No abstract

No abstract

Multilayer Artificial Neural Networks (ANNs) with the backpropagation algorithm were used to estimate the decrease in relative saturated conductivity due to an increase in sodicity and salinity. Data from the literature on the relative saturated hydraulic conductivity measured using water having levels of sodicity and salinity in different types of semiarid soils were used. The clay content of these soils is predominantly montmorillonite. The input data consisted of clay percentage, cation exchange capacity, electrolyte concentration, and estimated soil exchangeable sodium percentage at equilibrium stage with the solution applied. The data was divided into three groups randomly to meet the three phases required for developing the ANNs model (i. e. training, evaluation, and testing).The activation function selected was the TANSIG layer in the middle, while the exit function was the PURELIN layer. The comparisons between the experimental and predicted data on relative saturated hydraulic conductivity during training and testing phases showed good agreement. This was evident from the statistical indicators used for the evaluation process. For the training phase, the values of mean absolute error (MAE), root mean square error (RMSE), the correlation coefficient (r) and the determination coefficient (R 2 ) were 0.08, 0.13, 0.91, and 0.83, respectively. The performance of the ANNs model was evaluated against a part of the data selected randomly form the whole set of data collected (i. e. data not used during the model testing phase). The resultant values for MAE and RMSE, r and R 2 were 0.12, 0.16, 0.82 and 0.68, respectively. It should be noted that many factors were not considered, such as soil pH, type of clay, and organic matter, due to the limitations of the data available. Using these factors as input in ANNs might improve model predictions. However, the results suggested that the ANNs model performs well in soils with very low levels of organic matter. Sodicity Salinity Soil Hydraulic ConductivityArtificial Neural Networks

Determining variabilities of soil properties is important for ecological modelling, environmental predictions, precise agriculture, and management of natural resources. This study was aimed to examine Inverse distance weight (IDW) to predict the spatial variability of Exchangeable Sodium Percentage (ESP), Calcium Carbonate Percentage (% CaCO3) soil pH, Electrical conductivity and % Gypsum . The study area selected for this work consists of Ayn Hizam, Qaryat- Batth and Taknis. Data for 220 randomly distributed representing soil profiles were encoded in spreadsheets, 198 of them were used for predicting the spatial variability in the GIS environment for ESP, % CaCO3, soil pH, Electrical conductivity and % Gypsum. The rest of Data (i.e. 22 representative soil profiles) were utilized to evaluate the maps produced using Kriging or IDW methods. The results showed that using IDW method was trustable because the values of RMSE and R2 for all the IDW maps were within the acceptable range. The study suggested adopting the Geostatistical methods for studying spatial prediction for different soil proprieties. In addition, the study recommended updating soil data for the study area.

This study aimed to monitor the change in land cover in Garabulli regionduring the period (1992 - 2010) by using remote sensing technique. The satellite imagesused in this study were obtained from the satellite Spot 4 for each of years of 1992 and 2000 and Spot 5 for year 2010.  The supervised classification was performed on the Spot images using maximum likelihood classification. The land cover changes were detected during different times by land cover maps which were produced using ENVI software. The results have revealed clear changes in the land cover whereas barren land, agricultural land, and urban area have been increased by 37.6%, 35.1%, and 28% between 1992 and 2010, respectively. Meanwhile, forest and rangeland were decreased between 1992 and 2010 by 65% and 41%, respectively. The results showed that declining of forest and rangeland may lead to rapidly increase of desertification. Additionally, the present study revealed that the remote sensing techniques can be used effectively in monitoring and interpreting the changes which may occur in the land cover.