of distributional information across resolutions.

Improved interpretability of spatial models.

Abstract

For many survey-based spatial modelling problems, responses are observed as spatially aggregated over survey regions due to limited resources. Covariates, from weather models and satellite imageries, can be observed at many different spatial resolutions, making the pre-processing of covariates a key challenge for any spatial modelling task. We propose a Gaussian process regression model to flexibly handle multiresolution covariates by employing an additive kernel that can efficiently aggregate features across resolutions. Compared to existing approaches that rely on resolution matching, our approach better maintains distributional information across resolutions, leading to better performance and interpretability. Our model yields stronger predictive performance and interpretability on both simulated and crop yield datasets.