用生成扩散模型将全球气候数据精准放大到区域尺度，提升预报精度。
IPSL-AID: Generative Diffusion Models for Climate Downscaling from Global to Regional Scales
- 基于扩散模型，从粗分辨率输入生成0.25度高分辨率气候图
- 准确还原极端事件、功率谱与空间结构的统计分布特征
- 可生成不确定性量化场景，适合气候风险评估与政策制定
应对气候变化的有效适应与减缓策略需要高分辨率气候投影以支持决策。传统全球气候模型通常分辨率在150至200公里之间，无法刻画关键的区域过程。IPSL-AID是一种基于去噪扩散概率模型的全球到区域降尺度工具，利用ERA5再分析数据训练，通过粗分辨率输入及其时空上下文，生成温度、风速和降水的0.25度分辨率场。该模型还能对细尺度特征建模概率分布，生成具有合理不确定性的可能情景。实验表明，模型能准确重建统计分布，包括极端事件、功率谱和空间结构。本工作展示了生成式扩散模型在高效气候降尺度中的潜力及不确定性量化能力。
原文摘要 · Abstract (English)
Effective adaptation and mitigation strategies for climate change require high-resolution projections to inform strategic decision-making. Conventional global climate models, which typically operate at resolutions of 150 to 200 kilometers, lack the capacity to represent essential regional processes. IPSL-AID is a global to regional downscaling tool based on a denoising diffusion probabilistic model designed to address this limitation. Trained on ERA5 reanalysis data, it generates 0.25 degree resolution fields for temperature, wind, and precipitation using coarse inputs and their spatiotemporal context. It also models probability distributions of fine-scale features to produce plausible scenarios for uncertainty quantification. The model accurately reconstructs statistical distributions, including extreme events, power spectra, and spatial structures. This work highlights the potential of generative diffusion models for efficient climate downscaling with uncertainty
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。