用物理守恒的输运机制，实现气象超分辨率重建。
CASCADE: Cross-scale Advective Super-resolution with Climate Assimilation and Downscaling Evolution
- 将超分辨率视为跨尺度输运过程，通过学习速度场迭代推演细节。
- 在4倍超分辨率任务中，各项指标均优于基线模型，且结果时序一致。
- 适合需要物理一致性与质量守恒的极端天气模拟与预测场景。
地表物理场的超分辨率面临超越自然图像增强的独特挑战：细粒度结构必须符合物理动力学、保持质量与能量守恒，并在时间上协同演化。这些约束对极端事件尤为重要，因为罕见、局部且高强度的特征驱动影响，而时间不一致的“幻觉”细节可能扭曲灾害风险。我们提出CASCADE（跨尺度输运型超分辨率，融合气候同化与降尺度演化），将时空超分辨率重新定义为显式的跨尺度输运过程。不同于逐像素幻化高频内容，CASCADE通过学习的速度场，沿半拉格朗日变形迭代推进粗分辨率信息，重建精细结构。该架构将运动分解为可解析（大尺度）与次网格（未解析）分量，类比数值天气预报中的闭合问题，并通过同化风格的创新步骤保证低分辨率一致性。在SEVIR雷达数据上对强对流风暴进行4倍超分辨率评估，CASCADE在连续指标（PSNR、SSIM、MAE）和阈值型技能评分（CSI、HSS、POD）上均超越强基线模型，同时提供可解释的可视化速度场与修正场。通过将输运作为基本算子而非隐式学习，CASCADE生成时间一致、物理合理且质量守恒的重构结果，适用于大气与海洋中以输运为主导的极端现象。
原文摘要 · Abstract (English)
Super-resolution of geophysical fields presents unique challenges beyond natural image enhancement: fine-scale structures must respect physical dynamics, conserve mass and energy, and evolve coherently in time. These constraints are especially critical for extreme events, where rare, localized, high-intensity features drive impacts and where temporally inconsistent "hallucinated" detail can misrepresent hazards. We introduce CASCADE (Cross-scale Advective Super-resolution with Climate Assimilation and Downscaling Evolution), a framework that reframes spatiotemporal super-resolution as an explicit transport process across scales. Rather than hallucinating high-frequency content per pixel, CASCADE reconstructs fine structure by iteratively advecting coarse information along learned, flow-conditioned velocity fields through semi-Lagrangian warping. The architecture decomposes motion into resolved (large-scale) and subgrid (unresolved) components, mirroring the closure problem in numerical weather prediction, and enforces low-resolution consistency through an assimilation-style innovation step. Evaluated on SEVIR radar data for 4x super-resolution of severe convective storms, CASCADE outperforms strong baselines across both continuous metrics (PSNR, SSIM, MAE) and threshold-based skill scores (CSI, HSS, POD) while providing interpretable diagnostics through visualizable velocity and correction fields. By encoding advection as the fundamental operator rather than learning it implicitly, CASCADE produces temporally coherent, physically consistent, and mass-conserving reconstructions well suited to advection-dominated extremes in atmospheric and oceanic applications.
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。