Research on the Application of CYGNSS Data and Machine Learning for Monitoring and Predicting Soil Salinity in the Ben Tre Area, Vinh Long Province
Main Article Content
Abstract
Abstract: Soil salinity is a serious environmental problem, directly affecting crop productivity and sustainable agricultural development, especially in the context of climate change. This study develops a low-cost method for mapping soil electrical conductivity (EC), based on machine learning combined with multi-source remote sensing data for the Ben Tre area, Vinh Long province, a coastal plain region of the Mekong Delta, Vietnam. Three machine learning models (CatBoost (CB), Random Forest (RF), XGBoost (XGB)) were used with 17 input variables extracted from MODIS imagery, ancillary data, and GNSS-R reflectivity data from the CYGNSS satellite. Feature importance analysis revealed that Surface Reflectivity (SR) derived from CYGNSS was one of the three most important predictors. The performance comparison showed a distinction between the models' learning capabilities and their generalization performance. On the training set, CatBoost demonstrated superior learning capability (R = 0.89), followed by XGB (R = 0.84) and RF (R = 0.83). However, on the validation set, RF model showed the best generalization performance, achieving R = 0.71. The resulting salinity distribution map indicates a clear spatial trend: salinity increases from the inland Western areas to the coastal Eastern areas. The research results confirm the feasibility of integrating machine learning and GNSS-R data for soil salinity monitoring.
Keywords:
Soil salinity, CYGNSS, Machine learning, Remote sensing, Ben Tre, Vinh Long.
References
[1] T. G. Nguyen, N. A. Tran, P. L. Vu, Q. H. Nguyen, H. D. Nguyen, Q. T. Bui, Salinity Intrusion Prediction Using Remote Sensing and Machine Learning in Data-Limited Regions: A Case Study in Vietnam’s Mekong Delta, Geoderma Regional, Vol. 27, 2021, pp. e00424, https://doi.org/10.1016/j.geodrs.2021.e00424.
[2] F. Khormali, M. Ajami, S. Ayoubi, C. Srinivasarao, S. P. Wani, Role of Deforestation and Hillslope Position on Soil Quality Attributes of Loess-Derived Soils in Golestan Province, Iran, Agriculture, Ecosystems & Environment, Vol. 134, No. 3, 2009, pp. 178-189, https://doi.org/10.1016/j.agee.2009.06.017.
[3] B. Wicke et al., The Global Technical and Economic Potential of Bioenergy from Salt-Affected Soils, Energy and Environmental Science, Vol. 4, No. 8, 2011, pp. 2669-2681, https://doi.org/10.1039/C1EE01029H.
[4] T. Gorji, E. Sertel, A. Tanik, Monitoring Soil Salinity via Remote Sensing Technology Under Data Scarce Conditions: A Case Study From Turkey, Ecological Indicators, Vol. 74, 2017,
pp. 384-391, https://doi.org/10.1016/j.ecolind.2016.11.043.
[5] Ministry of Agriculture and Rural Development, Summary Report on Drought and Salinity Intrusion in the Southern Region 2019-2020, https://phongchongthientai.mard.gov.vn/Pages/bao-cao-tong-hop-tinh-hinh-han-han-xam-nhap-man-khu-vuc-mien-nam-2019--2020.aspx, 2020 (accessed on: April 09, 2026) (in Vietnamese).
[6] Ministry of Agriculture and Rural Development, Salinity Intrusion Causes Ben Tre to Lose Thousands of Billions of VND Every Year, https://phongchongthientai.mard.gov.vn/Pages/xam-nhap-man-khien-ben-tre-thiet-hai-hang-ngan-ti-dong-moi-nam.aspx, 2022 (accessed on: April 09, 2026) (in Vietnamese).
[7] T. Gorji, A. Tanik, E. Sertel, Soil Salinity Prediction, Monitoring and Mapping Using Modern Technologies, Procedia Earth and Planetary Science, Vol. 15, 2015, pp. 507-512, https://doi.org/10.1016/j.proeps.2015.08.062.
[8] V. L. Mulder, S. De Bruin, M. E. Schaepman, T. R. Mayr, The Use of Remote Sensing in Soil and Terrain Mapping - A Review, Geoderma, Vol. 162, No. 1, 2011, pp. 1-19, https://doi.org/10.1016/j.geoderma.2010.12.018.
[9] H. D. Nguyen, D. K. Dang, Q. T. Bui, Estuary Salinity Prediction Using Machine Learning: Case Study in the Hau Estuary in Mekong River, Vietnam, Water Supply, Vol. 25, No. 2, 2025, pp. 327-342, https://doi.org/10.2166/ws.2025.007.
[10] A. A. A. Aldabaa, D. C. Weindorf, S. Chakraborty, A. Sharma, B. Li, Combination of Proximal and Remote Sensing Methods for Rapid Soil Salinity Quantification, Geoderma, Vol. 239-240, 2015,
pp. 34-46, https://doi.org/10.1016/j.geoderma.2014.09.011.
[11] J. Ding, D. Yu, Monitoring and Evaluating Spatial Variability of Soil Salinity in Dry and Wet Seasons in the Werigan–Kuqa Oasis, China, Using Remote Sensing and Electromagnetic Induction Instruments, Geoderma, Vol. 235-236, 2014,
pp. 316-322, https://doi.org/10.1016/j.geoderma.2014.07.028.
[12] Y. Liu, et al., Estimating the Soil Salinity Over Partially Vegetated Surfaces From Multispectral Remote Sensing Image Using Non-Negative Matrix Factorization, Geoderma, Vol. 354, 2019, pp. 113887, https://doi.org/10.1016/j.geoderma.2019.113887.
[13] S. H. Yueh, R. Shah, M. J. Chaubell, A. Hayashi, X. Xu, A. Colliander, A Semiempirical Modeling of Soil Moisture, Vegetation, and Surface Roughness Impact on CYGNSS Reflectometry Data, IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, 2022, pp. 1-17, https://doi.org/10.1109/TGRS.2020.3035989.
[14] H. Kim, V. Lakshmi, Use of Cyclone Global Navigation Satellite System (CyGNSS) Observations for Estimation of Soil Moisture, Geophysical Research Letters, Vol. 45, No. 16, 2018, pp. 8272-8282, https://doi.org/10.1029/2018GL078923.
[15] J. Wang et al., A Novel Retrieval Model for Soil Salinity From CYGNSS: Algorithm and Test in the Yellow River Delta, Geoderma, Vol. 432, 2023, pp. 116417, https://doi.org/10.1016/j.geoderma.2023.116417.
[16] C. Chew, E. Small, Description of the UCAR/CU Soil Moisture Product, Remote Sensing, Vol. 12, No. 10, 2020, https://doi.org/10.3390/rs12101558.
[17] C. Chew, Soil Moisture Sensing Using Spaceborne GNSS Reflections: Comparison of CYGNSS Reflectivity to SMAP Soil Moisture, Geophysical Research Letters, 2018, https://doi.org/10.1029/2018GL077905.
[18] P. Ghasemigoudarzi, W. Huang, O. De Silva, Q. Yan, D. T. Power, Flash Flood Detection From CYGNSS Data Using the RUSBoost Algorithm, IEEE Access, Vol. 8, 2020, pp. 171864-171881, https://doi.org/10.1109/ACCESS.2020.3025302.
[19] W. Yang, F. Guo, X. Zhang, Y. Zhu, Z. Li, Z. Zhang, First Quasi-Global Soil Moisture Retrieval Using Fengyun-3 GNSS-R Constellation Observations, Remote Sensing of Environment, Vol. 321, 2025, pp. 114653, https://doi.org/10.1016/j.rse.2025.114653.
[20] Y. Zhu, F. Guo, X. Zhang, Spaceborne GNSS-R Soil Moisture Retrieval From GPS/BDS-3/Galileo Satellites, GPS Solutions, Vol. 29, No. 1, 2024, pp. 10, https://doi.org/10.1007/s10291-024-01767-8.
[21] T. T. Zhang, J. G. Qi, Y. Gao, Z. T. Ouyang, S. L. Zeng, B. Zhao, Detecting Soil Salinity With MODIS Time Series VI Data, Ecological Indicators, Vol. 52, 2015, pp. 480-489, https://doi.org/10.1016/j.ecolind.2015.01.004.
[22] L. Breiman, Random Forests, Machine Learning, Vol. 45, No. 1, 2001, pp. 5-32, https://doi.org/10.1023/A:1010933404324.
[23] T. Chen, C. Guestrin, XGBoost: A Scalable Tree Boosting System, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785-794, https://doi.org/10.1145/2939672.2939785.
[24] L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, A. Gulin, CatBoost: Unbiased Boosting With Categorical Features, Advances in Neural Information Processing Systems, Vol. 31, 2018.
https://doi.org/10.48550/arXiv.1706.09516.
[25] O. Eroglu, M. Kurum, D. Boyd, A. C. Gurbuz, High Spatio-Temporal Resolution CYGNSS Soil Moisture Estimates Using Artificial Neural Networks, Remote Sensing, Vol. 11, No. 19, 2019, https://doi.org/10.3390/rs11192272.
[26] E. Vermote, R. Wolfe, MOD09GQ MODIS/Terra Surface Reflectance Daily L2G Global 250m SIN Grid V006, NASA EOSDIS Land Processes Distributed Active Archive Center (DAAC) Data Set, 2015, pp. MOD09GQ.006, https://doi.org/10.5067/MODIS/MOD09GQ.006.
[27] H. D. Nguyen et al., Soil Salinity Prediction Using Hybrid Machine Learning and Remote Sensing in Ben Tre Province on Vietnam’s Mekong River Delta, Environmental Science and Pollution Research, Vol. 30, No. 29, 2023, pp. 74340-74357, https://doi.org/10.1007/s11356-023-27516-x.
[28] A. Calabia, I. Molina, S. Jin, Soil Moisture Content From GNSS Reflectometry Using Dielectric Permittivity From Fresnel Reflection Coefficients, Remote Sensing, Vol. 12, No. 1, 2020, https://doi.org/10.3390/rs12010122.
[29] Y. U. Haq, M. Shahbaz, S. Asif, K. Ouahada, H. Hamam, Identification of Soil Types and Salinity Using MODIS Terra Data and Machine Learning Techniques in Multiple Regions of Pakistan, Sensors, Vol. 23, No. 19, 2023, https://doi.org/10.3390/s23198121.
[30] J. Friedman, T. Hastie, R. Tibshirani, Additive Logistic Regression: A Statistical View of Boosting (With Discussion and a Rejoinder by the Authors), The Annals of Statistics, Vol. 28, No. 2, 2000, pp. 337-407, https://doi.org/10.1214/aos/1016218223.
[31] J. H. Friedman, Greedy Function Approximation: A Gradient Boosting Machine, The Annals of Statistics, Vol. 29, No. 5, 2001, pp. 1189-1232, https://doi.org/10.1214/aos/1013203451.
[32] A. Zarei, M. Hasanlou, M. Mahdianpari, A Comparison of Machine Learning Models for Soil Salinity Estimation Using Multi-Spectral Earth Observation Data, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. V-3, 2021, pp. 257-263, https://doi.org/10.5194/isprs-annals-V-3-2021-257-2021.
[33] S. Aksoy, E. Sertel, R. Roscher, A. Tanik, N. Hamzehpour, Assessment of Soil Salinity Using Explainable Machine Learning Methods and Landsat 8 Images, International Journal of Applied Earth Observation and Geoinformation, Vol. 130, 2024, pp. 103879, https://doi.org/10.1016/j.jag.2024.103879.
[34] A. Samat, E. Li, W. Wang, S. Liu, C. Lin, J. Abuduwaili, Meta-XGBoost for Hyperspectral Image Classification Using Extended MSER-Guided Morphological Profiles, Remote Sensing, Vol. 12, No. 12, 2020, https://doi.org/10.3390/rs12121973.
[35] J. Bergstra, R. Bardenet, Y. Bengio, B. Kégl, Algorithms for Hyper-Parameter Optimization, Advances in Neural Information Processing Systems, Vol. 24, 2011.
[36] Z. Shao, M. N. Ahmad, A. Javed, Comparison of Random Forest and XGBoost Classifiers Using Integrated Optical and SAR Features for Mapping Urban Impervious Surface, Remote Sensing, Vol. 16, No. 4, 2024, https://doi.org/10.3390/rs16040665.
[37] Y. Liu, S. Zhang, J. Zhang, L. Tang, Y. Bai, Assessment and Comparison of Six Machine Learning Models in Estimating Evapotranspiration Over Croplands Using Remote Sensing and Meteorological Factors, Remote Sensing, Vol. 13, No. 19, 2021, https://doi.org/10.3390/rs13193838.
[38] E. K. Sahin, Assessing the Predictive Capability of Ensemble Tree Methods for Landslide Susceptibility Mapping Using XGBoost, Gradient Boosting Machine, and Random Forest, SN Applied Sciences, Vol. 2, 2020, pp. 1308, https://doi.org/10.1007/s42452-020-3060-1.
[2] F. Khormali, M. Ajami, S. Ayoubi, C. Srinivasarao, S. P. Wani, Role of Deforestation and Hillslope Position on Soil Quality Attributes of Loess-Derived Soils in Golestan Province, Iran, Agriculture, Ecosystems & Environment, Vol. 134, No. 3, 2009, pp. 178-189, https://doi.org/10.1016/j.agee.2009.06.017.
[3] B. Wicke et al., The Global Technical and Economic Potential of Bioenergy from Salt-Affected Soils, Energy and Environmental Science, Vol. 4, No. 8, 2011, pp. 2669-2681, https://doi.org/10.1039/C1EE01029H.
[4] T. Gorji, E. Sertel, A. Tanik, Monitoring Soil Salinity via Remote Sensing Technology Under Data Scarce Conditions: A Case Study From Turkey, Ecological Indicators, Vol. 74, 2017,
pp. 384-391, https://doi.org/10.1016/j.ecolind.2016.11.043.
[5] Ministry of Agriculture and Rural Development, Summary Report on Drought and Salinity Intrusion in the Southern Region 2019-2020, https://phongchongthientai.mard.gov.vn/Pages/bao-cao-tong-hop-tinh-hinh-han-han-xam-nhap-man-khu-vuc-mien-nam-2019--2020.aspx, 2020 (accessed on: April 09, 2026) (in Vietnamese).
[6] Ministry of Agriculture and Rural Development, Salinity Intrusion Causes Ben Tre to Lose Thousands of Billions of VND Every Year, https://phongchongthientai.mard.gov.vn/Pages/xam-nhap-man-khien-ben-tre-thiet-hai-hang-ngan-ti-dong-moi-nam.aspx, 2022 (accessed on: April 09, 2026) (in Vietnamese).
[7] T. Gorji, A. Tanik, E. Sertel, Soil Salinity Prediction, Monitoring and Mapping Using Modern Technologies, Procedia Earth and Planetary Science, Vol. 15, 2015, pp. 507-512, https://doi.org/10.1016/j.proeps.2015.08.062.
[8] V. L. Mulder, S. De Bruin, M. E. Schaepman, T. R. Mayr, The Use of Remote Sensing in Soil and Terrain Mapping - A Review, Geoderma, Vol. 162, No. 1, 2011, pp. 1-19, https://doi.org/10.1016/j.geoderma.2010.12.018.
[9] H. D. Nguyen, D. K. Dang, Q. T. Bui, Estuary Salinity Prediction Using Machine Learning: Case Study in the Hau Estuary in Mekong River, Vietnam, Water Supply, Vol. 25, No. 2, 2025, pp. 327-342, https://doi.org/10.2166/ws.2025.007.
[10] A. A. A. Aldabaa, D. C. Weindorf, S. Chakraborty, A. Sharma, B. Li, Combination of Proximal and Remote Sensing Methods for Rapid Soil Salinity Quantification, Geoderma, Vol. 239-240, 2015,
pp. 34-46, https://doi.org/10.1016/j.geoderma.2014.09.011.
[11] J. Ding, D. Yu, Monitoring and Evaluating Spatial Variability of Soil Salinity in Dry and Wet Seasons in the Werigan–Kuqa Oasis, China, Using Remote Sensing and Electromagnetic Induction Instruments, Geoderma, Vol. 235-236, 2014,
pp. 316-322, https://doi.org/10.1016/j.geoderma.2014.07.028.
[12] Y. Liu, et al., Estimating the Soil Salinity Over Partially Vegetated Surfaces From Multispectral Remote Sensing Image Using Non-Negative Matrix Factorization, Geoderma, Vol. 354, 2019, pp. 113887, https://doi.org/10.1016/j.geoderma.2019.113887.
[13] S. H. Yueh, R. Shah, M. J. Chaubell, A. Hayashi, X. Xu, A. Colliander, A Semiempirical Modeling of Soil Moisture, Vegetation, and Surface Roughness Impact on CYGNSS Reflectometry Data, IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, 2022, pp. 1-17, https://doi.org/10.1109/TGRS.2020.3035989.
[14] H. Kim, V. Lakshmi, Use of Cyclone Global Navigation Satellite System (CyGNSS) Observations for Estimation of Soil Moisture, Geophysical Research Letters, Vol. 45, No. 16, 2018, pp. 8272-8282, https://doi.org/10.1029/2018GL078923.
[15] J. Wang et al., A Novel Retrieval Model for Soil Salinity From CYGNSS: Algorithm and Test in the Yellow River Delta, Geoderma, Vol. 432, 2023, pp. 116417, https://doi.org/10.1016/j.geoderma.2023.116417.
[16] C. Chew, E. Small, Description of the UCAR/CU Soil Moisture Product, Remote Sensing, Vol. 12, No. 10, 2020, https://doi.org/10.3390/rs12101558.
[17] C. Chew, Soil Moisture Sensing Using Spaceborne GNSS Reflections: Comparison of CYGNSS Reflectivity to SMAP Soil Moisture, Geophysical Research Letters, 2018, https://doi.org/10.1029/2018GL077905.
[18] P. Ghasemigoudarzi, W. Huang, O. De Silva, Q. Yan, D. T. Power, Flash Flood Detection From CYGNSS Data Using the RUSBoost Algorithm, IEEE Access, Vol. 8, 2020, pp. 171864-171881, https://doi.org/10.1109/ACCESS.2020.3025302.
[19] W. Yang, F. Guo, X. Zhang, Y. Zhu, Z. Li, Z. Zhang, First Quasi-Global Soil Moisture Retrieval Using Fengyun-3 GNSS-R Constellation Observations, Remote Sensing of Environment, Vol. 321, 2025, pp. 114653, https://doi.org/10.1016/j.rse.2025.114653.
[20] Y. Zhu, F. Guo, X. Zhang, Spaceborne GNSS-R Soil Moisture Retrieval From GPS/BDS-3/Galileo Satellites, GPS Solutions, Vol. 29, No. 1, 2024, pp. 10, https://doi.org/10.1007/s10291-024-01767-8.
[21] T. T. Zhang, J. G. Qi, Y. Gao, Z. T. Ouyang, S. L. Zeng, B. Zhao, Detecting Soil Salinity With MODIS Time Series VI Data, Ecological Indicators, Vol. 52, 2015, pp. 480-489, https://doi.org/10.1016/j.ecolind.2015.01.004.
[22] L. Breiman, Random Forests, Machine Learning, Vol. 45, No. 1, 2001, pp. 5-32, https://doi.org/10.1023/A:1010933404324.
[23] T. Chen, C. Guestrin, XGBoost: A Scalable Tree Boosting System, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785-794, https://doi.org/10.1145/2939672.2939785.
[24] L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, A. Gulin, CatBoost: Unbiased Boosting With Categorical Features, Advances in Neural Information Processing Systems, Vol. 31, 2018.
https://doi.org/10.48550/arXiv.1706.09516.
[25] O. Eroglu, M. Kurum, D. Boyd, A. C. Gurbuz, High Spatio-Temporal Resolution CYGNSS Soil Moisture Estimates Using Artificial Neural Networks, Remote Sensing, Vol. 11, No. 19, 2019, https://doi.org/10.3390/rs11192272.
[26] E. Vermote, R. Wolfe, MOD09GQ MODIS/Terra Surface Reflectance Daily L2G Global 250m SIN Grid V006, NASA EOSDIS Land Processes Distributed Active Archive Center (DAAC) Data Set, 2015, pp. MOD09GQ.006, https://doi.org/10.5067/MODIS/MOD09GQ.006.
[27] H. D. Nguyen et al., Soil Salinity Prediction Using Hybrid Machine Learning and Remote Sensing in Ben Tre Province on Vietnam’s Mekong River Delta, Environmental Science and Pollution Research, Vol. 30, No. 29, 2023, pp. 74340-74357, https://doi.org/10.1007/s11356-023-27516-x.
[28] A. Calabia, I. Molina, S. Jin, Soil Moisture Content From GNSS Reflectometry Using Dielectric Permittivity From Fresnel Reflection Coefficients, Remote Sensing, Vol. 12, No. 1, 2020, https://doi.org/10.3390/rs12010122.
[29] Y. U. Haq, M. Shahbaz, S. Asif, K. Ouahada, H. Hamam, Identification of Soil Types and Salinity Using MODIS Terra Data and Machine Learning Techniques in Multiple Regions of Pakistan, Sensors, Vol. 23, No. 19, 2023, https://doi.org/10.3390/s23198121.
[30] J. Friedman, T. Hastie, R. Tibshirani, Additive Logistic Regression: A Statistical View of Boosting (With Discussion and a Rejoinder by the Authors), The Annals of Statistics, Vol. 28, No. 2, 2000, pp. 337-407, https://doi.org/10.1214/aos/1016218223.
[31] J. H. Friedman, Greedy Function Approximation: A Gradient Boosting Machine, The Annals of Statistics, Vol. 29, No. 5, 2001, pp. 1189-1232, https://doi.org/10.1214/aos/1013203451.
[32] A. Zarei, M. Hasanlou, M. Mahdianpari, A Comparison of Machine Learning Models for Soil Salinity Estimation Using Multi-Spectral Earth Observation Data, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. V-3, 2021, pp. 257-263, https://doi.org/10.5194/isprs-annals-V-3-2021-257-2021.
[33] S. Aksoy, E. Sertel, R. Roscher, A. Tanik, N. Hamzehpour, Assessment of Soil Salinity Using Explainable Machine Learning Methods and Landsat 8 Images, International Journal of Applied Earth Observation and Geoinformation, Vol. 130, 2024, pp. 103879, https://doi.org/10.1016/j.jag.2024.103879.
[34] A. Samat, E. Li, W. Wang, S. Liu, C. Lin, J. Abuduwaili, Meta-XGBoost for Hyperspectral Image Classification Using Extended MSER-Guided Morphological Profiles, Remote Sensing, Vol. 12, No. 12, 2020, https://doi.org/10.3390/rs12121973.
[35] J. Bergstra, R. Bardenet, Y. Bengio, B. Kégl, Algorithms for Hyper-Parameter Optimization, Advances in Neural Information Processing Systems, Vol. 24, 2011.
[36] Z. Shao, M. N. Ahmad, A. Javed, Comparison of Random Forest and XGBoost Classifiers Using Integrated Optical and SAR Features for Mapping Urban Impervious Surface, Remote Sensing, Vol. 16, No. 4, 2024, https://doi.org/10.3390/rs16040665.
[37] Y. Liu, S. Zhang, J. Zhang, L. Tang, Y. Bai, Assessment and Comparison of Six Machine Learning Models in Estimating Evapotranspiration Over Croplands Using Remote Sensing and Meteorological Factors, Remote Sensing, Vol. 13, No. 19, 2021, https://doi.org/10.3390/rs13193838.
[38] E. K. Sahin, Assessing the Predictive Capability of Ensemble Tree Methods for Landslide Susceptibility Mapping Using XGBoost, Gradient Boosting Machine, and Random Forest, SN Applied Sciences, Vol. 2, 2020, pp. 1308, https://doi.org/10.1007/s42452-020-3060-1.