Simulating soil loss rate in Ekbatan Dam watershed using experimental and statistical approaches

Reservoir sedimentation resulting fromwater erosion is an important environmental issue inmany countries where storage of water is crucial for economic and agricultural development.Therefore,this paper reports results from analysis of the soil hydrological response,i.e.soil water erosion,to simulated rainfall resulting in sediment accumulation at the reservoir of Ekbatan Dam(Hamedan province,Iran).Also,another objective of this study was to simulate the future trends in reservoir sedimentation(soil loss rate;SLR)from indoor rainfall simulator data by multiple linear regression(MLR)and Artificial Neural Networks(ANNs).For this research,three sampling points with different types of soils were chosen including clayey sand soil(SC-SM),silty soil(ML),and clayey soil(CL).The input parameters were slope gradient(sin θ),soil type(St),water content(w),dry density(γd),shear strength(τ),unconfined compressive strength(qu),permeability(k),and California bearing ratio(CBR).Using MLR and ANN methods,7 models were developed with 2 constant predictors(i.e.sin θ and St)and 6 free predictors which were added in each step one by one.Among MLR models,model 5 with St,sin θ,γd,τ,w,and qu as input parameters was statistically significant.Among ANN models,model 4 with St,sin θ,?d,τ,and w as input parameters,9 nodes,and 1 hidden layer was statistically significant.The root mean square error(RMSE),mean error(ME),and correlation coefficient(R)values were 1.433 kg/m^2 h,0.0195 kg/m^2 h,and 0.698 for the MLRmodel and 0.38 kg/m^2 h,0.151 kg/m^2 h,and 0.98 for the ANN model,respectively.These results show that the ANN model could better predict the SLR in comparison to the MLR model.The results also demonstrate that shear strength,among the strength parameters,had a greater impact on the SLR than compressive strengths(qu and CBR).Last but not the least,the reservoir sedimentationwas estimated for all methods and compared with the observed data.The results indicate that the ANN model is more appropriate for forecasting/simulating the sediment yield for a small watershed.