Forest fires are one of the most important factors in environmental risk assessment and it is the main cause of forest destruction in the Mediterranean region. Forestlands have a number of known benefits such as decreasing soil erosion, containing wild life habitats, etc. Additionally, forests are also important player in carbon cycle and decreasing the climate change impacts. This paper discusses forest fire probability mapping of a Mediterranean forestland using a multiple data assessment technique. An artificial neural network (ANN) method was used to map forest fire probability in Upper Seyhan Basin (USB) in Turkey. Multi-layer perceptron (MLP) approach based on back propagation algorithm was applied in respect to physical, anthropogenic, climate and fire occurrence datasets. Result was validated using relative operating characteristic (ROC) analysis. Coefficient of accuracy of the MLP was 0.83. Landscape features input to the model were assessed statistically to identify the most descriptive factors on forest fire probability mapping using the Pearson correlation coefficient. Landscape features like elevation (R = −0.43), tree cover (R = 0.93) and temperature (R = 0.42) were strongly correlated with forest fire probability in the USB region

Soil salinity negatively affects plant growth and leads to soil degradation. Saline lands result in low agricultural productivity, affecting the well-being of farmers and the economic situation in the region. The prediction of soil salinization dynamics plays a crucial role in sustainable development of agricultural regions, in preserving the ecosystems, and in improving irrigation management practices. Accurate information through monitoring and evaluating the changes in soil salinity is essential for the development of strategies for agriculture productivity and efficient soil management. As part of an ex-ante analysis, we presented a comprehensive statistical framework for predicting soil salinity dynamics using the Homogeneity test and linear regression model. The framework was operationalized in the context of the Khorezm region of Uzbekistan, which suffers from high levels of soil salinity. The soil salinity trends and levels were projected under the impact of climate change from 2021 to 2050 and 2051 to 2100. The results show that the slightly saline soils would generally decrease (from 55.4% in 2050 to 52.4% by 2100 based on the homogeneity test; from 55.9% in 2050 to 54.5% by 2100 according to the linear regression model), but moderately saline soils would increase (from 31.2% in 2050 to 32.5% by 2100 based on the homogeneity test; from 31.2% in 2050 to 32.4% by 2100 according to the linear regression model). Moreover, highly saline soils would increase (from 13.4% in 2050 to 15.1% by 2100 based on the homogeneity test; from 12.9% in 2050 to 13.1% by 2100 according to the linear regression model). The results of this study provide an understanding that soil salinity depends on climate change and help the government to better plan future management strategies for the region.

Understanding the soil and hydrologic processes in agricultural watersheds are vital for reliable assessments of water quantity and quality to support integrated river basin management. However, deriving hydrology-relevant information is complicated in flat data-scarce agricultural watersheds due to constraints in watershed delineation, flat topography, poor natural drainage, and irregular irrigation schedules by human intervention. The study aimed to improve the applicability of the Soil and Water Assessment Tool (SWAT) model to simulate daily flow and NO₃ concentrations in a flat data-scarce agricultural watershed in the Lower Seyhan Plain (LSP) in Turkey. Refined digitized stream networks, discharge data derived from fully equipped gauging stations, and satellite data (Landsat 7 ETM+, Aster GDEM, etc.) had to be integrated into the modeling process to improve the simulation quality. The model was calibrated using a 2-year (2011–2012) dataset of streamflow and NO₃ using the Sequential Uncertainty Fitting (SUFI-2) approach and validated from 2013 to 2018. Daily water yields were predicted with a reasonable simulation accuracy (E values ranging from 0.53 to 0.82 and percent bias (PBIAS) from 0 to +4.1). The results proved that integrating redefined stream networks to SWAT within a Geographic Information System (GIS) environment increases the simulation capability of flow and nitrate dynamics efficiently. Automated delineation of these networks and sub-basins at low topographic transitions limits the SWAT accuracy.