In this study, we present the performances of the best training algorithm in Multilayer Perceptron (MLP) neural networks for prediction of suspended sediment discharges in Mellah catchment. Time series data of daily suspended sediment discharge and water discharge from the gauging station of Bouchegouf were used for training and testing the networks. A number of statistical parameters, i.e. root mean square error (RMSE), mean absolute error (MAE), coefficient of efficiency (CE) and coefficient of determination (R2) were used for performance evaluation of the model. The model produced satisfactory results and showed a very good agreement between the predicted and observed data. The results also showed that the performance of the MLP model was capable to capture the exact pattern of the sediment discharge data in the Mellah catchment.

Land and water are two most vital natural resources of the world and hence these resources must be conserved carefully to protect environment and maintain ecological balance. Estimation of soil erosion is one of the prerequisites for conservation and management of water resources and watersheds. The present study was carried out to predict soil erosion in the Mellah catchment, northeastern Algeria. Due to the importance of the water resources of this watershed and the lack of sedimentation data in this valley, a comprehensive methodology integrates Revised Universal Soil Loss Equation (RUSLE) model, remote sensing and GIS techniques to determine the catchment soil erosion vulnerability. The elaborations of RUSLE factors in this study were based on multisource data for the improvement of soil erosion estimation. The results indicated that the average soil loss is 10.21 t. ha -1 .yr -1 , with a total annual soil loss in the basin area of 5648.58 t. Around 90% of area was under very low erosion risk, and5% of area was considered as moderate erosion risk while 3% of area was considered as high to very high erosion risk. The climate change and rainfall fluctuations witnessed influenced the soil loss in this region. Thus, the high erosivity registered has consequent in the detachment of particles due to the soil texture types in this region. The conjunction of high erosivity, soil texture and high steep slopes in this region resulted in high potential soil erosion which could lead to the deterioration of water resources if not a mitigation measures and an immediate intervention are taken in the Mellah catchment.