Soil Salinity Mapping Research Articles

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

• Earth Engine platform facilitated the analysis of multi-sensor data for soil salinity mapping. • Landsat- 8 and Sentinel-2A derived soil salinity maps were compared. • Machine learning regression methods provided good results to map soil salinity. Soil salinization caused by natural and anthropogenic factors is an important environmental hazard especially in arid and semi-arid regions of the world. Accumulation of salts in the soil is a major threat to crop production and global agriculture; therefore, rapid and precise detection of salt-affected lands is highly critical for preserving soil sustainability and supporting food production. Advancement in remote sensing techniques and machine-learning algorithms has started to contribute to fast and large-scale monitoring and mapping of soil salinization throughout the world. This paper aims to analyze the performance of three different machine-learning algorithms to map soil salinity using Landsat-8 OLI, Sentinel-2A satellite images, and ground-based electrical conductivity (EC) measurements with the aid of Google Earth Engine (GEE) platform. Classification and regression trees (CART), random forest (RF), and support vector regression (SVR) methods are implemented to create a correlation between ground measurements and satellite-derived environmental variables or spectral indices. After selecting the optimum five variables including wetness band, three soil salinity indices, and one vegetation index, soil salinity maps are generated in three machine-learning algorithms. The output soil salinity map in RF algorithm demonstrated the most reliable spatial distribution of various soil salinity classes in the selected study area. Despite CART provided slightly better prediction of soil salinity with R-squared (R 2 ) of 0.98 for Sentinel-2A data, and 0.96 for Landsat-8 OLI data in comparison with accuracy results of RF technique with R 2 of 0.96 for Sentinel-2A data and 0.94 for Landsat-8 OLI data, the output map of RF model estimated more reliable salinity levels in salt crusts, agricultural lands, drainage areas, and swamps. The corresponding result highly matched with visual interpretation. Soil salinity maps derived from SVR algorithms by using various combinations of input variables displayed relatively poor estimation of soil EC values compared to the other two methods.

Soil Salinity Mapping with Landsat 8 Oli Imagery and Random Forest Algorithm

Soil Salinity Mapping with Landsat 8 Oli Imagery and Random Forest Algorithm

Landscape-Scale Mapping of Soil Salinity With Multi-Height Electromagnetic Induction and Quasi-3D Inversion in Saharan Oasis, Tunisia

Landscape-Scale Mapping of Soil Salinity With Multi-Height Electromagnetic Induction and Quasi-3D Inversion in Saharan Oasis, Tunisia

Mapping Spatial Management Zones of Salt-Affected Soils in Arid Region: A Case Study in the East of the Nile Delta, Egypt

Soil salinization is a global problem that affects a large part of the world, especially arid and semi-arid regions. Hence, diagnosing soil salinity is the first step towards appropriate management. The current work aims to assess and map soil salinity in the eastern Nile Delta using principal component analysis (PCA). In order to develop appropriate solutions for rational management to mitigate the impacts of soil salinization and increase yield production 34 soil profiles were dug that covered the variation in the soils located at the northeast of the Nile delta. The spatial variation of soil parameters was mapped using ordinary kriging interpolation. The results of PCA illustrated that, among the studied soil properties, soil electrical conductivity (ECe), sodium adsorption ratio (SAR), exchangeable sodium percent (ESP), and bulk density (BD), are the critical factors affecting management practices in the Nile Delta. Two spatial management zones (SMZ) were identified; SMZ 1 occupied 45.04% of the study area and SMZ2 occupied 54.96% of the study area. The average of soil pH, ECe, SAR, CEC, ESP and BD were 8.31, 20.32 dSm−1, 47.19, 32.9 cmolckg−1, 32.85% and 1.47 Mgm−3 for the first cluster (SMZ1), respectively. In addition, the second cluster (SMZ2) had average soil pH, ECe, SAR, CEC, ESP and BD of 7.75, 12.30 dSm−1, 26.6, 25.23 cmolckg−1, 26.6% and 1.27 Mgm−3. The results showed p-value < 0.05 which confirms that there is a significant statistical difference between the two zones. Finally, the results obtained could be used as a fundamental basis for improving agricultural management practices in such salt-affected soils.

Digital soil mapping of soil salinity using EM38 and quasi‐3d modelling software (EM4Soil)

AbstractLand development in the form of irrigation has led to increased agricultural productivity, but natural stores of connate salt have led to salinization. To manage salinity, baseline information about the electrical conductivity of a saturated soil paste extract (ECe – dS/m) is necessary. To value add to the limited ECe that can be collected, proximal sensed data from electromagnetic (EM) induction instruments (e.g. EM38) are increasingly being used because the measured apparent soil electrical conductivity (ECa – mS/m) can be correlated with measured topsoil (0–0.3 m), subsurface (0.3–0.6 m), subsoil (0.6–0.9 m) and deep subsoil (0.9–1.2 m) ECe. However, errors may be introduced in prediction, given an EM38 measures ECa at depths of 0–1.5 m in vertical (EM38v) and 0–0.75 m in horizontal (EM38h) mode. To overcome this, we develop a linear regression (LR) between estimates of electrical conductivity (σ – mS/m), inverted from EM38v and EM38h using a quasi‐3d algorithm and measured ECe at the same depths. First, the LR was established (using R2) between estimates of σ inverted from ECa at heights of 0.5 (EM38v0.5 and EM38h0.5) and 0 m (EM38v0 and EM38h0), either alone or in combination, as well as in vertical mode (i.e. EM38v0.5 and EM38v0). ECa were also degraded (100%, 80%, 60% and 40%) to compare loss of prediction agreement (Lin's concordance) and accuracy (root mean square error). We use Normalized Difference Vegetation Index (NDVI) to qualitatively indicate crop growth. Moderate coefficient of determination (R2) was achieved between σ and ECe when we use the EM38v0.5 and EM38h0.5 (0.65) and EM38v0.5 and EM38v0 (0.69), but strong R2 was achieved using EM38v0 and EM38h0 (0.78) and in combination with the EM38v0.5 and EM38h0.5 (0.71). However, while good agreement (Lin's > 0.8) was achieved, during a leave‐one‐out cross‐validation for most EM38 combinations, the best result was achieved using EM38v0 and EM38h0 (Lin's = 0.87). There was also loss in prediction agreement and accuracy using any of the degraded ECa data sets, however. The final 3d map of ECe, as well as NDVI, showed where highly saline (>8 dS/m) areas in the west of most fields resulted as a function of leakage from the Kham‐rean Canal and topography (i.e. lower lying areas). We conclude the approach has broad application to map, potentially manage and monitor large areas of north‐east Thailand.

Upgrading the Salinity Index Estimation and Mapping Quality of Soil Salinity Using Artificial Neural Networks in the Lower-Cheliff Plain of Algeria in North Africa

Since decades ago, the Lower Cheliff plain is under the continuous influence of soil salinization induced by mismanagement of the groundwater resources. The main purpose of this study was to estimate and map soil salinity using both Salinity Index (SI) and Artificial Neural Networks (ANN). In doing so, a total of 796 soil samples of Electrical Conductivity (EC, dS.m–1) measured in laboratory combined to spectral parameters data of Landsat-8 OLI, by applying a Salinity Index (SI) and used also to training the ANN model (80% of total data), the rest of the dataset (20%) was retained for validation with both methods. The results of applying an ANN estimator based on the reflectance values of three bands: green (B3), red (B4) and near-infrared (B5) as learning input neurons, proved their interest in the estimation of EC given a high determination coefficient (R2 = 0.80) between the values of simulated truth and ground, compared to the results obtained using only the SI method giving a moderate precision (R2 = 0.42). Regarding the soil salinity mapping, the two methods generated contrasting results, the SI estimates that 68.5% of the total area is affected by salinity (underestimation) meanwhile the ANN gave an estimation of 78.8%. In a conclusion, the estimation and mapping of soil salinity using the SI method has been upgraded significantly when ANN was involved.

Soil salinity mapping using remote sensing and GIS

The monitoring of soil salinity plays a vital role in agricultural society. Soil salinity causes land degradation processes, especially in arid and semi-arid regions, which influence soil properties, reduce yield production of crops, and affect infrastructure. This research produces soil salinity mapping of the East Delta in Egypt in 1995 using remote sensing technology. A Landsat 5 image taken on 26 September 1995 was used. Radiometric and atmospheric corrections for satellite data were applied. Different salinity indices (SIs) were used, such as the normalized difference salinity index, SI1, SI2, SI3, SI4, SI5, SI6, and SI7, in addition to the normalized difference vegetation index, which was used for data filtration. The field’s electrical conductivity was measured during the period from 22 to 26 September 1995 by the Japanese International Cooperation Agency. These data were used as ground truth for the correlation analysis with different indices image bands values. Simple linear regression and mean relative error were used to find the best index, which was SI5 with a 0.87 correlation with field truth data and mean relative error equal 22.7%. This index was used to produce a salinity map of the Eastern Delta with acceptable accuracy. Finally, it is concluded that using remote sensing in salinity detection and mapping is highly appreciated.

Digital Mapping of Surface Soil Salinity in Khuzestan Province, Using Regression Kriging

Digital Mapping of Surface Soil Salinity in Khuzestan Province, Using Regression Kriging

Ground Observations and Environmental Covariates Integration for Mapping of Soil Salinity: A Machine Learning-Based Approach

Soil salinization is a severe danger to agricultural activity in arid and semi-arid areas, reducing crop production and contributing to land destruction. This investigation aimed to utilize machine learning algorithms to predict spatial soil salinity (dS m−1) by combining environmental covariates derived from remotely sensed (RS) data, a digital elevation model (DEM), and proximal sensing (PS). The study is located in an arid region, southern Iran (52°51′–53°02′E; 28°16′–28°29′N), in which we collected 300 surface soil samples and acquired the spectral data with RS (Sentinel-2) and PS (electromagnetic induction instrument (EMI) and portable X-ray fluorescence (pXRF)). Afterward, we analyzed the data using five machine learning methods as follows: random forest—RF, k-nearest neighbors—kNN, support vector machines—SVM, partial least squares regression—PLSR, artificial neural networks—ANN, and the ensemble of individual models. To estimate the electrical conductivity of the saturated paste extract (ECe), we built three scenarios, including Scenario (1): Synthetic Soil Image (SySI) bands and salinity indices derived from it; Scenario (2): RS data, PS data, topographic attributes, and geology and geomorphology maps; and Scenario (3): the combination of Scenarios (1) and (2). The best prediction accuracy was obtained for the RF model in Scenario (3) (R2 = 0.48 and RMSE = 2.49), followed by Scenario (2) (RF model, R2 = 0.47 and RMSE = 2.50) and Scenario (1) for the SVM model (R2 = 0.26 and RMSE = 2.97). According to ensemble modeling, a combined strategy with the five models exceeded the performance of all the single ones and predicted soil salinity in all scenarios. The results revealed that the ensemble modeling method had higher reliability and more accurate predictive soil salinity than the individual approach. Relative improvement (RI%) showed that the R2 index in the ensemble model improved compared to the most precise prediction for the Scenarios (1), (2), and (3) with 120.95%, 56.82%, and 66.71%, respectively. We applied the best model in each scenario for mapping the soil salinity in the selected area, which indicated that ECe tended to increase from the northwestern to south and southeastern regions. The area with high ECe was located in the regions that mainly had low elevations and playa. The areas with low ECe were located in the higher elevations with steeper slopes and alluvial fans, and thus, relief had great importance. This study provides a precise, cost-effective, and scientific base prediction for decision-making purposes to map soil salinity in arid regions.

Monitoring soil salinization and its spatiotemporal variation at different depths across the Yellow River Delta based on remote sensing data with multi-parameter optimization.

Soil salinization is recognized as a key issue negatively affecting agricultural productivity and wetland ecology. It is necessary to develop effective methods for monitoring the spatiotemporal distribution of soil salinity at a regional scale. In this study, we proposed an optimized remote sensing-based model for detecting soil salinity in different depths across the Yellow River Delta (YRD), China. A multi-dimensional model was built for mapping soil salinity, in which five types of predictive factors derived from Landsat satellite images were exacted and tested, 94 in-situ measured soil salinity samples with depths of 30-40cm and 90-100cm were collected to establish and validate the predicting model result. By comparing multiple linear regression (MLR) and partial least squares regression (PLSR) models with considering the correlation between predictive factors and soil salinity, we established the optimized prediction model which integrated the multi-parameter (including SWIR1, SI9, MSAVI, Albedo, and SDI) optimization approach to detect soil salinization in the YRD from 2003 to 2018. The results indicated that the estimates of soil salinity by the optimized prediction model were in good agreement with the measured soil salinity. The accuracy of the PLSR model performed better than that of the MLR model, with the R2 of 0.642, RMSE of 0.283, and MAE of 0.213 at 30-40cm depth, and with the R2 of 0.450, RMSE of 0.276, and MAE of 0.220 at 90-100cm depth. From 2003 to 2018, the soil salinity showed a distinct spatial heterogeneity. The soil salinization level of the coastal shoreline was higher; in contrast, lower soil salinization level occurred in the central YRD. In the last 15years, the soil salinity at depth of 30-40cm experienced a decreased trend of fluctuating, while the soil salinity at depth of 90-100cm showed fluctuating increasing trend.

Potential of Landsat 8 OLI for mapping and monitoring of soil salinity in an arid region: A case study in Dushak, Turkmenistan.

Soil salinity is the most common land degradation agent that impairs soil functions, ecosystem services and negatively affects agricultural production in arid and semi-arid regions of the world. Therefore, reliable methods are needed to estimate spatial distribution of soil salinity for the management, remediation, monitoring and utilization of saline soils. This study investigated the potential of Landsat 8 OLI satellite data and vegetation, soil salinity and moisture indices in estimating surface salinity of 1014.6 ha agricultural land located in Dushak, Turkmenistan. Linear regression model was developed between land measurements and remotely sensed indicators. A systematic regular grid-sampling method was used to collect 50 soil samples from 0–20 cm depth. Sixteen indices were extracted from Landsat-8 OLI satellite images. Simple and multivariate regression models were developed between the measured electrical conductivity values and the remotely sensed indicators. The highest correlation between remote sensing indicators and soil EC values in determining soil salinity was calculated in SAVI index (r = 0.54). The reliability indicated by R2 value (0.29) of regression model developed with the SAVI index was low. Therefore, new model was developed by selecting the indicators that can be included in the multiple regression model from the remote sensing indicators. A significant (r = 0.74) correlation was obtained between the multivariate regression model and soil EC values, and salinity was successfully mapped at a moderate level (R2: 0.55). The classification of the salinity map showed that 21.71% of the field was non-saline, 29.78% slightly saline, 31.40% moderately saline, 15.25% strongly saline and 1.44% very strongly. The results revealed that multivariate regression models with the help of Landsat 8 OLI satellite images and indices obtained from the images can be used for modeling and mapping soil salinity of small-scale lands.

Spatio-temporal mapping and analysis of soil salinity: an integrated approach through electromagnetic induction (EMI), multivariate and geostatistical techniques

The information on salt load in soil is needed to enable suitable soil, crop and water management practices for crop production in salt affected land. An investigation was conducted to test the hypothesis that an integrated approach of electromagnetic induction (EMI), multivariate and geostatistical techniques can provide rapid and reliable information on soil salinity (ECe) at spatio-temporal scale. EMI survey and the analyzed data indicated that ECe better correlates with horizontal mode (EMH) of apparent soil electrical conductivity (R 2=0.83) than the vertical (EMV). Principal component (PCA) and Pearson correlation analysis revealed that Na+1, Ca2++Mg2+ and Cl−1 are the major soil chemical properties affecting apparent soil electrical conductivity. The spatial map of soil salinity based on EMH showed close proximity with the area represented by ECe observations. Study indicated that EMI methodology can be effectively used to predict, map and identify salinity zones for devising strategies for reclamation of saline soils.

Soil Moisture and Salinity Inversion Based on New Remote Sensing Index and Neural Network at a Salina-Alkaline Wetland

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.

Mapping the pH and Salinity Values for Paddy Field Area in East Coast Malaysia using Kriging Interpolation Technique

In paddy farming, the condition of soil is one of the important factors to promote a healthy growing plant. Certain pH and salinity levels are required in order to have soil condition which suits the microorganism life and promotes nutrient opportunity to the plant. Currently, the method used to identify the pH and salinity levels of the soil is by embedding a sensor on the soil which requires cost and time. Furthermore, it will only show the pH and salinity values at only one point and there are limitations if the area of interest is difficult to be accessed. In this research, a method was studied by using Kriging interpolation technique to map soil salinity and pH near Kelantan and Terengganu paddy cultivation area. Ground truth data were pre-processed to generate an image model mapping which consists of acidity, neutral, alkalinity and level of salinity at coordinates of interest using ArcGIS Pro software. As a result, the estimated pH and salinity value range were between 3.9 to 5.9 and 0.48 to 0.71 ds m-1 respectively. To test the accuracy of the model, analysis of RMSE was done for pH (0.854) and salinity (0.057). This research shall contribute as a preliminary study to model the soil pH and salinity values for monitoring purpose and as an aid to the farmers.

Digital Modeling of Three-Dimensional Soil Salinity Variation Using Machine Learning Algorithms in Arid and Semi-Arid lands of Qazvin Plain

Soil salinity, as one of the most important indicators of soil quality, has crucial roles in land use planning and land management in arid and semi-arid regions. The aim of this study was to model soil salinity at five standard depth (0-5, 5-15, 15-30, 30-60, and 60-100 cm) of global digital soil mapping project in 60,000 hectares of Qazvin plain with spatial resolution of 15m. Field studies included a sampling of 278 soil profiles and then the EC was measured in the laboratory. The recursive feature elimination (RFE) method was employed to select environmental covariates including parameters extracted from Landsat 8 image (OLI/TIRS) data, topography, and climatic parameters. Four machine learning algorithms as random forest (RF), cubist (CB), decision tree regression (DTr), and k-nearest neighbors (k-NN) were applied for predicting and mapping soil salinity. According to RFE, 10 covariates were chosen for each standardized depth. The results of modeling showed that the CB model at the depth of 0-5 and 15-30 cm with R2 values of 0.92 and 0.85 and RMSE 4.77 and 7.90 dS/m and the RF model at depths of 5-15, 30-60, and 60-100 cm with R2 values of 0.93, 0.94, 0.96 and RMSE 6.65, 5.10 and 3.20 dS/m, respectively, had the highest accuracy compared to two other models i.e., DTr and k-NN. Furthermore, the covariates extracted from RS data had more impact on topsoil salinity prediction while the climate and topographic attributes influence subsurface soil salinity. Generally, The RF and CB models along with appropriate environmental covariates were able to present salinity variation of study standard depths.

Combining laboratory measurements and proximal soil sensing data in digital soil mapping approaches

Digital soil mapping (DSM) products are limited in accuracy because of the lack of soil inputs. Soil sensing is a promising alternative to direct soil measurements that could provide much denser spatial samplings. Although using relevant and detailed soil sensing input in DSM is considered as vital to increase the prediction performances, there has been no studies in the literature that compare and develop the methods for integrating new sources of soil data that can be applied as inputs of DSM. This paper fills this gap on the example of mapping electrical conductivities from sites with laboratory measurements, in-field EM38MK2 measurements and spatially exhaustive covariates. Three different approaches are tested for putting in synergy real measurements and EM38MK2 measurements: (i) EM38MK2 measurement considered as measured points, (ii) EM38MK2 measurement used for building a new soil covariate and (iii) EM38MK2 measurement considered as a soft data in a regression co-kriging approach. According to soil analysis's financial expenditure, choosing an optimal sample size to merge laboratory analysis and in-field EM38MK2 measurements as surrogate data was done on the best method. The results showed (i) the utility of EM38MK2 data in DSM as a surrogate input data for mapping soil salinity (ii) Regression co-kriging was the best method for integration and (iii) The impact of EM38MK2 data on the gains of performance becomes greater and greater as the sizes of real measurements of soil salinity decrease. Hence, in other areas worldwide that soil sensing as alternative data is accessible, this research's future utilization could be possible as a promising way to tackle one of the essential constraints of DSM.

Sentinel-2 Images for Effective Mapping of Soil Salinity in Agricultural Fields

Salinity is a critical feature for the management of agricultural soil, particularly in arid and semi-arid areas. The present study was conducted to develop an effective soil salinity prediction model using Sentinel-2A (S2) satellite data. Initially, the collected soil samples were analysed for soil salinity (EC e ). Subsequently, multiple linear regression analysis was carried out between the obtained EC e values and S2 data, for the prediction of soil salinity models. The relationship between EC e and S2 data, including individual bands, band ratios and spectral indices showed moderate to highly significant correlations (R 2 = 0.43–0.83). A combination of SWIR-1 band and the simplified brightness index was found to be the most appropriate (R 2 = 0.65; P < 0.001) for prediction of soil salinity. The results of this study demonstrate the ability to obtain reliable estimates of EC using S2 data.

Remote sensing-based assessment of waterlogging and soil salinity: A case study from Kerala, India

Waterlogging and raised soil salinity are leading to land degradation and desertification problems worldwide. It can significantly reduce the agricultural practices and crop yields of affected lands. The present study is attempted to map waterlogged and saline affected areas using LISS-III satellite imagery of pre-monsoon and post-monsoon season of the year 2012. It was observed that the total size of seasonal waterlogged (only Rabi or only Kharif) is 454.96 ha (2.37%) of the total area. The land covered with perennial waterlogged area was found to be 535.54 ha (2.79 %) of the entire command area. The waterlogged area concerning the depth of groundwater was further categorized into most critical, critical, less critical and non-critical. The identification and mapping of salt affected (saline) area was performed during Rabi and Kharif season. Only 0.46% of the command area identified as saline land either in both or single season patches, remaining 99.54% area comes under non saline category. Out of total command area 80.58 and 19.42% areas comes under non-saline and saline zones respectively. The saline area was further classified into medium, high and very high zones. The saline affected area covered with medium, high and very high salt categories is 2.25 ha (0.012%), 26.380 ha (0.137%), and 0.624 ha (0.003%), respectively. In-situ measurements such as pH, electrical conductivity (EC) and exchangeable sodium percentage (ESP) were also used to validate the results. The methodology proposed in this study can potentially be used for cost-effective mapping of soil salinity in other geographical regions.

Soil salinity inversion based on differentiated fusion of satellite image and ground spectra

Due to the wide availability of remote sensing data from different sensors and platforms, soil salinity inversion based on the fusion of multisource remote sensing data is becoming a reality. However, existing fusion methods mainly use the average relationship from samples, which does not consider the differences in the relationships among samples. In this paper, a differentiated fusion method for determining satellite and ground spectral variables of soil salinity according to the differences among samples is proposed to increase the regional inversion precision. Nonnegative matrix factorization was employed to decompose soil salinity spectral variables from the Sentinel-2A Multi-Spectral Instrument (MSI) image and the simulated spectra on ground spectra. Then, the base spectra matrix of soil salinity was from the simulated data, and the weight coefficient matrix was obtained from the Sentinel-2A MSI data as the differentiated correction coefficients. By multiplying the base matrix and weight matrix, the spectral variables were reconstructed. The results indicate that this differentiated fusion method can not only enhance the correlation between soil salinity and Sentinel-2A MSI data but also improve the precision of regional soil salinity inversion models. For the differentiated fused model, the validation R2, RMSE, and RPD were 0.71, 7.02 g/kg, and 1.49, respectively; compared with the unfused model, the validation R2 increased by 0.09, the RMSE decreased by 0.80 g/kg, and the RPD increased by 0.18. Furthermore, the differentiated fused model performed better than the average-ratio adjusted model. These findings have practical implications for the use of multisource optical remote sensing data for regional soil salinity mapping and analysis.

Mapping soil salinity using a combined spectral and topographical indices with artificial neural network.

Monitoring the status of natural and ecological resources is necessary for conservation and protection. Soil is one of the most important environmental resources in agricultural lands and natural resources. In this research study, we used Landsat 8 and Artificial Neural Network (ANN) to monitor soil salinity in Qom plain. The geographical location of 72 surface soil samples from 7 land types was determined by the Latin hypercube method, and the samples were taken to determine the electrical conductivity (EC). Thirty percent of the data was considered as a validation set and 70% as a test set. In addition to the Landsat 8 bands, we used spectral indices of salinity, vegetation, topography, and drainage (DEM, TWI, and TCI) because of their impacts on soil formation and development. We used ANN with different algorithms to model soil salinity. We found that the GFF algorithm is the best for soil salinity modeling. Also, the TWI topography index and SI5 salinity index and NDVI vegetation index had the most effect on the outputs of the selected model. It was also found that flood plains and lowlands had the highest levels of salinity accumulation.