发表机构
Neurogica Inc.; LTS, Inc.; ME-Lab Japan, Inc.（Neurogica 公司; LTS 公司; ME-Lab Japan 公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出尺度递归修正流，通过先粗后细生成及按尺度分配采样步数，在少步降水集合中提升概率准确性与降雨检测，优于非递归流。
AI 中文摘要
精细分辨率的降水估计支持洪水风险评估和水资源管理，但粗分辨率的卫星产品无法解析每个网格单元内的降雨。生成模型通过生成一系列合理的、高分辨率的降雨场来解决这种模糊性。在这些模型中，修正流通过迭代地将随机噪声转换为降雨场来生成样本。减少采样步数可加速生成，但可能使集合成员过于相似，从而低估不确定性。我们提出了一种尺度递归修正流，它先生成宽泛模式，再生成局部细节，并通过比较空间尺度上的集合变率与预测误差来指导采样步数的分配。验证分数和降雨功率谱约束了这种分配，以避免过度放大。在美国本土的卫星到雷达降尺度实验中，我们的分析确定了在减少采样预算下，宽泛降雨模式是集合变率不足的主要来源。在固定架构和计算成本下，将更多步数分配给粗尺度流提高了跨训练种子的概率准确性和降雨检测能力。所提出的模型还以更短的采样时间实现了比使用更多步数的非递归流更好的概率准确性。
英文摘要
Fine-resolution precipitation estimates support flood risk assessment and water management, but coarse satellite products cannot resolve rainfall within each grid cell. Generative models address this ambiguity by producing ensembles of plausible high-resolution rainfall fields. Among these models, rectified flows generate samples by iteratively transforming random noise into rainfall fields. Reducing the number of sampling steps accelerates generation but can make ensemble members too similar, understating uncertainty. We propose a scale-recursive rectified flow that generates broad patterns before local details and guides sampling-step allocation by comparing ensemble variability with prediction error across spatial scales. Validation scores and rainfall power spectra constrain the allocation to avoid excessive amplification. In satellite-to-radar downscaling over the contiguous United States, our analysis identified broad rainfall patterns as the main source of insufficient ensemble variability under reduced sampling budgets. Allocating more steps to the coarse flow improved probabilistic accuracy and rain detection across training seeds at fixed architecture and computational cost. The proposed model also achieved better probabilistic accuracy with shorter sampling time than a nonrecursive flow using more steps.
