Design and analysis of land-use management scenarios requires detailed soil data. When such data are needed on a large scale, pedotransfer functions (PTFs) could be used to estimate different soil properties. Because existing regression-based PTFs for estimating cation exchange capacity (CEC) do not, in general, apply well to arid areas, this study was conducted (i) to evaluate the existing models and (ii) to develop neural network-based PTFs for predicting CEC in Aridisols of Isfahan in central Iran. As most researches have found a significant correlation between CEC and soil organic matter content (OM) and clay content, we also used these two variables for modelling of CEC. We tested several published PTFs and developed two neural network algorithms using multilayer perceptron and general regression neural networks based on a set of 170 soil samples. The data set was divided into two subsets for calibration and testing of the models. In general, the neural network-based models provided more reliable predictions than the regression-based PTFs.

No abstract

Due to potential problems associated with their toxicities, concentration of heavy metals in soils is of great environmental concern. To evaluate Cd content, its spatial pattern, and availability in the surface soils of agricultural, industrial and urban regions of Isfahan, central Iran, we collected 255 topsoil samples (0-20 cm) from the nodes of an irregular grid in a study area of 6800 km 2 . In the soil samples we measured total and DTPA-extractable Cd concentrations, soil pH, organic mater (OM), clay content, soil salinity, and chloride concentration. The total Cd concentration in 90% of the samples exceeded the suggested Swiss thresholds of 0.8 mg kg −1 . Landuse had a significant effect on total concentration of Cd in the soil but had no effect on DTPA-extractable Cd. High values of total Cd were found in industrial and urban areas whereas low values occurred in uncultivated lands. The correlation analysis revealed that soil salinity alone explained 36% of the Cd variation in the entire study area. The correlation was particularly strong in uncultivated areas (R 2 = 0.70). Spatial analysis of available Cd using indicator kriging and soil salinity showed a spatial co-occurrence of these two variables.

No abstract

Soil organic carbon (SOC) is a very important component of soil that supports the sustainability and quality in all ecosystems, especially in semi-arid region. This study was conducted to evaluate the effects of 15 different climatic, soil, and geometric factors on the SOC contents in different land use patterns and to determine relative importance of these desired variables for SOC estimation in one of the semi arid watershed zones in the western part of Iran. Feed forward back propagation artificial neural networks (ANN), was used to model and predict SOC. The performance of the model was evaluated using R² and MBE values of tested data set. Results showed that 31-2-1 neural networks have highest predictive ability that explains %76 of SOC variability. Neural network models slightly overestimated SOC content, and had higher ability to detect management variables effects on SOC variability. In all ANN structure, management system dominantly controlled SOC variability in rainfed crop land of semi arid condition.