用生成模型提升气候模拟分辨率，保留多变量关联关系。
Generative climate downscaling enables high-resolution compound risk assessment by preserving multivariate dependencies
- 基于扩散模型的多变量生成框架，联合建模多个气象变量。
- 在50倍分辨率提升下，变量间相关性误差降低4倍以上。
- 适合需要高精度复合风险评估的气候决策者使用。
基于物理的气候投影依赖全球气候模型，但其粗分辨率限制了区域决策。统计降尺度可高效增加细节，但许多方法独立处理变量，破坏了决定复合灾害（如热应激、干旱、野火）的关键变量间关系。本文展示一种基于扩散的多变量生成框架，结合偏差校正，在线性分辨率提升50倍的情况下，仍能恢复被破坏的变量间相关性。应用于日本五类气象变量时，该框架相比现有基线方法，将变量间相关性误差减少超过四倍，同时提升了单变量和空间精度，显著改善严重干旱的检测能力。结果表明，多变量生成降尺度可有效提升大分辨率差距下的复合风险评估可靠性。
原文摘要 · Abstract (English)
Physics-based climate projections using general circulation models are essential for assessing future risks, but their coarse resolution limits regional decision-making. Statistical downscaling can efficiently add detail, yet many methods treat variables independently, degrading inter-variable relationships that govern compound hazards such as heat stress, drought, and wildfire. Here we show that a diffusion-based multivariate generative framework, combined with bias correction, recovers degraded inter-variable correlations even under a 50$\times$ increase in linear resolution. When applied to five meteorological variables over Japan, the framework reduces inter-variable correlation errors by more than fourfold relative to existing baselines while improving both univariate and spatial accuracy, leading to more accurate detection of severe drought. These results demonstrate that multivariate generative downscaling improves the reliability of compound risk assessment under large resolution gaps.
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。