Downscaling land surface temperature data using edge detection and block-diagonal Gaussian process regression

2026-02-02

AI Summary

This study addresses the challenge of low-resolution ECOSTRESS land surface temperature (LST) data being insufficient for high-precision applications such as agricultural evapotranspiration estimation. To overcome this limitation, the authors propose a downscaling method that integrates high-resolution Landsat 8 imagery. By leveraging edge detection to delineate field boundaries, the approach uniquely incorporates parcel-level structural information into a Gaussian process regression model with a block-diagonal covariance structure. This formulation preserves inter-parcel independence while balancing computational efficiency and spatial correlation. The resulting framework effectively fuses multi-source remote sensing data and corrects for scale mismatches, producing high-resolution, high-accuracy LST products accompanied by quantified uncertainty estimates. These enhanced LST outputs are well-suited for diverse applications in precision agriculture, urban planning, and climate research.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Ensemble Methods
• Intelligent Robots: State Estimation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Accurate and high-resolution estimation of land surface temperature (LST) is crucial in estimating evapotranspiration, a measure of plant water use and a central quantity in agricultural applications. In this work, we develop a novel statistical method for downscaling LST data obtained from NASA's ECOSTRESS mission, using high-resolution data from the Landsat 8 mission as a proxy for modeling agricultural field structure. Using the Landsat data, we identify the boundaries of agricultural fields through edge detection techniques, allowing us to capture the inherent block structure present in the spatial domain. We propose a block-diagonal Gaussian process (BDGP) model that captures the spatial structure of the agricultural fields, leverages independence of LST across fields for computational tractability, and accounts for the change of support present in ECOSTRESS observations. We use the resulting BDGP model to perform Gaussian process regression and obtain high-resolution estimates of LST from ECOSTRESS data, along with uncertainty quantification. Our results demonstrate the practicality of the proposed method in producing reliable high-resolution LST estimates, with potential applications in agriculture, urban planning, and climate studies.

Problem

• land surface temperature
• downscaling
• high-resolution estimation
• agricultural applications
• spatial resolution

Innovation

• block-diagonal Gaussian process
• edge detection
• land surface temperature downscaling
• change of support
• spatial statistics