摘要
Accurate estimation of sediment load or transport rate is very important to a wide range of water resources projects. This study was undertaken to determine the most appropriate model to predict suspended load in the Chelehay Watershed, northeast of Iran. In total, 59 data series were collected from four gravel bed-rivers and a sand bed river and two depth integrating suspended load samplers to evaluate nine suspended load formulas and feed forward backpropagation Artificial Neural Network （ANN） structures. Although the Chang formula with higher correlation coefficient （r = 0.69） and lower Root Mean Square Error （RMSE = 0.013） is the best suspended load predictor among the nine studied formulas, the ANN models significantly outperform traditional suspended load formulas and show their superior performance for all statistical parameters. Among different ANN structures two models inclu- ding 4 inputs, 4 hidden and one output neurons, and 4 inputs, 4 and one hidden and one output neurons provide the best simulation with the RMSE values of 0.0009 and 0.001, respectively.
Accurate estimation of sediment load or transport rate is very important to a wide range of water resources projects. This study was undertaken to determine the most appropriate model to predict suspended load in the Chelehay Watershed, northeast of Iran. In total, 59 data series were collected from four gravel bed-rivers and a sand bed river and two depth integrating suspended load samplers to evaluate nine suspended load formulas and feed forward backpropagation Artificial Neural Network （ANN） structures. Although the Chang formula with higher correlation coefficient （r = 0.69） and lower Root Mean Square Error （RMSE = 0.013） is the best suspended load predictor among the nine studied formulas, the ANN models significantly outperform traditional suspended load formulas and show their superior performance for all statistical parameters. Among different ANN structures two models inclu- ding 4 inputs, 4 hidden and one output neurons, and 4 inputs, 4 and one hidden and one output neurons provide the best simulation with the RMSE values of 0.0009 and 0.001, respectively.
