少即是多：面向极端高温的数据高效千米尺度降尺度的误差-距离标度关系

中文摘要 AI 辅助

极端高温是城市适应最需要千米尺度数据的领域，但训练降尺度模型的模拟成本可能超过其节省的成本，且所需数据量尚未明确。我们通过CASPER（一种采用结构保持损失的U-Net模型，将32千米再分析数据降尺度至1千米的温度、湿度和风场）在1至8个月的24种配置下对其进行了测量。留出误差随与训练数据的气候距离线性增长，RMSE = 0.83 + 2.95 d，解释了其方差的90%，而数据量仅解释7%的方差，并可提前预测未见月份。在留出的极端夏季周中，CASPER保留了细尺度结构和跨变量物理特性，而这些在同等预算的基线方法中会退化；在有记录的极端高温事件期间，CASPER与站点观测的匹配误差在1.8 K以内。迁移到新区域时性能会随地理变化而下降；11天的本地模拟将温哥华的留出误差从3.8 K降至1.3 K。训练期应覆盖目标气候：以四倍少的模拟量达到相同精度，使无大型计算设施的研究团队也能进行千米尺度极端高温降尺度。

英文摘要

Extreme heat is where urban adaptation needs kilometer-scale data the most, but the simulations training a downscaler can cost more than they save, and how much is needed has not been identified. We measured it with CASPER, a U-Net with a structure-preserving loss downscaling 32 km reanalysis to 1 km temperature, humidity and wind, across 24 configurations of one to eight months. Held-out error grows linearly with climatological distance to the training data, RMSE = 0.83 + 2.95 d, explaining 90% of its variance against 7% for volume and predicting unseen months in advance. On held-out extreme summer weeks CASPER preserves the fine-scale structure and cross-variable physics that matched-budget baselines degrade, and matches station observations during documented heat waves to within 1.8 K. Transfer to a new region degrades geographically; 11 days of local simulation cuts Vancouver's held-out error from 3.8 to 1.3 K. Training periods should span the target climate: the same accuracy for four times less simulation, putting kilometer-scale downscaling of extreme heat within reach of groups without large computing facilities.

发表机构

• Concordia University（康考迪亚大学）
• National Research Council Canada（加拿大国家研究委员会）
• The American University in Cairo（开罗美国大学）
• Mila – Quebec Artificial Intelligence Institute（Mila——魁北克人工智能研究所）
• McGill University（麦吉尔大学）
• Université de Montréal（蒙特利尔大学）

机构由 AI 辅助整理，请以论文原文为准。