用扩散模型将气候模拟器分辨率从300公里提升至25公里，精准还原区域气候细节。
High-Resolution Climate Projections Using Diffusion-Based Downscaling of a Lightweight Climate Emulator
- 基于条件扩散模型，将轻量级气候模拟器输出从300公里分辨率下放至25公里。
- 在2010–2020年数据上验证，生成结果在纬向均方根误差和风场主成分上表现优异。
- 适合需要高分辨率气候预测的区域影响评估，如极端天气与生态研究。
数据驱动模型在气象与气候科学中引发重大范式转变，先进模型在中短期预报中表现出色。然而，这些模型常受限于长期不稳定性、气候漂移及训练与推理时的巨大计算成本，制约其在气候研究中的广泛应用。为解决这些问题，Guan等（2024）提出LUCIE，一种基于球面傅里叶神经算子（SFNO）架构的轻量化、物理一致气候模拟器，能准确再现气候平均态与季节变率。但其原始分辨率约300公里，不足以支持精细区域影响评估。为此，本文引入基于深度学习的降尺度框架，采用概率性扩散生成模型结合条件与后验采样机制，将粗分辨率的LUCIE输出下放到25公里。模型在2000–2009年共约14,000个ERA5时间步上训练，并在2010–2020年LUCIE预测结果上评估。性能通过纬向均方根误差、功率谱、概率密度函数及经向风第一主成分等多种指标衡量。结果显示，该方法在保持LUCIE粗尺度动态的同时，生成了约28公里分辨率的精细气候统计特征。
原文摘要 · Abstract (English)
The proliferation of data-driven models in weather and climate sciences has marked a significant paradigm shift, with advanced models demonstrating exceptional skill in medium-range forecasting. However, these models are often limited by long-term instabilities, climatological drift, and substantial computational costs during training and inference, restricting their broader application for climate studies. Addressing these limitations, Guan et al. (2024) introduced LUCIE, a lightweight, physically consistent climate emulator utilizing a Spherical Fourier Neural Operator (SFNO) architecture. This model is able to reproduce accurate long-term statistics including climatological mean and seasonal variability. However, LUCIE's native resolution (~300 km) is inadequate for detailed regional impact assessments. To overcome this limitation, we introduce a deep learning-based downscaling framework, leveraging probabilistic diffusion-based generative models with conditional and posterior sampling frameworks. These models downscale coarse LUCIE outputs to 25 km resolution. They are trained on approximately 14,000 ERA5 timesteps spanning 2000-2009 and evaluated on LUCIE predictions from 2010 to 2020. Model performance is assessed through diverse metrics, including latitude-averaged RMSE, power spectrum, probability density functions and First Empirical Orthogonal Function of the zonal wind. We observe that the proposed approach is able to preserve the coarse-grained dynamics from LUCIE while generating fine-scaled climatological statistics at ~28km resolution.
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。