Climate downscaling is a crucial technique within climate research, serving to project low-resolution (LR) climate data to higher resolutions (HR). Previous research has demonstrated the effectiveness of deep learning for downscaling tasks. However, most deep learning models for climate downscaling may not perform optimally for high scaling factors (i.e., 4x, 8x) due to their limited ability to capture the intricate details required for generating HR climate data. Furthermore, climate data behaves differently from image data, necessitating a nuanced approach when employing deep generative models. In response to these challenges, this paper presents a deep generative model for downscaling climate data, specifically precipitation on a regional scale. We employ a denoising diffusion probabilistic model (DDPM) conditioned on multiple LR climate variables. The proposed model is evaluated using precipitation data from the Community Earth System Model (CESM) v1.2.2 simulation. Our results demonstrate significant improvements over existing baselines, underscoring the effectiveness of the conditional diffusion model in downscaling climate data.

翻译：气候降尺度是气候研究中的关键技术，旨在将低分辨率气候数据投影至高分辨率。已有研究表明深度学习在降尺度任务中的有效性。然而，多数用于气候降尺度的深度学习模型在高放大倍数（如4倍、8倍）条件下性能欠佳，因其难以捕捉生成高分辨率气候数据所需的精细细节。此外，气候数据与图像数据存在本质差异，需采用更细致的方法运用深度生成模型。针对上述挑战，本文提出一种面向区域尺度降水数据降尺度的深度生成模型。该模型采用以多种低分辨率气候变量为条件的去噪扩散概率模型。我们利用社区地球系统模型v1.2.2模拟的降水数据对模型进行验证。结果表明，相较于现有基线方法，本模型实现了显著性能提升，充分验证了条件扩散模型在气候数据降尺度中的有效性。