Downscaling Microwave Brightness Temperatures Using Self Regularized Regressive Models

TL;DR

This paper introduces SRRM, a novel downscaling algorithm for microwave brightness temperatures that leverages auxiliary variables and biophysical models to achieve high-resolution estimates for hydrological and agricultural use.

Contribution

The paper presents a new self-regularized regression approach that combines clustering and kernel regression for effective downscaling of microwave brightness temperatures.

Findings

Achieved RMSE of 5.76 K during vegetated season

Achieved RMSE of 1.2 K during non-vegetated periods

Demonstrated effectiveness on synthetic data over NC-Florida

Abstract

A novel algorithm is proposed to downscale microwave brightness temperatures ($\mathrm{T_B}$), at scales of 10-40 km such as those from the Soil Moisture Active Passive mission to a resolution meaningful for hydrological and agricultural applications. This algorithm, called Self-Regularized Regressive Models (SRRM), uses auxiliary variables correlated to $\mathrm{T_B}$ along-with a limited set of \textit{in-situ} SM observations, which are converted to high resolution $\mathrm{T_B}$ observations using biophysical models. It includes an information-theoretic clustering step based on all auxiliary variables to identify areas of similarity, followed by a kernel regression step that produces downscaled $\mathrm{T_B}$. This was implemented on a multi-scale synthetic data-set over NC-Florida for one year. An RMSE of 5.76~K with standard deviation of 2.8~k was achieved during the vegetated season and an RMSE of 1.2~K with a standard deviation of 0.9~K during periods of no vegetation.