SATFRONT: 利用卫星数据和机器学习检测大气锋面
SATFRONT: Detecting Atmospheric Fronts with Satellite Data using Machine Learning
Ioannis Dravilas · Miruna Stoicescu · Roope Tervo · Carlos Horn · Oriol Hinojo Comellas · Sina Montazeri · et al.
中文摘要
中纬度地区许多高影响天气与大气锋面相关，但锋面的识别和分类仍主要依赖人工和主观判断。现有深度学习方法主要依赖网格化再分析或预报数据，限制了其在时间紧迫应用中可用的卫星观测上的适用性。SATFRONT 是一个机器学习框架，利用地球静止卫星观测检测欧洲上空的冷锋、暖锋和锢囚锋，再分析数据作为可选附加输入。模型使用五个欧洲国家气象局的锋面分析训练，并针对 2024 年英国气象局分析进行评估。仅使用卫星观测时，SATFRONT 在 150 km 容差下达到 0.428 的临界成功指数（CSI），处于不同气象局分析之间的一致性范围（0.277-0.501）内，且高于使用卫星数据的业务化规则锋面检测器（0.133）。加入 ERA5 再分析后，CSI 提升至 0.591。ERA5 显著改善单个锋面的位置，但其对锋面年空间分布的影响因锋面类型而异。这些结果表明，冷锋、暖锋和锢囚锋可直接从地球静止卫星观测中检测，为时间紧迫应用所需的高时间频率自动锋面分析提供了基础。
关键要点
- 01现有深度学习方法依赖再分析或预报数据，难以用于时间紧迫的卫星观测应用。
- 02SATFRONT 仅用卫星观测检测冷锋、暖锋和锢囚锋，150 km 容差下 CSI 为 0.428。
- 03该分数处于不同气象局分析一致性范围（0.277-0.501）内，高于规则检测器的 0.133。
- 04加入 ERA5 再分析后 CSI 升至 0.591，显著改善单个锋面位置。
- 05ERA5 对锋面年空间分布的影响因锋面类型而异。
解读
尚无解读。
原始英文摘要
arXiv:2610.42111v1 Announce Type: cross Abstract: Atmospheric fronts are associated with much of the high-impact weather in the mid-latitudes, yet their identification and classification remain largely manual and subjective. Existing deep learning approaches rely primarily on gridded reanalysis or forecast data, limiting their applicability to satellite observations available for time-critical applications. We introduce SATFRONT, a machine learning framework for detecting cold, warm, and occluded fronts over Europe from geostationary satellite observations, with reanalysis data as an optional additional input. The model is trained on frontal analyses from five European national meteorological services and evaluated against UK Met Office analyses for 2024. Using satellite observations alone, SATFRONT achieves a Critical Success Index (CSI) of 0.428 at a 150 km tolerance, within the range of agreement between analyses from different meteorological services (0.277-0.501) and higher than that of an operational rule-based front detector that uses satellite data (0.133). Adding ERA5 reanalysis increases the CSI to 0.591. ERA5 substantially improves the placement of individual fronts, although its effect on their annual spatial distribution varies by front type. These results demonstrate that cold, warm, and occluded fronts can be detected directly from geostationary satellite observations, providing a basis for automated frontal analyses at the high temporal frequency required for time-critical applications.