Improvement of spatial estimation for soil organic carbon stocks in Yuksekova plain using Sentinel 2 imagery and gradient descent-boosted regression tree.

Carbon sequestration in earth surface is higher than the atmosphere, and the amount of carbon stored in wetlands is much greater than all other land surfaces. The purpose of this study was to estimate soil organic carbon stocks (SOCS) and investigate spatial distribution pattern of Yuksekova wetlands and surrounding lands in Hakkari province of Turkey using machine learning and remote sensing data. Disturbed and undisturbed soil samples were collected from 10-cm depth in 50 locations differed with land use and land cover. Vegetation, soil, and moisture indices were calculated using Sentinel 2 Multispectral Sensor Instrument (MSI) data. Significant correlations (p≤0.01) were obtained between the indices and SOCS; thus, the remote sensing indices (ARVI 0.43, BI -0.43, GSI -0.39, GNDI 0.44, NDVI 0.44, NDWI 0.38, and SRCI 0.51) were used as covariates in multi-layer perceptron neural network (MLP) and gradient descent-boosted regression tree (GBDT) machine learning models. Mean absolute error, root mean square error, and mean absolute percentage error were 3.94 (Mg C ha -1), 6.64 (Mg C ha-1), and 9.97%, respectively. The simple ratio clay index (SRCI), which represents the soil texture, was the most important factor in the SOCS estimation variance. In addition, the relationship between SRCI and Topsoil Grain Size Index revealed that topsoil clay content is a highly important parameter in spatial variation of SOCS. The spatial SOCS values obtained using the GBDT model and the mean SOCS values of the CORINE land cover classes were significantly different. The land cover has a significant effect on SOC in Yuksekova plain. The mean SOCS for continuously ponded fields was 45.58 Mg C ha-1, which was significantly different from the mean SOCS of arable lands. The mean SOCS in arable lands, with significant areas of natural vegetation, was 50.22 Mg C ha-1 and this amount was significantly higher from the SOCS of other land covers (p<0.01). The wetlands had the highest SOCS (61.46 Mg C ha-1), followed by the lands principally occupied by natural vegetation and used as rangelands around the wetland (50.22 Mg C ha-1). Environmental conditions had significant effect on SOCS in the study area. The use of remote sensing indices instead of using single bands as estimators in the GBDT algorithm minimized radiometric errors, and reliable spatial SOCS information was obtained by using the estimators. Therefore, the spatial estimation of SOCS can be successfully determined with up-to-date machine learning algorithms only using remote sensing predictor variables. Reliable estimation of SOCS in wetlands and surrounding lands can help understand policy and decision makers the importance of wetlands in mitigating the negative impacts of global warming.

Combining spatial autocorrelation with artificial intelligence models to estimate spatial distribution and risks of heavy metal pollution in agricultural soils.

Information on spatial distribution and potential sources of heavy metals in agricultural lands is very important for human health and food safety. In this study, pollution degree of lead (Pb), cadmium (Cd), and nickel (Ni) in Yüksekova Plain, located on the border in the southeastern part of Turkey, was evaluated by geoaccumulation index (Igeo), modified contamination factor (mCdeg), and Nemerow pollution index (PINemerow) combined with spatial autocorrelation using deep learning algorithms. A total of 304 soil samples were collected from two different depths (0-20 and 20-40 cm) in the study area, which covered 17.5 thousand ha land. Covariates were determined for spatial distribution models of Pb, Cd, and Ni by factor analysis (FA). Spatial distribution models for surface soils were developed using pedovariables (silt, sand, clay lime, organic matter, electrical conductivity, pH, Ca, and Na) determined by the FA and Igeo and mCdeg values by artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) models. The estimation success of models for different depths was assessed by root mean square error (RMSE), mean absolute percent error (MAPE), and Taylor diagrams. The RMSE and MAPE values showed a strong correlation between heavy metal contents and the covariates. The RMSE values of ANN-Ni0-20, ANN-Ni20-40, ANN-Pb0-20, ANN-Cd0-20, and ANN-Cd20-40 models (0.01240, 0.07257, 0.0039, 0.00045, 0.00044, and 0.04607, respectively) confirmed the success of the models. Likewise, the MAPE values between 0.2 and 8.5% indicated that all models were very good predictors. In addition, the Taylor diagrams showed that the estimation performance of ANFIS and ANN models are compatible. The IgeoNi and IgeoPb values in both models at both depths indicated that strongly to extremely polluted (4-5) areas are quite high in the study area, while the IgeoCd values revealed that unpolluted areas are widespread. The mCdeg index value showed a moderate to high contamination at the first depth, while very high contamination at the second depth in most of the study area. Spatial distribution of PINemerow revealed that moderate pollution (2-3) is common in both soil depths of the study area. The PINemerow of subsurface layer was between 0.91 and 1 (warning limit class) in a small part of the study area. The results showed that vertical mobility of heavy metals is closely related to pedovariables. In addition, the ANN and ANFIS models are capable of exhibiting the heterogeneity in the spatial distribution pattern of high variation in the data. Thus, the locations with extreme contamination have been accurately determined. The pollution indices calculated considering the commonly used international reference values revealed that heavy metal pollution in some part of the study area reached the detrimental levels for human health and food safety. The results suggested that the pollution indices were more successful than simple heavy metal concentrations in interpreting the pollution risk levels. High-resolution spatial information reported in this study can help policy makers and authorities to reduce heavy metal emissions of pollutants or, if possible, to eliminate the pollution.

Soil salinity assessment of a natural pasture using remote sensing techniques in central Anatolia, Turkey.

Soil salinity is a major land degradation process reducing biological productivity in arid and semi-arid regions. Therefore, its effective monitoring and management is inevitable. Recent developments in remote sensing technology have made it possible to accurately identify and effectively monitor soil salinity. Hence, this study determined salinity levels of surface soils in 2650 ha agricultural and natural pastureland located in an arid region of central Anatolia, Turkey. The relationship between electrical conductivity (EC) values of 145 soil samples and the dataset created using Landsat 5 TM satellite image was investigated. Remote sensing dataset for 23 variables, including visible, near infrared (NIR) and short-wave infrared (SWIR) spectral ranges, salinity, and vegetation indices were created. The highest correlation between EC values and remote sensing dataset was obtained in SWIR1 band (r = -0.43). Linear regression analysis was used to reveal the relationship between six bands and indices selected from the variables with the highest correlations. Coefficient of determination (R2 = 0.19) results indicated that models obtained using satellite image did not provide reliable results in determining soil salinity. Microtopography is the major factor affecting spatial distribution of soil salinity and caused heterogeneous distribution of salts on surface soils. Differences in salt content of soils caused heterogeneous distribution of halophytes and led to spectral complexity. The dark colored slickpots in small-scale depressions are common features of sodic soils, which are responsible for spectral complexity. In addition, low spatial resolution of Landsat 5 TM images is another reason decreasing the reliability of models in determining soil salinity.

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.