Sediment concentration prediction at Gangotri in the Himalayas using Artificial Neural Networks

Abstract

The present study explores for the first time, the possibility of modelling sediment concentration with Artificial Neural Networks at the source of Bhagirathi River in the Himalayas. Considering discharge, rainfall and temperature to be the main controlling factors of sediment concentration in the study area, seven ANN models using Feed Forward Back Propagation algorithm with different inputs have been created, trained and tested for prediction of sediment concentration. The inputs applied in the models are either the variables mentioned above as independent factors or a combination of them. Daily data of discharge, rainfall, temperature and sediment concentration for the melt period of May-October from the year 2000 to 2004, when maximum sediment movement takes place, has been used for modelling and a maximum Correlation Coefficient value of 0. 89 has been obtained between observed and ANN predicted values of sediment concentration. The study has brought out that in the study area, where anthropogenic factors are minimal; discharge and rainfall taken together play a more significant role in affecting sediment concentration. Overall, ANNs perform better when multiple inputs are employed rather than single input.