Wasserstein GAN-Based Precipitation Downscaling with Optimal Transport for Enhancing Perceptual Realism

TL;DR

This paper introduces a Wasserstein GAN approach with optimal transport for precipitation downscaling, significantly enhancing the perceptual realism of high-resolution forecasts beyond traditional metrics.

Contribution

It demonstrates that WGAN can produce more visually realistic precipitation fields and provides a new method for evaluating dataset quality and realism.

Findings

WGAN-generated fields show improved perceptual realism.

Critic scores correlate with human perception.

Large critic score discrepancies identify unrealistic outputs.

Abstract

High-resolution (HR) precipitation prediction is essential for reducing damage from stationary and localized heavy rainfall; however, HR precipitation forecasts using process-driven numerical weather prediction models remains challenging. This study proposes using Wasserstein Generative Adversarial Network (WGAN) to perform precipitation downscaling with an optimal transport cost. In contrast to a conventional neural network trained with mean squared error, the WGAN generated visually realistic precipitation fields with fine-scale structures even though the WGAN exhibited slightly lower performance on conventional evaluation metrics. The learned critic of WGAN correlated well with human perceptual realism. Case-based analysis revealed that large discrepancies in critic scores can help identify both unrealistic WGAN outputs and potential artifacts in the reference data. These findings suggest that the WGAN framework not only improves perceptual realism in precipitation downscaling but also offers a new perspective for evaluating and quality-controlling precipitation datasets.