B-spline neural networks for forecasting daily inflow to the Chukha reservoir | |
| Author | Dukpa, Nima |
| Call Number | AIT RSPR no.IM-99-02 |
| Subject(s) | Neural networks (Computer science) Chukha Reservoir Hydraulic measurements |
| Note | A research study submitted in partial fulfillment of the requirements for the degree of Master of Engineering, School of Advanced and Technologies |
| Publisher | Asian Institute of Technology |
| Series Statement | Research studies project report ; no. IM-99-02 |
| Abstract | This research work investigates the B-spline neural network approach to daily river flow forecasting. The model is built using combinations of univariate basis functions. The network's weights are computed through analytical method. This research work also investigates the forecasting ability of the B-spline networks in the long and short forecast horizon. In order to make an objective evaluation of the said networks, backpropagation network model for comparison purpose. Simulations are conducted using daily stream discharge and rainfall data to test the model for its forecasting ability. The model investigated here is found to give efficiency index greater than 90% in all three cases viz. lead time one day, two days and three days. The same data sets run on backpropagation give efficiency index of nearly 90%. |
| Year | 1999 |
| Corresponding Series Added Entry | Asian Institute of Technology. Research studies project report ; no. IM-99-02 |
| Type | Research Study Project Report (RSPR) |
| School | School of Advanced Technologies (SAT) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Huynh Ngoc Phien; |
| Examination Committee(s) | Hoang Le Tien;Aekavute Sujarae; |
| Scholarship Donor(s) | Royal Government of Bhutan; |
| Degree | Research studies project report (M.Sc.) - Asian Institute of Technology, 1999 |