用最优传输WGAN提升降水降尺度的视觉真实感
Wasserstein GAN-Based Precipitation Downscaling with Optimal Transport for Enhancing Perceptual Realism
- 采用基于最优传输的WGAN进行降水降尺度生成
- 生成结果在细节结构上更逼真，虽指标略低但更符合人眼感知
- 能识别模型输出与参考数据中的异常，适合气象质量评估
高分辨率降水预测对减轻持续性局部强降雨造成的损失至关重要，但基于物理过程的数值天气预报模型实现高分辨率降水预报仍具挑战。本研究提出使用基于最优传输代价的Wasserstein生成对抗网络（WGAN）进行降水降尺度。相比传统均方误差训练的神经网络，该方法生成的降水场在细粒度结构上更具视觉真实性，尽管在常规评估指标上表现稍逊。WGAN学习到的判别器分数与人类感知真实感高度相关。案例分析显示，判别器评分的显著差异可有效识别不合理的生成结果及参考数据中的潜在伪影。这些发现表明，WGAN框架不仅提升了降水降尺度的感知真实感，还为降水数据集的评估与质量控制提供了新视角。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。