发表机构
University of Florida; Stony Brook University; University of Maryland; University of Colorado Boulder; Pacific Northwest National Laboratory（佛罗里达大学; 石溪大学; 马里兰大学; 科罗拉多大学博尔德分校; 太平洋西北国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究基于小波扩散模型评估降水降尺度的跨区域泛化能力，发现全区域训练模型性能最佳，且样本级空间自相关与检测性能高度相关，支持向数据稀缺区域迁移。
AI 中文摘要
扩散模型在千米尺度降水降尺度方面展现出巨大潜力，但其在地理上未见过的区域和事件类型中的性能仍未得到充分理解。本研究基于小波扩散模型（WDM）框架，评估了跨区域和跨事件的泛化能力。六个3x3度的美国区域代表了对流、冬季、热带和大气河降水类型。低分辨率输入通过对NOAA多雷达/多传感器（MRMS）合成反射率场进行块平均生成。将仅在俄克拉荷马州（OK）样本上训练的WDM与在所有六个区域上训练的WDM进行比较，并与最近邻和双三次插值方法对比。模型性能使用三个指标族进行评估，分别衡量图像域重建、频谱和分布保真度以及逐箱降水检测。仅在OK训练的WDM在OK之外仍具有竞争力。尽管全区域WDM在整体图像域和检测性能上表现最佳且最一致，但其增益在不同降水强度下并不均匀。在5-dBZ反射率箱上的逐箱关键成功指数（CSI）显示，WDM的改进集中在局部高反射率结构中，而图像域指标部分掩盖了这些改进。此外，样本间的性能差异与降水场的空间组织密切相关，通过Moran's I（每个反射率箱的空间自相关）量化。按样本强度分层的样本级Moran's I-CSI相关性在所有六个区域达到0.901，包括训练中未见过的区域。总体而言，这些发现支持未来将降尺度模型迁移到本地训练数据有限的区域，并生成全球一致的高分辨率降水产品的努力。
英文摘要
Diffusion models have shown strong potential for kilometer-scale precipitation downscaling, but their performance in geographically unseen regions and event regimes remains insufficiently understood. Building on the wavelet diffusion model (WDM) framework, this study evaluates cross-region and cross-event generalization. Six 3 x 3 deg U.S. regions represent convective, winter, tropical, and atmospheric-river precipitation regimes. Low-resolution inputs are generated by block averaging NOAA Multi-Radar/Multi-Sensor (MRMS) composite reflectivity fields. A WDM trained only on Oklahoma (OK) samples and a WDM trained on all six regions are compared with nearest-neighbor and Bicubic interpolation. Model performance is evaluated using three metric families that measure image-domain reconstruction, spectral and distributional fidelity, and bin-wise precipitation detection. The OK-trained WDM remains competitive outside OK. Although the all-region WDM delivers the best and most consistent overall image-domain and detection performance, its gains are uneven across precipitation intensities. Bin-wise critical success index (CSI) over 5-dBZ reflectivity bins shows that WDM improvements concentrate in localized higher-reflectivity structures, which image-domain metrics partly obscure. In addition, the performance differences among samples are strongly associated with the spatial organization of the precipitation field, quantified by Moran's I as the spatial autocorrelation of each reflectivity bin. The sample-level Moran's I-CSI correlation stratified by sample intensity reaches 0.901 in all six regions, including regions unseen during training. Overall, these findings support future efforts to transfer downscaling models to regions with limited local training data and to generate globally consistent, high-resolution precipitation products.
