Global, spatially explicit modelling of zenith wet delay with XGBoost

IF 3.9 2区地球科学 Q1 GEOCHEMISTRY & GEOPHYSICS

Journal of Geodesy Pub Date : 2024-04-05 DOI:10.1007/s00190-024-01829-2

{"title":"Global, spatially explicit modelling of zenith wet delay with XGBoost","authors":"","doi":"10.1007/s00190-024-01829-2","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>Radio signals transmitted by Global Navigation Satellite System (GNSS) satellites experience tropospheric delays. While the hydrostatic part, referred to as zenith hydrostatic delay (ZHD) when mapped to the zenith direction, can be analytically modelled with sufficient accuracy, the wet part, referred to as zenith wet delay (ZWD), is much more difficult to determine and needs to be estimated. Thus, there exist several ZWD models which are used for various applications such as positioning and climate research. In this study, we present a data-driven, global model of the spatial ZWD field, based on the Extreme Gradient Boosting (XGBoost). The model takes the geographical location, the time, and a number of meteorological variables (in particular, specific humidity at several pressure levels) as input, and can predict ZWD anywhere on Earth as long as the input features are available. It was trained on ZWDs at 10718 GNSS stations and tested on ZWDs at 2684 GNSS stations for the year 2019. Across all test stations and all observations, the trained model achieved a mean absolute error of 6.1 mm, respectively, a root mean squared error of 8.1 mm. Comparisons of the XGBoost-based ZWD predictions with independently computed ZWDs and baseline models underline the good performance of the proposed model. Moreover, we analysed regional and monthly models, as well as the seasonal behaviour of the ZWD predictions in different climate zones, and found that the global model exhibits a high predictive skill in all regions and across all months of the year.</p>","PeriodicalId":54822,"journal":{"name":"Journal of Geodesy","volume":"46 1","pages":""},"PeriodicalIF":3.9000,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Geodesy","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1007/s00190-024-01829-2","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GEOCHEMISTRY & GEOPHYSICS","Score":null,"Total":0}

引用次数: 0

Abstract

Radio signals transmitted by Global Navigation Satellite System (GNSS) satellites experience tropospheric delays. While the hydrostatic part, referred to as zenith hydrostatic delay (ZHD) when mapped to the zenith direction, can be analytically modelled with sufficient accuracy, the wet part, referred to as zenith wet delay (ZWD), is much more difficult to determine and needs to be estimated. Thus, there exist several ZWD models which are used for various applications such as positioning and climate research. In this study, we present a data-driven, global model of the spatial ZWD field, based on the Extreme Gradient Boosting (XGBoost). The model takes the geographical location, the time, and a number of meteorological variables (in particular, specific humidity at several pressure levels) as input, and can predict ZWD anywhere on Earth as long as the input features are available. It was trained on ZWDs at 10718 GNSS stations and tested on ZWDs at 2684 GNSS stations for the year 2019. Across all test stations and all observations, the trained model achieved a mean absolute error of 6.1 mm, respectively, a root mean squared error of 8.1 mm. Comparisons of the XGBoost-based ZWD predictions with independently computed ZWDs and baseline models underline the good performance of the proposed model. Moreover, we analysed regional and monthly models, as well as the seasonal behaviour of the ZWD predictions in different climate zones, and found that the global model exhibits a high predictive skill in all regions and across all months of the year.

查看原文本刊更多论文

利用 XGBoost 对天顶湿延迟进行全球空间显式建模

摘要全球导航卫星系统（GNSS）卫星发射的无线电信号会出现对流层延迟。静压部分（映射到天顶方向时称为天顶静压延迟（ZHD））可以用足够精确的方法进行分析建模，而湿压部分（称为天顶湿延迟（ZWD））则更难确定，需要进行估算。因此，有多种 ZWD 模型可用于定位和气候研究等各种应用。在本研究中，我们提出了一种基于极端梯度提升（XGBoost）的数据驱动型全球空间 ZWD 场模型。该模型将地理位置、时间和一些气象变量（特别是几个气压水平下的比湿度）作为输入，只要输入特征可用，就能预测地球上任何地方的 ZWD。该预测方法根据 10718 个全球导航卫星系统站点的 ZWD 进行了训练，并根据 2019 年 2684 个全球导航卫星系统站点的 ZWD 进行了测试。在所有测试站和所有观测数据中，训练模型的平均绝对误差为 6.1 毫米，均方根误差为 8.1 毫米。将基于 XGBoost 的 ZWD 预测与独立计算的 ZWD 和基线模型进行比较，凸显了所提出模型的良好性能。此外，我们还分析了区域和月度模型，以及不同气候区 ZWD 预测的季节性表现，发现全球模型在所有区域和全年所有月份都表现出较高的预测能力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Geodesy 地学-地球化学与地球物理

CiteScore

8.60

自引率

9.10%

发文量

审稿时长

9 months

期刊介绍： The Journal of Geodesy is an international journal concerned with the study of scientific problems of geodesy and related interdisciplinary sciences. Peer-reviewed papers are published on theoretical or modeling studies, and on results of experiments and interpretations. Besides original research papers, the journal includes commissioned review papers on topical subjects and special issues arising from chosen scientific symposia or workshops. The journal covers the whole range of geodetic science and reports on theoretical and applied studies in research areas such as: -Positioning -Reference frame -Geodetic networks -Modeling and quality control -Space geodesy -Remote sensing -Gravity fields -Geodynamics