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.

Accuracy Assessment of Kriging, artificial neural network, and a hybrid approach integrating spatial and terrain data in estimating and mapping of soil organic carbon.

This study aimed to produce a soil organic carbon (SOC) content map with high accuracy and spatial resolution using the most effective factors in the model. The spatial SOC estimation success of Inverse Distance Weighting (IDW), Ordinary Kriging (OK), Empirical Bayesian Kriging (EBK), Multi-Layered Perception Network (MLP) and MLP-OK Hybrid models were compared to obtain the most reliable model in estimating the SOC content. The study area was located in Besni district in the Southeastern Anatolia Region of Turkey. Total of 132 surface (0-30 cm) soil samples were collected from the covers 1330 km2 land and analyzed for SOC, lime, clay and sand content and soil reaction included in the estimation models. Mean annual precipitation and temperature, elevation, compound topographic index, enhanced vegetation and normalized difference vegetation index, were also used as the inputs in the modelling. The spatial distribution of SOC was determined using a MLP and a two-stage ensemble model (MLP-OK) combining the estimation of OK residuals. Soil surveys and covariates were used to train and validate the MLP-OK hybrid model. The MLP-OK model provided a more accurate estimation of SOC content with minimal estimation errors (ME: -0.028, 45 MAE: 0.042, RMSE: 0.066) for validation points compared to the other models. The MLP-OK model outperformed other models by 75.09 to 77.92%. The MLP-OK model estimated the lower and upper limits of the estimated and the measured values in a consistent manner compared to the other models. The spatial distribution map of SOC content obtained by ANN-kriging approach was significantly affected by ancillary variables, and revealed more detail than other interpolation methods in the northern, central, southwestern and southeastern parts of the study area. The results revealed that the assembling of MLP with OK model can contribute to obtain more reliable regional, national and global spatial soil information.

Germination Biology of Two Invasive Physalis Species and Implications for Their Management in Arid and Semi-arid Regions.

Two Solanaceae invasive plant species (Physalis angulata L. and P. philadelphica Lam. var. immaculata Waterfall) infest several arable crops and natural habitats in Southeastern Anatolia region, Turkey. However, almost no information is available regarding germination biology of both species. We performed several experiments to infer the effects of environmental factors on seed germination and seedling emergence of different populations of both species collected from various locations with different elevations and habitat characteristics. Seed dormancy level of all populations was decreased with increasing age of the seeds. Seed dormancy of freshly harvested and aged seeds of all populations was effectively released by running tap water. Germination was slightly affected by photoperiods, which suggests that seeds are slightly photoblastic. All seeds germinated under wide range of temperature (15-40 °C), pH (4-10), osmotic potential (0 to -1.2 MPa) and salinity (0-400 mM sodium chloride) levels. The germination ability of both plant species under wide range of environmental conditions suggests further invasion potential towards non-infested areas in the country. Increasing seed burial depth significantly reduced the seedling emergence, and seeds buried below 4 cm of soil surface were unable to emerge. In arable lands, soil inversion to maximum depth of emergence (i.e., 6 cm) followed by conservational tillage could be utilized as a viable management option.

Invasion Potential of Two Tropical Physalis Species in Arid and Semi-Arid Climates: Effect of Water-Salinity Stress and Soil Types on Growth and Fecundity.

Invasive plants are recognized for their impressive abilities to withstand adverse environmental conditions however, all invaders do not express the similar abilities. Therefore, survival, growth, nutrient uptake and fecundity of two co-occurring, invasive Physalis species were tested under water and salinity stresses, and different soil textures in the current study. Five different water stress levels (100, 75, 50, 25, and 12.5% pot water contents), four different soil salinity levels (0, 3, 6, and 12 dSm-1) and four different soil textures (67% clay, 50% clay, silt clay loam and sandy loam) were included in three different pot experiments. Both weeds survived under all levels of water stress except 12.5% water contents and on all soil types however, behaved differently under increasing salinity. The weeds responded similarly to salinity up till 3 dSm-1 whereas, P. philadelphica survived for longer time than P. angulata under remaining salinity regimes. Water and salinity stress hampered the growth and fecundity of both weeds while, soil textures had slight effect. Both weeds preferred clay textured soils for better growth and nutrient uptake however, interactive effect of weeds and soil textures was non-significant. P. angulata accumulated higher K and Na while P. philadelphica accrued more Ca and Mg as well as maintained better K/Na ratio. P. angulata accumulated more Na and P under salinity stress while, P. philadelphica accrued higher K and Mg, and maintained higher K/Na ratio. Collectively, highest nutrient accumulation was observed under stress free conditions and on clay textured soils. P. philadelphica exhibited higher reproductive output under all experimental conditions than P. angulata. It is predicted that P. philadelphica will be more problematic under optimal water supply and high salinity while P. angulata can better adapt water limited environments. The results indicate that both weeds have considerable potential to further expand their ranges in semi-arid regions of Turkey.

Spatial variability of depth and salinity of groundwater under irrigated ustifluvents in the Middle Black Sea Region of Turkey.

Information on the potential risk for soil salinity buildup can be very helpful for soil salinity management in irrigated areas. We evaluated the spatial and temporal variability of groundwater salinity (GWS) and groundwater depth (GWD), which are two of the most important indicators of soil salinity, by indicator kriging technique in a large irrigated area in northern Turkey. GWS and GWD were measured on a monthly basis from irrigation season (August 2003) to rainy season (April 2004) at 60 observation wells in the 8,187-ha irrigated area. Five indicator thresholds were used for GWS and GWD. The semivariogram for each of the thresholds for both variables was analyzed then used together with experimental data to interpolate and map the corresponding conditional cumulative distribution functions (CCDF). Risk for soil salinity buildup was greater in the irrigation season compared to that in the rainy season. The greatest risk for soil salinity buildup occurred in the eastern part of the study area, suffering from poor drainage problem due to malfunctioning drainage infrastructure, as indicated by the CCDF of GWS and GWD obtained in both seasons. It was concluded that a combination of mechanical and cultural measures should be taken in high-risk locations to avoid further salinity problems.