无需配对数据，用扩散模型实现跨气候模型的物理一致降尺度。
Zero-Shot Statistical Downscaling via Diffusion Posterior Sampling
- 基于再分析数据学习物理一致性先验，结合地理与时间信息约束生成
- 在99百分位误差上显著优于现有零样本方法，能重建台风等复杂天气
- 引入统一坐标引导机制，解决大比例缩放下的梯度消失问题
传统监督式气候降尺度因缺乏配对训练数据及与再分析数据之间的域差距，难以泛化到不同全球气候模型（GCMs）。当前零样本方法存在物理不一致和大缩放因子下梯度消失问题。本文提出零样本统计降尺度（ZSSD），一种无需训练时使用配对数据的零样本框架。ZSSD利用从再分析数据中学习的物理一致性气候先验，通过地理边界和时间信息进行条件控制以保证物理合理性。此外，为实现对不同GCM的鲁棒推理，引入统一坐标引导策略，有效缓解原始扩散后验采样中的梯度消失问题，并确保与大尺度场的一致性。实验表明，ZSSD在99百分位误差上显著优于现有零样本基线，并成功在异构GCM间重建了台风等复杂天气事件。
原文摘要 · Abstract (English)
Conventional supervised climate downscaling struggles to generalize to Global Climate Models (GCMs) due to the lack of paired training data and inherent domain gaps relative to reanalysis. Meanwhile, current zero-shot methods suffer from physical inconsistencies and vanishing gradient issues under large scaling factors. We propose Zero-Shot Statistical Downscaling (ZSSD), a zero-shot framework that performs statistical downscaling without paired data during training. ZSSD leverages a Physics-Consistent Climate Prior learned from reanalysis data, conditioned on geophysical boundaries and temporal information to enforce physical validity. Furthermore, to enable robust inference across varying GCMs, we introduce Unified Coordinate Guidance. This strategy addresses the vanishing gradient problem in vanilla DPS and ensures consistency with large-scale fields. Results show that ZSSD significantly outperforms existing zero-shot baselines in 99th percentile errors and successfully reconstructs complex weather events, such as tropical cyclones, across heterogeneous GCMs.
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。