测试生成模型在不同地区降水降尺度中的通用性与迁移能力
On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling
- 用全球15个区域数据分层划分，评估模型跨区域性能
- 基于ERA5和IMERG数据，0.1度分辨率下验证生成模型泛化效果
- 揭示现有模型在新地理区域的适用边界，指导实际应用
深度学习在气候与天气预报的统计降尺度中展现出巨大潜力，生成式方法尤其擅长捕捉精细尺度的降水模式。然而，大多数现有模型具有区域局限性，其在未见地理区域的泛化能力仍缺乏系统研究。本研究评估生成式降尺度模型在全球范围内的泛化表现。采用全球框架，以ERA5再分析数据为预测因子，以IMERG在0.1°分辨率下的降水估测值为目标。通过分层级的位置数据划分，对全球15个不同区域进行系统性性能评估，检验模型在多样地理环境下的适应能力。
原文摘要 · Abstract (English)
Deep learning offers promising capabilities for the statistical downscaling of climate and weather forecasts, with generative approaches showing particular success in capturing fine-scale precipitation patterns. However, most existing models are region-specific, and their ability to generalize to unseen geographic areas remains largely unexplored. In this study, we evaluate the generalization performance of generative downscaling models across diverse regions. Using a global framework, we employ ERA5 reanalysis data as predictors and IMERG precipitation estimates at $0.1^\circ$ resolution as targets. A hierarchical location-based data split enables a systematic assessment of model performance across 15 regions around the world.
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。