Abstract:
The complexity of rainfall-runoff-sediment yield hy
drological processes remains a
challenge for runoff and sediment yield prediction
for large mountainous watersheds. In
this study, a simple Non-Linear Dynamic (NLD) model
has been employed for predicting
daily runoff and sediment yield by considering the
watershed memory based rainfall and
runoff, and rainfall-runoff and sediment yield, res
pectively. The results were compared
with two commonly used Artificial Neural Network (A
NN) and Wavelet based ANN
(WNN) models by taking maximum input parameters of
values of time memory for
rainfall, runoff, and sediment yield derived from t
he developed NLD model through step-
wise regression. The feed forward ANN models with b
ack propagation algorithm was
used. Twenty-six years’ daily rainfall, runoff, and
sediment yield data of Bino Watershed,
Uttarakhand, were used in this study. The coefficie
nt of determination, root mean square
error, and model efficiency were adopted to evaluat
e the model’s performance. The
results revealed a better performance by the ANN an
d WNN rainfall-runoff models
compared to the NLD, however, NLD rainfall-runoff-s
ediment model showed higher
efficiency than the ANN and WNN models in case of c
onsidering whole time series
data. Under-prediction of sediment yield by all the
models resulted from sudden
landslides/flash floods in Himalayan W
atersheds. The study showed that though WNN
was better than ANN and NLD, its application cannot
be generalized for entire
mountainous watersheds. Again, criteria for success
ful selection of a useful sub-
component in WNN need to be developed. The study al
so indicates the greater capturing
power of WNN for simulation of extreme flows with l
owest percent-error-peak-flow
values.
Keywords
: Dynamic, Mountainous watershed, Neural networks,
Peak flow, Time lag.
