Soil salinization in the Hetao Irrigation District of Inner Mongolia severely hampers the sustainable development of local agriculture. Accurately understanding the spatial distribution of soil salinity is crucial for improving agricultural productivity and protecting the ecological environment. This study utilized multi-source remote sensing data, including Sentinel-2 image-derived indices (salinity indices: S1, S2, S3, SAIO, CRSI, SI1, SI2, SI3, SI4, SI5, and SI_T; vegetation indices: SAVI, NDVI, RDVI, GNDVI, TVI, DVI, NDGI, and ENDVI), and SRTM topographic factors (Aspect, Elevation, LS_Factor, Roughness, TWI, Slope, TPI, SPI). It initially screened feature variables using Pearson correlation analysis and constructed three soil salinity inversion models: Random Forest (RF), Light Gradient Boosting Machine (LGBM), and Extreme Gradient Boosting (XGB). Furthermore, it applied the Shapley Additive Explanations (SHAP) method to elucidate the contributions and directions of feature variables on model predictions. The results indicate: ① Pearson correlation analysis shows that the top ten feature variables most strongly correlated with the target variables are Elevation, S1, S2, S3, DVI, SI_T, NDGI, CRSI, SAVI, and TVI; ② The XGB model performs the best in this study (training set R2: 0.724 9; validation set R2: 0.427 3), although further optimization is necessary to enhance its generalization ability; ③ Different models exhibit varying capacities for capturing feature variables, with the terrain factor Elevation being the most significant contributor to the RF and XGB models, while the salinity index CRSI is the most significant contributor to the LGBM model. This study provides theoretical support for monitoring soil salinization in the Hetao Irrigation District and offers important insights for the precise prevention and control of local soil salinization and ecological protection.
VAN ZELME, ZHANGY X, TESTERINKC. Salt tolerance mechanisms of plants[J]. Annual Review of Plant Biology,2020,71:403-433.
[2]
HASSANIA, AZAPAGICA, SHOKRIN. Global predictions of primary soil salinization under changing climate in the 21st century[J]. Nature Communications, 2021,12(1):6663.
KHASANOVS, LIF D, KULMATOVR, et al. Evaluation of the perennial spatio-temporal changes in the groundwater level and mineralization, and soil salinity in irrigated lands of arid zone: As an example of Syrdarya Province, Uzbekistan[J]. Agricultural Water Management,2022,263:107444.
[6]
MAH, ZHAOW J, DUANW C, et al. Inversion model of soil salinity in alfalfa covered farmland based on sensitive variable selection and machine learning algorithms[J]. PeerJ,2024,12:e18186.
[7]
HEY J, ZHANGZ T, XIANGR, et al. Monitoring salinity in bare soil based on Sentinel-1/2 image fusion and machine learning[J]. Infrared Physics & Technology,2023,131:104656.
[8]
ZHAOW J, MAH, ZHOUC, et al. Soil salinity inversion model based on BPNN optimization algorithm for UAV multispectral remote sensing[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2023,16:6038-6047.
SONGJ, YIY J. Cascaded machine learning of soil moisture and salinity prediction in estuarine wetlands based on in situ internet of things monitoring[J]. Water Resources Research,2025,61(4):e2024WR038271.
MANTENAS, MAHAMMOODV, RAOK N. Prediction of soil salinity in the Upputeru river estuary catchment, India, using machine learning techniques[J]. Environmental Monitoring and Assessment,2023,195(8):1006.
[14]
ZAREIA, HASANLOUM, MAHDIANPARIM. A comparison of machine learning models for soil salinity estimation using multi-spectral earth observation data[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences,2021,V-3-2021:257-263.
[15]
THANGARASUT, MENGASHH A, ALLAFIR, et al. Spatial prediction of soil salinity: Remote sensing and machine learning approach[J]. Journal of South American Earth Sciences,2025,156:105440.
[16]
JIAP P, ZHANGJ H, LIANGY N, et al. The inversion of arid-coastal cultivated soil salinity using explainable machine learning and Sentinel-2[J]. Ecological Indicators,2024,166:112364.
[17]
JIANGX F, DUANH C, LIAOJ, et al. Estimation of soil salinization by machine learning algorithms in different arid regions of northwest China[J]. Remote Sensing,2022,14(2):347.
[18]
AKSOYS, SERTELE, ROSCHERR, et al. Assessment of soil salinity using explainable machine learning methods and Landsat 8 images[J]. International Journal of Applied Earth Observation and Geoinformation,2024,130:103879.
YUEJ B, YANGG J, TIANQ J, et al. Estimate of winter-wheat above-ground biomass based on UAV ultrahigh-ground-resolution image textures and vegetation indices[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2019,150:226-244.
[25]
WANGN, XUEJ, PENGJ, et al. Integrating remote sensing and landscape characteristics to estimate soil salinity using machine learning methods: A case study from southern Xinjiang, China[J]. Remote Sensing, 2020,12(24):4118.
[26]
ELSHEWYM A, MOHAMEDM H A, REFAATM. Developing a soil salinity model from landsat 8 satellite bands based on advanced machine learning algorithms[J]. Journal of the Indian Society of Remote Sensing,2024,52(3):617-632.
ZHONGL, GUOX, DINGM, et al. SHAP values accurately explain the difference in modeling accuracy of convolution neural network between soil full-spectrum and feature-spectrum[J]. Computers and Electronics in Agriculture,2024,217:108627.
[29]
SAHBENIG, NGABIREM, MUSYIMIP K, et al. Challenges and opportunities in remote sensing for soil salinization mapping and monitoring: A review[J]. Remote Sensing,2023,15(10):2540.
[30]
MOHAMMEDS, ARSHADS, BASHIRB, et al. Evaluating machine learning performance in predicting sodium adsorption ratio for sustainable soil-water management in the eastern Mediterranean[J]. Journal of Environmental Management,2024,370:122640.
[31]
VABALASA, GOWENE, POLIAKOFFE, et al. Machine learning algorithm validation with a limited sample size[J]. Plos One,2019,14(11):e0224365.
[32]
RAJPUTD, WANGW J, CHENC C. Evaluation of a decided sample size in machine learning applications[J]. BMC Bioinformatics,2023,24(1):48.
[33]
ZHAOJ H, ZHANGC Y, MINL, et al. Retrieval of farmland surface soil moisture based on feature optimization and machine learning[J]. Remote Sensing,2022,14(20):5102.
[34]
MAH, ZHAOW J, DUANW C, et al. Inversion model of soil salinity in alfalfa covered farmland based on sensitive variable selection and machine learning algorithms[J]. PeerJ,2024,12:e18186.
YANGQ, FANX M, WANGL L, et al. Detection of soil salinity distribution and its change in the Yellow River Delta comparing 2006 and 2022[J]. Land Degradation & Development,2024,35(14):4288-4303.
[38]
NIES Y, BIANJ M, ZHOUY C. Estimating the spatial distribution of soil salinity with geographically weighted regression kriging and its relationship to groundwater in the western Jilin irrigation area, NorthEast China[J]. Polish Journal of Environmental Studies,2021,30(1):283-294.
[39]
WUW C, AL-SHAFIEW M, MHAIMEEDA S, et al. Soil salinity mapping by multiscale remote sensing in Mesopotamia, Iraq[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(11):4442-4452.
CHENX, YANGS Q, WENX Y, et al. Study on soil salinity inversion of different crop types based on multi-time series[J]. Plant and Soil,2025,514:1187-1203.
[42]
JEONGH, ABBASA, KIMH G, et al. Spatial prediction of groundwater salinity in multiple aquifers of the Mekong Delta region using explainable machine learning models[J]. Water Research,2024,266:122404.