Rainfall regression from C-band Synthetic Aperture Radar using Multi-Task Generative Adversarial Networks

TL;DR

This paper presents a novel multi-task GAN-based method to accurately estimate rainfall from SAR data, overcoming collocation issues and improving performance in windy conditions.

Contribution

It introduces a multi-objective GAN framework that leverages NEXRAD and Sentinel-1 data to enhance rainfall estimation accuracy from SAR imagery.

Findings

Improved rainfall estimation accuracy over previous methods.

Effective extension of model performance up to wind speeds of 15 m/s.

Successful integration of multi-source data for better collocation handling.

Abstract

This paper introduces a data-driven approach to estimate precipitation rates from Synthetic Aperture Radar (SAR) at a spatial resolution of 200 meters per pixel. It addresses previous challenges related to the collocation of SAR and weather radar data, specifically the misalignment in collocations and the scarcity of rainfall examples under strong wind. To tackle these challenges, the paper proposes a multi-objective formulation, introducing patch-level components and an adversarial component. It exploits the full NEXRAD archive to look for potential co-locations with Sentinel-1 data. With additional enhancements to the training procedure and the incorporation of additional inputs, the resulting model demonstrates improved accuracy in rainfall estimates and the ability to extend its performance to scenarios up to 15 m/s.