Enhancing precipitation detection: A multi-sensor approach using conditional GANs and recurrent networks

Abstract

The advent of automatic precipitation detection with high-frequency data at very low spatial resolution (4 km)renders the satellite infrared brightness temperature (IR-BT) sensor a promising variable. Nevertheless, thisapproach must confront the inherent simplicity of this variable, where there is not always a strong correlationwith convective precipitation, and the very low number of rain events occurring in nature, presenting animbalanced problem. This paper proposes a novel approach to identify rainfall that integrates the IR-BTvariable with lightning activity, defined as the number of detected lightning flashes per unit of time and space.The approach utilizes a recurrent neural network to estimate a binary output and a conditional GAN (cGAN)framework, which enhances the training and performance of this imbalanced problem. Inverse Dice loss, analternative loss function, is employed to enhance the convergence and results of our framework: PD-GAN.Tests have shown that integrating sensors and the proposed architecture leads to positive outcomes, includinga reduction in false alarms and an enhancement in the overlap of positive events.