逐点是否无意义？基于图神经网络的降水临近预报的多模态消融研究
Pointwise is Pointless? A Multimodal Ablation Study for Precipitation Nowcasting with Graph Neural Networks
AI总结：
本研究通过多模态图神经网络系统，消融分析雷达、数值预报、地面观测、卫星数据及训练损失对降水临近预报的影响，发现各模态分别改善不同方面，点观测虽提升局部但需结合损失函数和不确定性表示才能优化雷达场。
摘要：
稀疏点观测在降水临近预报中日益可用，但尚不清楚它们能在多大程度上改善密集雷达场预报。我们通过北欧雷达区域的多模态图神经网络临近预报系统部分回答了这个问题。该模型预测未来两小时内每五分钟的降雨率，并采用雷达历史、MEPS数值天气预报、Netatmo地面观测、MSG卫星通道、随机噪声和基于CRPS的集合损失的不同组合进行训练。本研究设计为对操作相关信源和训练目标的消融。我们比较了仅雷达、NWP信息、站点信息、卫星信息、噪声增强和基于CRPS的配置，使用雷达网格、站点位置、降雨起始的互补诊断，以及oracle、位移和幅度评分。结果表明，每个信源改善了预报问题的不同方面。MEPS稳定了仅雷达外推，Netatmo观测改善了局部站点和起始诊断，卫星预测因子减少了某些站点级偏差，但在确定性使用时可能过早激活降雨。基于CRPS的配置提供了最一致的雷达网格增益，而卫星与CRPS的组合设置给出了最佳的整体oracle/DAS评分。这些结果不支持点观测对临近预报无用的结论，但表明局部观测技能和空间相干雷达场技能是不同的目标。实际意义是，稀疏观测可以提供有用的局部约束，但它们对雷达类场的益处取决于训练损失、不确定性表示以及观测支持在模型中的编码方式。
英文摘要：
Sparse point observations are increasingly available for precipitation nowcasting, but it is unclear how much they improve dense radar-field forecasts. We partially address this question with a multimodal graph neural network nowcasting system over the Nordic radar domain. The model predicts rain rate every five minutes up to two hours ahead and is trained with different combinations of radar history, MEPS numerical weather prediction, Netatmo surface observations, MSG satellite channels, stochastic noise, and CRPS-based ensemble losses. The study is designed as an ablation of operationally relevant information sources and training objectives. We compare radar-only, NWP-informed, station-informed, satellite-informed, noise-augmented, and CRPS-based configurations using complementary diagnostics on the radar grid, at station locations, for rain onset, and through oracle, displacement, and amplitude scores. The results show that each source improves a different part of the forecast problem. MEPS stabilises radar-only extrapolation, Netatmo observations improve local station and onset diagnostics, and satellite predictors reduce some station-level biases but may activate rain too early when used deterministically. CRPS-based configurations provide the most consistent radar-grid gains, while the combined satellite and CRPS setup gives the best overall oracle/DAS score. These results do not support the conclusion that point observations are uninformative for nowcasting, but they show that local observational skill and spatially coherent radar-field skill are distinct targets. The practical implication is that sparse observations can provide useful local constraints, but their benefit for radar-like fields depends on the training loss, uncertainty representation, and how observation support is encoded in the model.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
