Spatial prediction and mapping of soil salinity using machine learning and remote sensing covariates

Salinity is a serious threat to the crop production in the southern region of Bangladesh and it is especially important during dry period of a year. A study was undertaken to examine the changes in water and soil salinity over the period from February to April, 2014 at Kalapara upazila of Patuakhali district. Water samples were periodically collected from lake, pond, earthen well, deep tube-wells (5, 15 and 30 km away from the sea) and rivers (Tulatoli, Khaprabhanga, Sonatala and Andharmanik). Soil sampling was done from different crop fields (mustard, sweet gourd, potato, chilli, Khira-cucumber) and water melon and also from Sonatala and Andharmanik River flooded soils inside and outside polders. The electrical conductivity (EC) value of lake and pond waters was below 4 dS/m showing quite safe for irrigation while the EC value of earthen well exceeded 4 dS/m which are suitable in April. Water salinity of deep tube-wells (DTWs) increased as the DTW was closer to the sea, however all EC values were below 4 dS/m that suitable for irrigation, but not suitable for drinking purpose. Salinity level of all rivers tended to rise with the advancement of drying period, and for all dates of sampling, the EC value showed more than 4 dS/m. Soil salinity varied between inside and outside polder, and between mustard and sweet gourd fields, the higher EC values were observed outside polder and in the sweet gourd field. Soil EC levels were all above 4 dS/m particularly in April, crops showed varying degrees of leaf injury depending on the types of crops and extent of soil salinity. The EC values were positively correlated with Na and K contents of soil.DOI: http://dx.doi.org/10.3329/jesnr.v7i2.22218 J. Environ. Sci. & Natural Resources, 7(2): 111-114 2014

Assessing the performance of machine learning algorithms for soil salinity mapping in Google Earth Engine platform using Sentinel-2A and Landsat-8 OLI data

Soil salinization is a global issue resulting in soil degradation, arable land loss and ecological environmental deterioration. Over the decades, multispectral and hyperspectral remote sensing have enabled efficient and cost-effective monitoring of salt-affected soils. However, the potential of hyperspectral sensors installed on an unmanned aerial vehicle (UAV) to estimate and map soil salinity has not been thoroughly explored. This study quantitatively characterized and estimated field-scale soil salinity using an electromagnetic induction (EMI) equipment and a hyperspectral camera installed on a UAV platform. In addition, 30 soil samples (0~20 cm) were collected in each field for the lab measurements of electrical conductivity. First, the apparent electrical conductivity (ECa) values measured by EMI were calibrated using the lab measured electrical conductivity derived from soil samples based on empirical line method. Second, the soil salinity was quantitatively estimated using the random forest (RF) regression method based on the reflectance factors of UAV hyperspectral images and satellite multispectral data. The performance of models was assessed by Lin’s concordance coefficient (CC), ratio of performance to deviation (RPD), and root mean square error (RMSE). Finally, the soil salinity of three study fields with different land cover were mapped. The results showed that bare land (field A) exhibited the most severe salinity, followed by dense vegetation area (field C) and sparse vegetation area (field B). The predictive models using UAV data outperformed those derived from GF-2 data with lower RMSE, higher CC and RPD values, and the most accurate UAV-derived model was developed using 62 hyperspectral bands of the image of the field A with the RMSE, CC, and RPD values of 1.40 dS m−1, 0.94, and 2.98, respectively. Our results indicated that UAV-borne hyperspectral imager is a useful tool for field-scale soil salinity monitoring and mapping. With the help of the EMI technique, quantitative estimation of surface soil salinity is critical to decision-making in arid land management and saline soil reclamation.

The precision of estimating soil salinity is considered a key task in solving soil salinity problems and irrigation management of agriculture. This problem is increasingly important in the Mekong Delta, where it is severely affected by this phenomenon in the context of climate variability. Therefore, this paper aims to construct a soil salinity map with high accuracy using machine learning and Sentinel 2A, namely Xgboost (XGB) and Random Forest (RF). The province of Tra Vinh in the Mekong Delta has been selected as the case study. 68 soil salinity samples were collected in August 2024, and 25 conditioning factors extracted from the Sentinel 2A image were used as input data for the machine-learning model. Three statistical indices, namely root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2), were used to evaluate the effectiveness of machine learning models. The results showed that with an R2 value of 0.86, the XGB model was superior to the RF model with an R2 value of 0.67. Furthermore, Tra Vinh province, the coastal region, and along the Mekong River are more severely affected by soil salinity with an electrical conductivity (EC) value of more than 10. This region, more affected by soil salinity, is related to rising tides and sea levels in the context of climate variability. This study plays an important role and can support farmers in regions affected by soil salinity in building investment measures to reduce the impacts of soil salinity on the development of agriculture.

In response to the global ecological and agricultural challenges posed by coastal saline-alkali areas, this study focuses on Dongying City as a representative region, aiming to develop a high-precision soil salinity prediction mapping method that integrates multi-source remote sensing data with machine learning techniques. Utilizing the SCORPAN model framework, we systematically combined diverse remote sensing datasets and innovatively established nine distinct strategies for soil salinity prediction. We employed four machine learning models—Support Vector Regression (SVR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Geographical Gaussian Process Regression (GGPR) for modeling, prediction, and accuracy comparison, with the objective of achieving high-precision salinity mapping under complex vegetation cover conditions. The results reveal that among the models evaluated across the nine strategies, the SVR model demonstrated the highest accuracy, followed by RF. Notably, under Strategy IX, the SVR model achieved the best predictive performance, with a coefficient of determination (R2) of 0.62 and a root mean square error (RMSE) of 0.38 g/kg. Analysis based on SHapley Additive exPlanations (SHAP) values and feature importance indicated that Vegetation Type Factors contributed significantly and consistently to the model’s performance, maintaining higher importance than traditional salinity indices and playing a dominant role. In summary, this research successfully developed a comprehensive, high-resolution soil salinity mapping framework for the Dongying region by integrating multi-source remote sensing data and employing diverse predictive strategies alongside machine learning models. The findings highlight the potential of Vegetation Type Factors to enhance large-scale soil salinity monitoring, providing robust scientific evidence and technical support for sustainable land resource management, agricultural optimization, ecological protection, efficient water resource utilization, and policy formulation.

Soil salinization is one of the most active land degradation processes, affecting predominantly arid, semi-arid, and dry sub-humid regions and leading to decreased agricultural yields. The Indo-Gangetic plain, which includes the irrigated command areas with arid and semi-arid climatic conditions are severely affected by secondary soil salinization. Assessing the spatial and temporal extent as well as the severity of salinization is an important step for adoption of proper reclamation measures to boost agricultural productivity in the salt affected areas. The study was conducted with this background to evaluate the extent and severity of soil salinization in alluvial plains of Mathura district of Uttar Pradesh, India. In this study, the satellite data of 6 months from January 2019 to June 2019 were pre-processed and various spectral indices were generated in Google Earth Engine. Remote sensing techniques provides an ideal platform for addressing this problem at larger scales and thus we employed Sentinel-2 derived vegetation and salinity spectral indices for distinguishing temporal change in severity of soil salinization and map the salinity as a function of these indices for the entire study area. The time series salinity analysis showed that among the various spectral indices Ratio Vegetation Index (RVI), Normalized Difference Vegetation Index (NDVI) and Normalized Difference Soil Index (NDSI) had a clear differentiation between slight, moderate and severe salinity class in the first three months of the study period and the Salinity Index II (SI_II) could differentiate for the first four months. Further, two machine learning algorithms namely Random Forest (RF) and Support Vector Machine (SVM), were used to create soil salinity prediction models making use of the soil Electrical Conductivity (EC) values of 115 ground-sampling sites as the predictand variable and the optimal spectral indices as the predictor variables. Further, we evaluated the prediction ability of different models using 12 and 24 variables combination using R2 and RMSE values. The prediction accuracy of the RF model was found to be slightly higher than that of the SVM model, and the spatial distribution pattern of soil salinity predicted by the two models were comparable. We concluded that spectral indices combined with machine learning techniques have the potential for low cost reliable spatial and temporal soil salinity distribution mapping for planning and implementation of salinity reclamation measures.

Accurate monitoring of soil salinization plays a key role in the ecological security and sustainable agricultural development of arid regions. As a branch of artificial intelligence, machine learning acquires new knowledge through self-learning and continuously improves its own performance. The purpose of this study is to combine Sentinel-2 Multispectral Imager (MSI) data and MSI-derived covariates with measured soil salinity data and to apply three machine learning algorithms in modeling to estimate and map the soil salinity in the study sample area. According to the convenient transportation conditions, the study area and sampling quadrat were set up, and the 5-point method was used to collect the soil mixed samples, and 160 soil mixed samples were collected. Kennard–Stone (K–S) algorithm was used for sample classification, 70% for modeling and 30% for verification. The machine learning algorithm uses Support Vector Machines (SVM), Artificial Neural Network (ANN), and Random Forest (RF). The results showed that (1) the average reflectance of each band of the MSI data ranged from 0.21–0.28. According to the spectral characteristics corresponding to different soil electrical conductivity (EC) levels (1.07–79.6 dS m−1), the spectral reflectance of salinized soil in the MSI data ranged from 0.09–0.35. (2) The correlation coefficient between the MSI data and MSI-derived covariates and soil EC was moderate, and the correlation between certain MSI data sets and soil EC was not significant. (3) The SVM soil EC estimation model established with the MSI data set attained a higher performance and accuracy (R2 = 0.88, root mean square error (RMSE) = 4.89 dS m−1, and ratio of the performance to the interquartile range (RPIQ) = 1.96, standard error of the laboratory measurements to the standard error of the predictions (SEL/SEP) = 1.11) than those attained with the soil EC estimation models established with the RF and ANN models. (4) We applied the SVM soil EC estimation model to map the soil salinity in the study area, which showed that the farmland with higher altitudes discharged a large amount of salt to the surroundings due to long-term irrigation, and the secondary salinization of the farmland also caused a large amount of salt accumulation. This research provides a scientific basis for the simulation of soil salinization scenarios in arid areas in the future.

Soil salinization is considered one of the disasters that have significant effects on agricultural activities in many parts of the world, particularly in the context of climate change and sea level rise. This problem has become increasingly essential and severe in the Mekong River Delta of Vietnam. Therefore, soil salinity monitoring and assessment are critical to building appropriate strategies to develop agricultural activities. This study aims to develop a low-cost method based on machine learning and remote sensing to map soil salinity in Ben Tre province, which is located in Vietnam's Mekong River Delta. This objective was achieved by using six machine learning algorithms, including Xgboost (XGR), sparrow search algorithm (SSA), bird swarm algorithm (BSA), moth search algorithm (MSA), Harris hawk optimization (HHO), grasshopper optimization algorithm (GOA), particle swarm optimization algorithm (PSO), and 43 factors extracted from remote sensing images. Various indices were used, namely, root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R2) to estimate the efficiency of the prediction models. The results show that six optimization algorithms successfully improved XGR model performance with an R2 value of more than 0.98. Among the proposed models, the XGR-HHO model was better than the other models with a value of R2 of 0.99 and a value of RMSE of 0.051, by XGR-GOA (R2 = 0.931, RMSE = 0.055), XGR-MSA (R2 = 0.928, RMSE = 0.06), XGR-BSA (R2 = 0.926, RMSE = 0.062), XGR-SSA (R2 = 0.917, 0.07), XGR-PSO (R2 = 0.916, RMSE = 0.08), XGR (R2 = 0.867, RMSE = 0.1), CatBoost (R2 = 0.78, RMSE = 0.12), and RF (R2 = 0.75, RMSE = 0.19), respectively. These proposed models have surpassed the reference models (CatBoost and random forest). The results indicated that the soils in the eastern areas of Ben Tre province are more saline than in the western areas. The results of this study highlighted the effectiveness of using hybrid machine learning and remote sensing in soil salinity monitoring. The finding of this study provides essential tools to support farmers and policymakers in selecting appropriate crop types in the context of climate change to ensure food security.

In arid and semi-arid regions, soil moisture and salinity are important elements to control regional ecology and climate, vegetation growth and land function. Soil moisture and salt content are more important in arid wetlands. The Ebinur Lake wetland is an important part of the ecological barrier of Junggar Basin in Xinjiang, China. The Ebinur Lake Basin is a representative area of the arid climate and ecological degradation in central Asia. It is of great significance to study the spatial distribution of soil moisture and salinity and its causes for land and wetland ecological restoration in the Ebinur Lake Basin. Based on the field measurement and Landsat 8 satellite data, a variety of remote sensing indexes related to soil moisture and salinity were tested and compared, and the prediction models of soil moisture and salinity were established, and the accuracy of the models was assessed. Among them, the salinity indexes D1 and D2 were the latest ones that we proposed according to the research area and data. The distribution maps of soil moisture and salinity in the Ebinur Lake Basin were retrieved from remote sensing data, and the correlation analysis between soil moisture and salinity was performed. Among several soil moisture and salinity prediction indexes, the normalized moisture index NDWI had the highest correlation with soil moisture, and the salinity index D2 had the highest correlation with soil salinity, reaching 0.600 and 0.637, respectively. The accuracy of the BP neural network model for estimating soil salinity was higher than the one of other models; R2 = 0.624, RMSE = 0.083 S/m. The effect of the cubic function prediction model for estimating soil moisture was also higher than that of the BP neural network, support vector machine and other models; R2 = 0.538, RMSE = 0.230. The regularity of soil moisture and salinity changes seemed to be consistent, the correlation degree was 0.817, and the synchronous change degree was higher. The soil salinity in the Ebinur Lake Basin was generally low in the surrounding area, high in the middle area, high in the lake area and low in the vegetation coverage area. The soil moisture in the Ebinur Lake Basin slightly decreased outward with the Ebinur Lake as the center and was higher in the west and lower in the east. However, the spatial distribution of soil moisture had a higher mutation rate and stronger heterogeneity than that of soil salinity.

Digital mapping of soil salinization based on Sentinel-1 and Sentinel-2 data combined with machine learning algorithms

Assessment of the spatial variability of apparent electrical conductivity in a tile drained catchment in Fensholt subcatchment, Jutland, Denmark for improved small-scale prediction of highly reducing areas

Soil salinity analysis of Urmia Lake Basin using Landsat-8 OLI and Sentinel-2A based spectral indices and electrical conductivity measurements

Prediction of soil salinity parameters using machine learning models in an arid region of northwest China

Updated soil salinity with fine spatial resolution and high accuracy: The synergy of Sentinel-2 MSI, environmental covariates and hybrid machine learning approaches

Soil, a significant natural resource, plays a crucial role in supporting various ecosystems and serves as the foundation of Pakistan’s economy due to its primary use in agriculture. Hence, timely monitoring of soil type and salinity is essential. However, traditional methods for identifying soil types and detecting salinity are time-consuming, requiring expert intervention and extensive laboratory experiments. The objective of this study is to propose a model that leverages MODIS Terra data to identify soil types and detect soil salinity. To achieve this, 195 soil samples were collected from Lahore, Kot Addu, and Kohat, dating from October 2022 to November 2022. Simultaneously, spectral data of the same regions were obtained to spatially map soil types and salinity of bare land. The spectral reflectance of band values, salinity indices, and vegetation indices were utilized to classify the soil types and predict soil salinity. To perform the classification and regression tasks, the study employed three popular techniques in the research community: Random Forest (RF), Ada Boost (AB), and Gradient Boosting (GB), along with Decision Tree (DT), K-Nearest Neighbor (KNN), and Extra Tree (ET). A 70–30 test train validation split was used for the implementation of these techniques. The efficacy of the multi-class classification models for soil types was evaluated using accuracy, precision, recall, and f1-score. On the other hand, the regression models’ performances were evaluated and compared using R-squared (R), Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). The results demonstrated that Random Forest outperformed other methods for both predicting soil types (accuracy = 65.38, precision = 0.60, recall = 0.57, and f1-score = 0.57) and predicting salinity (R = 0.90, MAE = 0.56, MSE = 0.98, RMSE = 0.97). Finally, the study designed a web portal to enable real-time prediction of soil types and salinity using these models. This web portal can be utilized by farmers and decision-makers to make informed decisions regarding soil, crop cultivation, and agricultural planning.