Prediction of Soil Salinity Using Remote Sensing Tools and Linear Regression Model (original) (raw)
Related papers
Sentinel-2 based mapping of soil salinity of arid soils in southeastern regions of Tunisia
Arid and semi-arid regions are faced on soil salinization’s problem causing land degradation that’s why studies are focused on the prevention and the mitigation of this parameter in these environments. It degrades soil, limits plant growth and reduces crop productivity. Recently, the demand for rapid and economic detection of soil salinization has been rising. Remote sensing and multispectral data Sentinel_2 are used to predict and mapping soil salinity in southern Tunisia. In this study, 80 samples were collected from the soil surface (the upper 10 cm). A predictive model was constructed based on the measured soil electrical conductivity (EC) and spectral indices developed from satellite image. The results revealed that salinity index SI1, SI2 and band 3 have the highest correlation with EC. Multiple regression analysis showed a moderate accuracy with R2 = 0.42 and an RMSE = 18.3.This predictive model, special to arid and semi-arid environments, can be applied to other satellite da...
Soil salinity expansion is an environmental challenge particularly in arid and semi arid regions. In order to evaluate the progressing extent of soil salinity in relation with natural and human-induced conditions, a study was conducted using the Landsat TM imagery. The present study was conducted in the Garmsar area to the East of Tehran. A total of 288 soil samples were analyzed to determine the relationship between the spectral reflectance and Electrical Conductivity (EC), as salinity indicator. Multiple regression analysis and Ordinary Least Square regression (OLS) were used to examine the relationships between EC and derived spectral to generate several models. In the case of derived spectral, mid-infrared band (TM Band-7), visible band (Band-1), Tasseled cap3 (Wetness index) and PCA2 (Principal Component Analysis) were found to be most correlated with the observed EC values of the surface layer of the soil, at 99% confidence level. The accuracy of the prediction model was tested using a validation set of 52 soil samples in Eyvanekey plain, close to study area where the environmental circumstance consist of similar properties. RMSE and MAE were used to evaluate the performance of the map prediction quality. Results showed that the appropriate model could predict the soil salinity with precision of 4.1 and 0.49 dS m -1 , respectively. The predicted salinity ranged from 0dS/m to 110dS/m. Therefore, the EC estimations were suitable to generate soil salinity map. Sensitivity analysis was tested on applied parameters that showed Band-1 and Band-7 were 3 and 2 times more than sensitive rather than other parameters respectively. The results are promising and certainly useful for soil salinity prediction.
Ecological Indicators, 2020
Soil salinization is one of the significant soil degradation problems especially faced in arid and semi-arid regions of the world. It poses a high threat to soil productivity in agricultural lands. The demand for economic and rapid detection and temporal monitoring of soil salinity has been rising recently. Satellite imagery and remote sensing approaches are the significant tools for accurate prediction and mapping of soil salinity in various regions of the world. This study aims to compare Landsat-8 OLI and Sentinel-2A derived soil salinity maps of the western part of Urmia Lake in Iran by applying three different salinity indices in conjunction with field measurements. Totally 70 soil samples were collected from top 20 cm of surface soil in October 2016 from an area of 18 km 2. Landsat-8 OLI and Sentinel-2A images were acquired in the same month; both images were atmospherically and radiometrically corrected prior to applying soil salinity indices. After comparing Normalized Difference Vegetation Index (NDVI) value of corresponding pixel for each sample with its electrical conductivity (EC) value, 54 soil samples with various EC ranges were selected for mapping. Among them, 42 samples were used for establishing the regression model and remaining 12 samples were utilized to validate the model. Multiple and linear regression analyses were conducted to correlate the EC data with their corresponding soil salinity spectral index values derived from visible bands of satellite images. The results revealed that soil salinity indices extracted from both Landsat-8 OLI and Sentinel-2A visible bands estimated soil salinity with acceptable accuracy of R 2 0.73 and 0.74, respectively. Multiple linear regression analysis using both Landsat-8 OLI and Sentinel-2A data demonstrated higher accuracy with R 2 value of 0.77 and 0.75, respectively, compared to linear regression. This study proves that various soil salinity classes with different EC ranges can be estimated by correlating ground measurement data with satellite data.
Detection and modeling of soil salinity variations in arid lands using remote sensing data
Open Geosciences, 2021
Soil salinization is a ubiquitous global problem. The literature supports the integration of remote sensing (RS) techniques and field measurements as effective methods for developing soil salinity prediction models. The objectives of this study were to (i) estimate the level of soil salinity in Abu Dhabi using spectral indices and field measurements and (ii) develop a model for detecting and mapping soil salinity variations in the study area using RS data. We integrated Landsat 8 data with the electrical conductivity measurements of soil samples taken from the study area. Statistical analysis of the integrated data showed that the normalized difference vegetation index and bare soil index showed moderate correlations among the examined indices. The relation between these two indices can contribute to the development of successful soil salinity prediction models. Results show that 31% of the soil in the study area is moderately saline and 46% of the soil is highly saline. The results support that geoinformatic techniques using RS data and technologies constitute an effective tool for detecting soil salinity by modeling and mapping the spatial distribution of saline soils. Furthermore, we observed a low correlation between soil salinity and the nighttime land surface temperature.
Mapping soil salinity in irrigated land using optical remote sensing data
EURASIAN JOURNAL OF SOIL SCIENCE (EJSS), 2014
Soil salinity caused by natural or human-induced processes is certainly a severe environmental problem that already affects 400 million hectares and seriously threatens an equivalent surface. Salinization causes negative effects on the ground; it affects agricultural production, infrastructure, water resources and biodiversity. In semi-arid and arid areas, 21% of irrigated lands suffer from waterlogging, salinity and/or sodicity that reduce their yields. 77 million hectares are saline soils induced by human activity, including 58% in the irrigated areas. In the irrigated perimeter of Tadla plain (central Morocco), the increased use of saline groundwater and surface water, coupled with agricultural intensification leads to the deterioration of soil quality. Experimental methods for monitoring soil salinity by direct measurements in situ are very demanding of time and resources, and also very limited in terms of spatial coverage. Several studies have described the usefulness of remote sensing for mapping salinity by its synoptic coverage and the sensitivity of the electromagnetic signal to surface soil parameters. In this study, we used an image of the TM Landsat sensor and field measurements of electrical conductivity (EC), the correlation between the image data and field measurements allowed us to develop a semi-empirical model allowing the mapping of soil salinity in the irrigated perimeter of Tadla plain. The validation of this model by the ground truth provides a correlation coefficient r² = 0.90. Map obtained from this model allows the identification of different salinization classes in the study area.
Agronomy
Oasis lands in Egypt are commonly described as salty soils; therefore, waterlogging and higher soil salinity are major obstacles to sustainable agricultural development. This study aims to map and assess soil salinization at El-Farafra Oasis in the Egypt Western Desert based on salinity indices, Imaging Spectroscopy (IS), and statistical techniques. The regression model was developed to test the relationship between the electrical conductivity (ECe) of 70 surface soil samples and seven salinity indices (SI 1, SI 2, SI 5, SI 6, SI 7, SI 8, and SI 9) to produce soil salinity maps depending on Landsat-8 (OLI) images. The investigations of soil salinization and salinity indices were validated in a studied area based on 30 soil samples; the obtained results represented that all salinity indices have shown satisfactory correlations between ECe values for each soil sample site and salinity indices, except for the SI 5 index that present non-significant correlations with R2 value of 0.2688....
Desert, 2020
Soil salinity undergoes significant spatial and temporal variations; therefore, salinity mapping is difficult, expensive, and time consuming. However, researchers have mainly focused on arid soils (bare) and less attention has been paid to halophyte plants and their role as salinity indicators. Accordingly, this paper aimed to investigate the relationship between soil properties, such as electrical conductivity of the saturation extract (ECe) and the spectral reflectance of vegetation species and bare soil, to offer a method for providing salinity map using remote sensing. Various vegetation species and bare soil reflectance were measured. Spectral Response Index (SRI) for bare soil and soil with vegetation was measured via the Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), and salinity indexes. The electrical conductivity of the saturated extract, texture, and organic matter of soil samples were determined. The correlation coefficient of soil salinity with SRI, SAVI, and salinity indexes were obtained, and a model was presented for soil salinity prediction. EC map was estimated using the proposed model. The correlation between SRI and EC was higher than other models (0.97). The results showed that the salinity map obtained from the model had the highest compliance (0.96) with field findings. In general, in this area and similar areas, the SRI index is an acceptable indicator of salinity and soil salinity mapping.
Soil salinity and ground surface morphology in the Lower Cheliff plain (Algeria) can directly or indirectly impact the stability of environments. Soil salinization in this area is a major pedological problem related to several natural factors, and the topography appears to be important in understanding the spatial distribution of soil salinity. In this study, we analyzed the relationship between topographic feature and soil salinity, giving their role in understanding and estimating the spatial distribution of soil salinity in the Lower Cheliff plain. Two satellite images of Landsat 7 in winter and summer 2013 with reflectance values and the digital elevation model (DEM) were used. We derived the elevation and slope gradient values from the DEM corresponding to the sampling points in the field. We also calculated the vegetation and soil indices (i.e. NDVI (normalized difference vegetation index), RVI (ratio vegetation index), BI (brightness index) and CI (color index)) and soil salinity indices, and analyzed the correlations of soil salinity with topography parameters and the vegetation and soil indices. The results showed that soil salinity had no correlation with slope gradient, while it was significantly correlated with elevation when the EC (electrical conductivity) values were less than 8 dS/m. Also, a good relationship between the spectral bands and measured soil EC was found, leading us to define a new salinity index, i.e. soil adjusted salinity index (SASI). SASI showed a significant correlation with elevation and measured soil EC values. Finally, we developed a multiple linear regression for soil salinity prediction based on elevation and SASI. With the prediction power of 45%, this model is the first one developed for the study area for soil salinity prediction by the combination of remote sensing and topographic feature analysis.
Desert, 2028
Saline lakes can increase the soil and water salinity of the coastal areas. The main aim of this study is to distinguish the characteristics of the spectral reflectance of saline soil, analyze the statistical relationship between soil EC and characteristics of the spectral reflectance of saline soil, and to map soil salinity east of the Maharloo Lake. The correlation between field measurements of electrical conductivity and remote sensing spectral indices was evaluated using multiple regression analysis. In this study, Kriging, CoKriging, and multiple regressions were applied for soil salinity mapping and classification using 100 soil samples. After radiometric, geometric, and atmospheric corrections of Landsat OLI images, the statistical correlation between the electrical conductivity of field measurements and spectral reflectance was investigated. According to obtained results, the modified salinity index (MSI) with the highest correlation (R 2 =0.78) was used as an auxiliary vari...
Estimating Soil Salinity Over a Shallow Saline Water Table in Semiarid Tunisia
The Open Hydrology Journal, 2010
Rapid and reliable observations of soil electrical conductivity are essential in order to maintain sustainable irrigated agriculture. Direct measurement of the electrical conductivity of saturated soil paste (ECe), however, is tedious and time consuming. Therefore, there are needs to find efficient indirect methods to predict the soil salinity from other readily available observations. In this paper we explore the application of multiple linear regression (MLR) and artificial neural networks (ANN) to predict ECe variation from easily measured soil and groundwater properties under highly complex and heterogeneous field conditions in semiarid Tunisia. We compare two methods for dividing the data set into training and validation sub-sets; a statistical (SD) and a random data set division (RD), and their effect on model performance. The input variables were chosen from the plot coordinates, groundwater table properties (depth, electrical conductivity, piezometric level), and soil particle size at 5 depths. The results obtained with ANN and MLR indicate that the statistical properties of data in the training and validation sets need to be taken into account to ensure that optimal model performance is achieved. The SD can be considered as a solution to resolve the problem of over-fitting a model when using ANN. For the SD, the determination coefficient (R 2 ) when using an ANN model varied from 0.85 to 0.88 and the root mean square error from 1.23 to 1.80 dS m -1 . Because of the complexity of the field soil salinity process and the spatial variability of the data, this clearly indicates the potential to use ANN models to predict ECe.