Wasserstein GAN-Based Precipitation Downscaling with Optimal Transport for Enhancing Perceptual Realism
This work addresses the challenge of localized heavy rainfall prediction for weather forecasting, offering an incremental improvement in perceptual realism.
The study tackled the problem of generating high-resolution precipitation forecasts by using a Wasserstein Generative Adversarial Network (WGAN) with optimal transport for downscaling, resulting in visually realistic precipitation fields with fine-scale structures, though with slightly lower performance on conventional metrics.
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.