A GNSS-IR Soil Moisture Inversion Method Considering Multi-Factor Influences Under Different Vegetation Covers

The Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) has demonstrated significant potential for soil moisture content (SMC) monitoring due to its high spatiotemporal resolution. However, GNSS-IR inversion experiments are notably influenced by vegetation and meteorological f...

Full description

Saved in:
Bibliographic Details
Main Authors: Yadong Yao, Jixuan Yan, Guang Li, Weiwei Ma, Xiangdong Yao, Miao Song, Qiang Li, Jie Li
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/8/837
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849712215860445184
author Yadong Yao
Jixuan Yan
Guang Li
Weiwei Ma
Xiangdong Yao
Miao Song
Qiang Li
Jie Li
author_facet Yadong Yao
Jixuan Yan
Guang Li
Weiwei Ma
Xiangdong Yao
Miao Song
Qiang Li
Jie Li
author_sort Yadong Yao
collection DOAJ
description The Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) has demonstrated significant potential for soil moisture content (SMC) monitoring due to its high spatiotemporal resolution. However, GNSS-IR inversion experiments are notably influenced by vegetation and meteorological factors. To address these challenges, this study proposes a multi-factor SMC inversion method. Six GNSS stations from the Plate Boundary Observatory (PBO) were selected as study sites. A low-order polynomial was applied to separate the reflected signals, extracting parameters such as phase, frequency, amplitude, and effective reflector height. Auxiliary variables, including the Normalized Microwave Reflection Index (NMRI), cumulative rainfall, and daily average evaporation, were used to further improve inversion accuracy. A multi-factor SMC inversion dataset was constructed, and three machine learning models were selected to develop the SMC prediction model: Support Vector Regression (SVR), suitable for small and medium-sized regression tasks; Convolutional Neural Networks (CNN), with robust feature extraction capabilities; and NRBO-XGBoost, which supports automatic optimization. The multi-factor SMC inversion method achieved remarkable results. For instance, at the P038 station, the model attained an R<sup>2</sup> of 0.98, with an RMSE of 0.0074 and an MAE of 0.0038. Experimental results indicate that the multi-factor inversion model significantly outperformed the traditional univariate model, whose R<sup>2</sup> (RMSE, MAE) was only 0.88 (0.0179, 0.0136). Further analysis revealed that NRBO-XGBoost surpassed the other models, with its average R<sup>2</sup> outperforming SVR by 0.11 and CNN by 0.03. Additionally, the analysis of different surface types showed that the method achieved higher accuracy in grassland and open shrubland areas, with all models reaching R<sup>2</sup> values above 0.9. Therefore, the accuracy of the multi-factor SMC inversion model was validated, supporting the practical application of GNSS-IR technology in SMC inversion.
format Article
id doaj-art-ec7d79ec8e4b4ff1b25bb59cd4db713d
institution DOAJ
issn 2077-0472
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-ec7d79ec8e4b4ff1b25bb59cd4db713d2025-08-20T03:14:20ZengMDPI AGAgriculture2077-04722025-04-0115883710.3390/agriculture15080837A GNSS-IR Soil Moisture Inversion Method Considering Multi-Factor Influences Under Different Vegetation CoversYadong Yao0Jixuan Yan1Guang Li2Weiwei Ma3Xiangdong Yao4Miao Song5Qiang Li6Jie Li7College of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou 730070, ChinaCollege of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou 730070, ChinaState Key Laboratory of Aridland Crop Science, Ministry and Province Co-Established, Lanzhou 730070, ChinaState Key Laboratory of Aridland Crop Science, Ministry and Province Co-Established, Lanzhou 730070, ChinaCollege of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou 730070, ChinaCollege of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou 730070, ChinaCollege of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou 730070, ChinaCollege of Water Conservancy and Hydropower Engineering, Gansu Agricultural University, Lanzhou 730070, ChinaThe Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) has demonstrated significant potential for soil moisture content (SMC) monitoring due to its high spatiotemporal resolution. However, GNSS-IR inversion experiments are notably influenced by vegetation and meteorological factors. To address these challenges, this study proposes a multi-factor SMC inversion method. Six GNSS stations from the Plate Boundary Observatory (PBO) were selected as study sites. A low-order polynomial was applied to separate the reflected signals, extracting parameters such as phase, frequency, amplitude, and effective reflector height. Auxiliary variables, including the Normalized Microwave Reflection Index (NMRI), cumulative rainfall, and daily average evaporation, were used to further improve inversion accuracy. A multi-factor SMC inversion dataset was constructed, and three machine learning models were selected to develop the SMC prediction model: Support Vector Regression (SVR), suitable for small and medium-sized regression tasks; Convolutional Neural Networks (CNN), with robust feature extraction capabilities; and NRBO-XGBoost, which supports automatic optimization. The multi-factor SMC inversion method achieved remarkable results. For instance, at the P038 station, the model attained an R<sup>2</sup> of 0.98, with an RMSE of 0.0074 and an MAE of 0.0038. Experimental results indicate that the multi-factor inversion model significantly outperformed the traditional univariate model, whose R<sup>2</sup> (RMSE, MAE) was only 0.88 (0.0179, 0.0136). Further analysis revealed that NRBO-XGBoost surpassed the other models, with its average R<sup>2</sup> outperforming SVR by 0.11 and CNN by 0.03. Additionally, the analysis of different surface types showed that the method achieved higher accuracy in grassland and open shrubland areas, with all models reaching R<sup>2</sup> values above 0.9. Therefore, the accuracy of the multi-factor SMC inversion model was validated, supporting the practical application of GNSS-IR technology in SMC inversion.https://www.mdpi.com/2077-0472/15/8/837GNSS-IRSMCsatellite signalenvironmental featuresNRBO-XGBoost
spellingShingle Yadong Yao
Jixuan Yan
Guang Li
Weiwei Ma
Xiangdong Yao
Miao Song
Qiang Li
Jie Li
A GNSS-IR Soil Moisture Inversion Method Considering Multi-Factor Influences Under Different Vegetation Covers
Agriculture
GNSS-IR
SMC
satellite signal
environmental features
NRBO-XGBoost
title A GNSS-IR Soil Moisture Inversion Method Considering Multi-Factor Influences Under Different Vegetation Covers
title_full A GNSS-IR Soil Moisture Inversion Method Considering Multi-Factor Influences Under Different Vegetation Covers
title_fullStr A GNSS-IR Soil Moisture Inversion Method Considering Multi-Factor Influences Under Different Vegetation Covers
title_full_unstemmed A GNSS-IR Soil Moisture Inversion Method Considering Multi-Factor Influences Under Different Vegetation Covers
title_short A GNSS-IR Soil Moisture Inversion Method Considering Multi-Factor Influences Under Different Vegetation Covers
title_sort gnss ir soil moisture inversion method considering multi factor influences under different vegetation covers
topic GNSS-IR
SMC
satellite signal
environmental features
NRBO-XGBoost
url https://www.mdpi.com/2077-0472/15/8/837
work_keys_str_mv AT yadongyao agnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT jixuanyan agnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT guangli agnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT weiweima agnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT xiangdongyao agnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT miaosong agnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT qiangli agnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT jieli agnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT yadongyao gnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT jixuanyan gnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT guangli gnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT weiweima gnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT xiangdongyao gnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT miaosong gnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT qiangli gnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers
AT jieli gnssirsoilmoistureinversionmethodconsideringmultifactorinfluencesunderdifferentvegetationcovers