Downscaling land surface temperature data using edge detection and block-diagonal Gaussian process regression
This work addresses the need for accurate high-resolution LST estimation for applications in agriculture, urban planning, and climate studies, but it is incremental as it builds on existing Gaussian process methods with a domain-specific adaptation.
The paper tackled the problem of downscaling low-resolution land surface temperature (LST) data from NASA's ECOSTRESS mission to high-resolution estimates by developing a block-diagonal Gaussian process model that leverages edge detection on Landsat 8 data to capture agricultural field boundaries, resulting in reliable high-resolution LST estimates with uncertainty quantification.
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.