Tree-based algorithms for spatial modeling of soil particle distribution in arid and semi-arid region.

Accurate estimation of particle size distribution across a large area is crucial for proper soil management and conservation, ensuring compatibility with capabilities and enabling better selection and adaptation of precision agricultural techniques. The study investigated the performance of tree-based models, ranging from simpler options like CART to sophisticated ones like XGBoost, in predicting soil texture over a wide geographic region. Models were constructed using remotely sensed plant and soil indexes as covariates. Variable selection employed the Boruta approach. Training and testing data for machine learning models consisted of particle size distribution results from 622 surface soil samples collected in southeastern Turkey. The XGBoostClay model emerged as the most accurate predictor, with an R2 value of 0.74. Its superiority was further underlined by a 21.36% relative improvement in XGBoostClay RMSE compared to RFClay and 44.5% compared to CARTClay. Similarly, the R2 values for XGBoostSilt and XGBoostSand models reached 0.71 and 0.75 in predicting sand and silt content, respectively. Among the considered covariates, the normalized ratio vegetation index and slope angle had the highest impact on clay content (21%), followed by topographic position index and simple ratio clay index (20%), while terrain ruggedness index had the least impact (18%). These results highlight the effectiveness of Boruta approach in selecting an adequate number of variables for digital mapping, suggesting its potential as a viable option in this field. Furthermore, the findings of this study suggest that remote sensing data can effectively contribute to digital soil mapping, with tree-based model development leading to improved prediction performance.

Combination of fuzzy-AHP and GIS techniques in land suitability assessment for wheat (Triticum aestivum) cultivation.

Land suitability classification is a useful management practice to ensure planned and sustainable use of agricultural lands according to their potentials. The main purposes of this study were to analyze land suitability for bread wheat (Triticum aestivum) cultivation and generate a land suitability map for wheat by integrating the analytical hierarchy (AHP)-fuzzy algorithm with the Geographical Information System (GIS) in the Tozanli sub-basin located in the upper part of Yesilirmak Basin, Turkey. Topographic (elevation, slope, aspect) characteristics of the basin and some of physical and chemical properties of soils (texture, pH, electrical conductivity, lime, organic matter, and soil depth) were used as criteria in determining the suitability classes. Ninety-two disturbed soil samples were collected from 0 to 20 cm depth in October 2017 using random sampling method. Weighted overlay spatial analysis in GIS was used to combine different thematic layers to identify areas suitable for wheat production. The fuzzy-AHP suitability assessment model was adapted to determine the weights for topographic and soil properties. The highest specific weights were obtained for soil depth (0.232) and elevation (0.218), while the lowest weight was calculated for aspect (0.042). Highly, moderately, and marginally suitable lands for wheat cultivation cover 2.63, 9.85 and 32.59% of the study area, respectively. In addition, the results indicated that 54.92% of the total area is permanently unsuitable for wheat cultivation. The results revealed that integration of AHP-fuzzy algorithm and GIS techniques is a useful method for accurate evaluation of land suitability in planning for specific crop production and decreasing the negative environmental impacts of agricultural practices.

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.

Epidemiological, Clinical, and Laboratory Features of Children With COVID-19 in Turkey.

Objectives: The aim of this study is to identify the epidemiological, clinical, and laboratory features of coronavirus disease 2019 (COVID-19) in children. Methods: A retrospective study was conducted by pediatric infectious disease specialists from 32 different hospitals from all over Turkey by case record forms. Pediatric cases who were diagnosed as COVID-19 between March 16, 2020, and June 15, 2020 were included. Case characteristics including age, sex, dates of disease onset and diagnosis, family, and contact information were recorded. Clinical data, including the duration and severity of symptoms, were also collected. Laboratory parameters like biochemical tests and complete blood count, chest X-ray, and chest computed tomography (CT) were determined. Results: There were 1,156 confirmed pediatric COVID-19 cases. In total, male cases constituted 50.3% (n = 582) and females constituted 49.7% (n = 574). The median age of the confirmed cases was 10.75 years (4.5-14.6). Of the total cases, 90 were younger than 1 year of age (7.8%), 108 were 1-3 years of age (9.3%), 148 were 3-6 years of age (12.8%), 298 were 6-12 years of age (25.8%), 233 were 12-15 years of age (20.2%), and 268 cases were older than 15 years of age (23.2%). The most common symptom of the patients at the first visit was fever (50.4%) (n = 583) for a median of 2 days (IQR: 1-3 days). Fever was median at 38.4°C (38.0-38.7°C). The second most common symptom was cough (n = 543, 46.9%). The other common symptoms were sore throat (n = 143, 12.4%), myalgia (n = 141, 12.2%), dyspnea (n = 118, 10.2%), diarrhea (n = 112, 9.7%), stomachache (n = 71, 6.1%), and nasal discharge (n = 63, 5.4%). When patients were classified according to disease severity, 263 (22.7%) patients were asymptomatic, 668 (57.7%) patients had mild disease, 209 (18.1%) had moderate disease, and 16 (1.5%) cases had severe disease. One hundred and forty-nine (12.9%) cases had underlying diseases among the total cases; 56% of the patients who had severe disease had an underlying condition (p < 0.01). The need for hospitalization did not differ between patients who had an underlying condition and those who do not have (p = 0.38), but the need for intensive care was higher in patients who had an underlying condition (p < 0.01). Forty-seven (31.5%) of the cases having underlying conditions had asthma or lung disease (38 of them had asthma). Conclusions: To the best of our knowledge, this is one of the largest pediatric data about confirmed COVID-19 cases. Children from all ages appear to be susceptible to COVID-19, and there is a significant difference in symptomatology and laboratory findings by means of age distribution.