基于XGBoost模型的广西区域PWV估算及极端降雨分析

Estimation of PWV and Analysis of Extreme Rainfall in Guangxi Region Based on XGBoost Model

ES评分 0

DOI 10.14075/j.jgg.2025.08.295
刊名
Journal of Geodesy and Geodynamics
年,卷(期) 2026, 46(6)
作者
作者单位

1 桂林理工大学测绘地理信息学院, 桂林, 541006;
2 长安大学地质工程与测绘学院, 西安, 710054;
3 桂林市气象局, 桂林, 541001

摘要
针对气象参数缺失情况下实时/近实时GNSS PWV反演受限的问题, 基于XGBoost模型分别建立广西区域3种无需实测气象参数的PWV估算模型。首先建立输入为站点时间(DOY和HOD)、位置(Longitude、Latitude和Height)和GNSS ZTD, 输出特征为GNSS PWV的XGBZ-PWV模型, 然后在XGBZ-PWV模型的基础上分别加入2种经验PWV, 建立XGBZG-PWV模型和XGBZE-PWV模型。同时, 基于GNSS ZTD, 利用GPT3模型提供的气压与温度反演PWV(GPT3-PWV模型), 对所建PWV模型进行对比, 并以2022年广西区域基于GNSS ZTD、ERA5地表气压和温度反演的GNSS PWV作为参考值对所建立的模型进行精度验证。结果表明, 相比于GPT3-PWV模型, XGBZ-PWV、XGBZG-PWV和XGBZE-PWV模型的估算精度分别提升22.98%、29.03%和31.45%, 其中, XGBZE-PWV模型最优。在2022年2次极端降雨过程中, 对PWV与降雨的时空演变特征进行分析, 结果表明, XGBZE-PWV模型在极端天气条件下依然具有较好的适用性。
Abstract
Aiming at the limitation of real/near-real-time GNSS PWV retrieval under missing meteorological parameters, three PWV estimation models without the need for measured meteorological parameters were established in the Guangxi region based on the XGBoost model. First, the XGBZ-PWV model was developed with inputs including station time (DOY and HOD), location (Longitude, Latitude, and Height), and GNSS ZTD, and the output feature being GNSS PWV. Then, based on the XGBZ-PWV model, two empirical PWV values were incorporated to establish the XGBZG-PWV and XGBZE-PWV models, respectively. For comparison, the GPT3 model was used to provide pressure and temperature for PWV retrieval based on GNSS ZTD (GPT3-PWV model). The accuracy of the established models was validated using GNSS PWV retrieved from GNSS ZTD, ERA5 surface pressure, and temperature in the Guangxi region in 2022 as the reference value. The results show that, compared to the GPT3-PWV model, the estimation accuracy of the XGBZ-PWV, XGBZG-PWV, and XGBZE-PWV models improved by 22.98%, 29.03%, and 31.45%, respectively, with the XGBZE-PWV model performing the best. During two extreme rainfall events in 2022, the spatiotemporal evolution characteristics of PWV and rainfall were analyzed. The results demonstrate that the XGBZE-PWV model maintains good applicability even under extreme weather conditions.
关键词
ZTD; PWV; GNSS; XGBoost; 降雨
KeyWord
ZTD; PWV; GNSS; XGBoost; rainfall
基金项目
页码 702-709
  • 参考文献
  • 相关文献
  • 引用本文

闫立伟, 林买金, 谢劭峰, 黄良珂, 李向红, 方琼玉. 基于XGBoost模型的广西区域PWV估算及极端降雨分析 [J]. 大地测量与地球动力学. 2026; 46; (6). 702 - 709.

  • 文献评论

相关学者

相关机构