用分层扩散模型实现低成本高分辨率气候模拟
Generate the Forest before the Trees -- A Hierarchical Diffusion model for Climate Downscaling
- 分层采样设计，从粗到细逐步生成气候数据
- 仅需一半像素计算量，精度仍达主流水平
- 单模型适配多气候模型，适合大规模预测
降尺度对生成本地规划所需高分辨率气候数据至关重要，但传统方法计算成本高。近年来，基于扩散模型的AI降尺度方法展现出优异性能，能生成集合解并克服其他AI方法的平滑问题，但仍面临计算负担重的挑战。本文提出分层扩散降尺度（HDD）模型，通过简单下采样构建从粗到细的层次结构，引入可扩展的分层采样流程。HDD在ERA5再分析数据集和CMIP6模型上均达到竞争性精度，计算负载显著降低，运行时最多仅需原方法一半像素即可保持良好表现。此外，一个在0.25°分辨率训练的单一模型可无缝迁移至多个分辨率更粗的CMIP6模型。HDD为概率性气候降尺度提供轻量化替代方案，推动低成本大集合高分辨率气候预测的普及。完整代码见：https://github.com/HDD-Hierarchical-Diffusion-Downscaling/HDD-Hierarchical-Diffusion-Downscaling。
原文摘要 · Abstract (English)
Downscaling is essential for generating the high-resolution climate data needed for local planning, but traditional methods remain computationally demanding. Recent years have seen impressive results from AI downscaling models, particularly diffusion models, which have attracted attention due to their ability to generate ensembles and overcome the smoothing problem common in other AI methods. However, these models typically remain computationally intensive. We introduce a Hierarchical Diffusion Downscaling (HDD) model, which introduces an easily-extensible hierarchical sampling process to the diffusion framework. A coarse-to-fine hierarchy is imposed via a simple downsampling scheme. HDD achieves competitive accuracy on ERA5 reanalysis datasets and CMIP6 models, significantly reducing computational load by running on up to half as many pixels with competitive results. Additionally, a single model trained at 0.25° resolution transfers seamlessly across multiple CMIP6 models with much coarser resolution. HDD thus offers a lightweight alternative for probabilistic climate downscaling, facilitating affordable large-ensemble high-resolution climate projections. See a full code implementation at: https://github.com/HDD-Hierarchical-Diffusion-Downscaling/HDD-Hierarchical-Diffusion-Downscaling.
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。