ZWDX: a global zenith wet delay forecasting model using XGBoost

Abstract Tropospheric delays play a crucial role for Global Navigation Satellite Systems (GNSS). They are a major error source in GNSS positioning and, at the same time, also a variable of interest in GNSS meteorology. Regardless of whether the delay shall be eliminated or inverted to atmospheric pa...

Full description

Saved in:
Bibliographic Details
Main Authors: Laura Crocetti, Matthias Schartner, Marcus Franz Wareyka-Glaner, Konrad Schindler, Benedikt Soja
Format: Article
Language:English
Published: SpringerOpen 2024-12-01
Series:Earth, Planets and Space
Subjects:
Online Access:https://doi.org/10.1186/s40623-024-02104-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850133720130912256
author Laura Crocetti
Matthias Schartner
Marcus Franz Wareyka-Glaner
Konrad Schindler
Benedikt Soja
author_facet Laura Crocetti
Matthias Schartner
Marcus Franz Wareyka-Glaner
Konrad Schindler
Benedikt Soja
author_sort Laura Crocetti
collection DOAJ
description Abstract Tropospheric delays play a crucial role for Global Navigation Satellite Systems (GNSS). They are a major error source in GNSS positioning and, at the same time, also a variable of interest in GNSS meteorology. Regardless of whether the delay shall be eliminated or inverted to atmospheric parameters, and no matter how this is done, it is of utmost importance to accurately determine tropospheric delays. In this study, we present a global zenith wet delay (ZWD) model, called ZWDX, that offers accurate spatial and temporal ZWD predictions at any desired location on Earth. ZWDX is based on the XGBoost algorithm and uses ZWDs measured at over 19,000 GNSS stations as reference. The inputs of ZWDX are the geographical location, observation time, and specific humidity at nine atmospheric pressure levels. For our study, we train the model on the years 2010 to 2021 and then test it for the year 2022. While ZWDX is trained to predict ZWD values based on specific humidity values from the ERA5 reanalysis, we show that it also delivers good predictions when applied to HRES specific humidity forecasts, making it suitable for (short-term) ZWD forecasting. The ZWDX model predictions are evaluated at 2500 globally distributed, spatio-temporally independent GNSS stations, with forecasting horizons ranging from 0 h to 48 h, and achieve root mean squared errors (RMSE) between 10.1 mm and 16.2 mm. To independently evaluate ZWDX’s performance and to demonstrate its potential for a real-world downstream task, we use its predictions as a-priori values for a precise point positioning (PPP) analysis and compare the results with those obtained using ZWD values from VMF1 or VMF3. We find that the highest accuracy and fastest convergence are indeed achieved with ZWDX. Graphical Abstract
format Article
id doaj-art-e341371072174f6b985b7d7d1be75458
institution OA Journals
issn 1880-5981
language English
publishDate 2024-12-01
publisher SpringerOpen
record_format Article
series Earth, Planets and Space
spelling doaj-art-e341371072174f6b985b7d7d1be754582025-08-20T02:31:54ZengSpringerOpenEarth, Planets and Space1880-59812024-12-0176111610.1186/s40623-024-02104-6ZWDX: a global zenith wet delay forecasting model using XGBoostLaura Crocetti0Matthias Schartner1Marcus Franz Wareyka-Glaner2Konrad Schindler3Benedikt Soja4Institute of Geodesy and Photogrammetry, ETH ZurichInstitute of Geodesy and Photogrammetry, ETH ZurichDepartment of Geodesy and Geoinformation, TU WienInstitute of Geodesy and Photogrammetry, ETH ZurichInstitute of Geodesy and Photogrammetry, ETH ZurichAbstract Tropospheric delays play a crucial role for Global Navigation Satellite Systems (GNSS). They are a major error source in GNSS positioning and, at the same time, also a variable of interest in GNSS meteorology. Regardless of whether the delay shall be eliminated or inverted to atmospheric parameters, and no matter how this is done, it is of utmost importance to accurately determine tropospheric delays. In this study, we present a global zenith wet delay (ZWD) model, called ZWDX, that offers accurate spatial and temporal ZWD predictions at any desired location on Earth. ZWDX is based on the XGBoost algorithm and uses ZWDs measured at over 19,000 GNSS stations as reference. The inputs of ZWDX are the geographical location, observation time, and specific humidity at nine atmospheric pressure levels. For our study, we train the model on the years 2010 to 2021 and then test it for the year 2022. While ZWDX is trained to predict ZWD values based on specific humidity values from the ERA5 reanalysis, we show that it also delivers good predictions when applied to HRES specific humidity forecasts, making it suitable for (short-term) ZWD forecasting. The ZWDX model predictions are evaluated at 2500 globally distributed, spatio-temporally independent GNSS stations, with forecasting horizons ranging from 0 h to 48 h, and achieve root mean squared errors (RMSE) between 10.1 mm and 16.2 mm. To independently evaluate ZWDX’s performance and to demonstrate its potential for a real-world downstream task, we use its predictions as a-priori values for a precise point positioning (PPP) analysis and compare the results with those obtained using ZWD values from VMF1 or VMF3. We find that the highest accuracy and fastest convergence are indeed achieved with ZWDX. Graphical Abstracthttps://doi.org/10.1186/s40623-024-02104-6Zenith wet delay (ZWD)Global predictionsXGBoostMachine learning (ML)GNSSPrecise point positioning (PPP)
spellingShingle Laura Crocetti
Matthias Schartner
Marcus Franz Wareyka-Glaner
Konrad Schindler
Benedikt Soja
ZWDX: a global zenith wet delay forecasting model using XGBoost
Earth, Planets and Space
Zenith wet delay (ZWD)
Global predictions
XGBoost
Machine learning (ML)
GNSS
Precise point positioning (PPP)
title ZWDX: a global zenith wet delay forecasting model using XGBoost
title_full ZWDX: a global zenith wet delay forecasting model using XGBoost
title_fullStr ZWDX: a global zenith wet delay forecasting model using XGBoost
title_full_unstemmed ZWDX: a global zenith wet delay forecasting model using XGBoost
title_short ZWDX: a global zenith wet delay forecasting model using XGBoost
title_sort zwdx a global zenith wet delay forecasting model using xgboost
topic Zenith wet delay (ZWD)
Global predictions
XGBoost
Machine learning (ML)
GNSS
Precise point positioning (PPP)
url https://doi.org/10.1186/s40623-024-02104-6
work_keys_str_mv AT lauracrocetti zwdxaglobalzenithwetdelayforecastingmodelusingxgboost
AT matthiasschartner zwdxaglobalzenithwetdelayforecastingmodelusingxgboost
AT marcusfranzwareykaglaner zwdxaglobalzenithwetdelayforecastingmodelusingxgboost
AT konradschindler zwdxaglobalzenithwetdelayforecastingmodelusingxgboost
AT benediktsoja zwdxaglobalzenithwetdelayforecastingmodelusingxgboost