WaveOp-LiteFM：用于卫星到雷达降水反演的轻量级神经算子流匹配方法
WaveOp-LiteFM: Lightweight Neural-Operator Flow Matching for Satellite-to-Radar Precipitation Retrieval
AI总结：
针对卫星到雷达降水反演中流匹配模型的精度与效率权衡问题，提出WaveOp-LiteFM框架，通过SLW块等设计实现高性能低计算成本，在多数据集及台风案例中验证了有效性。
AI中文摘要：
卫星到雷达（S2R）反演是指从静止卫星观测数据中估算地基雷达降水，以实现雷达覆盖有限区域的降水监测。尽管近期生成式流匹配模型大幅提升了反演质量，但它们面临关键权衡：像素空间公式存在基于注意力的U-Net速度网络计算成本过高的问题，而潜空间建模则常牺牲精细降水细节或难以处理稀疏目标。为解决这一困境，我们提出WaveOp-LiteFM，一种用于S2R反演的轻量级神经算子流匹配框架。该方法引入基于谱局部小波（SLW）块的新型速度骨干网络，实现像素空间中高效且稳定的流匹配。具体而言，SLW块将降水特征解耦为三个不同频率区域：（i）谱分支捕获大尺度层状结构；（ii）局部分支建模短程相互作用；（iii）小波分支增强尖锐结构同时抑制噪声高频响应。基于此设计，输入自适应门控机制动态融合三个功能分支的特征。此外，跳跃门通过解码器内的加法融合高效重新整合编码器特征，避免了传统U-Net架构中代价高昂的通道拼接。在SEVIR和中国东南部数据集上的实验表明，WaveOp-LiteFM实现了最先进的反演性能，同时大幅降低了计算成本。除基准评估外，对中国大范围区域（包括近期巴威台风案例）的大范围推理显示，WaveOp-LiteFM在大规模真实场景中仍保持可靠的反演质量。
英文摘要：
Satellite-to-radar (S2R) retrieval refers to estimating ground-based radar precipitation from geostationary satellite observations, enabling precipitation monitoring in regions with limited radar coverage. While recent generative flow matching models have greatly advanced retrieval quality, they face a critical trade-off: pixel-space formulations suffer from the prohibitive computational costs of attention-based U-Net velocity networks, whereas latent-space modeling often sacrifices fine precipitation details or struggles with sparse targets. To address this dilemma, we propose WaveOp-LiteFM, a lightweight neural operator flow matching framework for S2R retrieval. Our approach introduces a novel velocity backbone built upon the spectral-local-wavelet (SLW) block, enabling efficient and stable flow matching in pixel space. Specifically, the SLW block disentangles precipitation features into three distinct frequency regimes: (i) the spectral branch captures large-scale stratiform organization; (ii) the local branch models short-range interactions; and (iii) the wavelet branch enhances sharp structures while suppressing noisy high-frequency responses. Building on this design, an input-adaptive gating mechanism dynamically fuses features from the three functional branches. Furthermore, a skip gate efficiently reintegrates encoder features through additive fusion within the decoder, avoiding the costly channel concatenation used in conventional U-Net architectures. Experiments on the SEVIR and Southeast China datasets show that WaveOp-LiteFM achieves state-of-the-art retrieval performance while substantially reducing computational costs. Beyond benchmark evaluation, large-area inference over China, including a recent Typhoon Bavi case, demonstrates that WaveOp-LiteFM maintains reliable retrieval quality in large-scale real-world scenarios.
