The reported study was undertaken in a small agricultural watershed, namely, Kapgari in Eastern I... more The reported study was undertaken in a small agricultural watershed, namely, Kapgari in Eastern India having a drainage area of 973 ha. The watershed was subdivided into three sub-watersheds on the basis of drainage network and land topography. An attempt was made to relate the continuously monitored runoff data from the sub-watersheds and the whole-watershed with the rainfall and temperature data using the artificial neural network (ANN) technique. The reported study also evaluated the bias in the prediction of daily runoff with shorter length of training data set using different resampling techniques with the ANN modeling. A 10-fold cross-validation (CV) technique was used to find the optimum number of hidden neurons in the hidden layer and to avoid neural network over-fitting during the training process for shorter length of data. The results illustrated that the ANN models developed with shorter length of training data set avoid neural network over-fitting during the training process, using a 10-fold CV method. Moreover, the biasness was also investigated using the bootstrap resampling technique based ANN (BANN) for short length of training data set. In comparison with the 10-fold CV technique, the BANN is more efficient in solving the problems of the over-fitting and under-fitting during training of models for shorter length of data set.
International Journal of Earth Sciences and Engineering , Oct 2011
Land and water are the two most vital natural resources of the world and these resources must be ... more Land and water are the two most vital natural resources of the world and these resources must be conserved and maintained carefully for environmental protection and ecological balance. Estimation of sediment yield is prerequisite for conservation and management of water resources and for many hydrological applications. Therefore, this study was undertaken for a small agricultural watershed, Kapgari having a drainage area of 973 ha for prediction of daily sediment yield. Artificial neural network (ANN) models were developed, to predict sediment yield on a daily basis for the watershed. A total of four ANN models were developed using rainfall and temperature data for predicting
sediment yield for Kapgari watershed and its three subwatersheds. Due to smaller data set availability a10fold cross validation method was used for selecting the best performing models and to avoid neural network overfitting during the training process. As a result models considering both rainfall and temperature as inputs performed better than those considering rainfall alone as input. Training and testing results of selected models show that models were predicting the daily sediment yield satisfactorily. Therefore these models can be used for estimating the sediment yield on a daily basis for Kapgari watershed and its subwatersheds.
The reported study was undertaken in a small agricultural watershed, namely, Kapgari in Eastern I... more The reported study was undertaken in a small agricultural watershed, namely, Kapgari in Eastern India having a drainage area of 973 ha. The watershed was subdivided into three sub-watersheds on the basis of drainage network and land topography. An attempt was made to relate the continuously monitored runoff data from the sub-watersheds and the whole-watershed with the rainfall and temperature data using the artificial neural network (ANN) technique. The reported study also evaluated the bias in the prediction of daily runoff with shorter length of training data set using different resampling techniques with the ANN modeling. A 10-fold cross-validation (CV) technique was used to find the optimum number of hidden neurons in the hidden layer and to avoid neural network over-fitting during the training process for shorter length of data. The results illustrated that the ANN models developed with shorter length of training data set avoid neural network over-fitting during the training process, using a 10-fold CV method. Moreover, the biasness was also investigated using the bootstrap resampling technique based ANN (BANN) for short length of training data set. In comparison with the 10-fold CV technique, the BANN is more efficient in solving the problems of the over-fitting and under-fitting during training of models for shorter length of data set.
International Journal of Earth Sciences and Engineering , Oct 2011
Land and water are the two most vital natural resources of the world and these resources must be ... more Land and water are the two most vital natural resources of the world and these resources must be conserved and maintained carefully for environmental protection and ecological balance. Estimation of sediment yield is prerequisite for conservation and management of water resources and for many hydrological applications. Therefore, this study was undertaken for a small agricultural watershed, Kapgari having a drainage area of 973 ha for prediction of daily sediment yield. Artificial neural network (ANN) models were developed, to predict sediment yield on a daily basis for the watershed. A total of four ANN models were developed using rainfall and temperature data for predicting
sediment yield for Kapgari watershed and its three subwatersheds. Due to smaller data set availability a10fold cross validation method was used for selecting the best performing models and to avoid neural network overfitting during the training process. As a result models considering both rainfall and temperature as inputs performed better than those considering rainfall alone as input. Training and testing results of selected models show that models were predicting the daily sediment yield satisfactorily. Therefore these models can be used for estimating the sediment yield on a daily basis for Kapgari watershed and its subwatersheds.
Uploads
sediment yield for Kapgari watershed and its three subwatersheds. Due to smaller data set availability a10fold cross validation method was used for selecting the best performing models and to avoid neural network overfitting during the training process. As a result models considering both rainfall and temperature as inputs performed better than those considering rainfall alone as input. Training and testing results of selected models show that models were predicting the daily sediment yield satisfactorily. Therefore these models can be used for estimating the sediment yield on a daily basis for Kapgari watershed and its subwatersheds.
sediment yield for Kapgari watershed and its three subwatersheds. Due to smaller data set availability a10fold cross validation method was used for selecting the best performing models and to avoid neural network overfitting during the training process. As a result models considering both rainfall and temperature as inputs performed better than those considering rainfall alone as input. Training and testing results of selected models show that models were predicting the daily sediment yield satisfactorily. Therefore these models can be used for estimating the sediment yield on a daily basis for Kapgari watershed and its subwatersheds.