统计与基于机器学习的集合天气预报后处理空间插值方法比较
Statistical versus machine learning-based spatial interpolation of post-processed ensemble weather forecasts
浏览论文内容
中文总结 AI 辅助
本研究比较统计与机器学习方法对ECMWF集合预报进行空间插值后处理，提出海拔感知线性池（ALP），在无观测站点实现小而显著的改进。
中文摘要 AI 辅助
统计后处理可改善集合天气预报，但在无观测地点生成校准预测仍具挑战性。本研究比较了统计和基于机器学习的方法，用于对德国有观测和无观测站点的ECMWF 2米温度和10米风速预报进行后处理。我们在有限和扩展预测变量设置下考虑了基于EMOS的方法、分布回归网络、Transformer和图神经网络。对于温度，我们还研究了线性预报组合，并提出了一种海拔感知线性池（ALP）。结果表明，在大多数设置下，后处理优于原始集合，但没有任何单一方法在所有变量、站点组和评估指标上表现最佳。所提出的ALP在无观测地点相比标准线性池提供了小而显著的改进。
英文摘要
Statistical post-processing improves ensemble weather forecasts, but generating calibrated predictions at locations without observations remains challenging. This study compares statistical and machine-learning-based methods for post-processing ECMWF 2-m temperature and 10-m wind speed forecasts at observed and unobserved stations in Germany. We consider EMOS-based approaches, distributional regression networks, Transformers, and graph neural networks under both limited and extended predictor settings. For temperature, we also investigate linear forecast combinations and propose an altitude-aware linear pool (ALP). The results show that post-processing improves upon the raw ensemble in most settings, but no single method performs best across all variables, station groups, and evaluation metrics. The proposed ALP provides a small but significant improvement over the standard linear pool at unobserved locations.
发表机构
- Faculty of Informatics, University of Debrecen（德布勒森大学信息学院）
机构由 AI 辅助整理，请以论文原文为准。
