Simulation of two-dimensional flow over flood plain by using artificial neural network | |
| Author | Wang Feixia |
| Call Number | AIT Thesis no.WM-01-06 |
| Subject(s) | Neural networks (Computer science) Hydrologic models Flood forecasting |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering |
| Publisher | Asian Institute of Technology |
| Abstract | Flood flow simulation models are now widely used but many of them require large amount of input data and their computations are complicated. With the development of computer science and modem technology, models are fast becoming attractive alternatives to provide accurate estimates of future water conditions effectively. One interested area in this emerging field of hydrological research is the application of Artificial Neural Network (ANN). Therefore, as the forecasting tool, ANN models are applied in this study to investigate the feasibility and capability of simulating flood flow. First, the simulation is carried out based on a hypothetical floodplain named ABCD floodplain in this study. MIKE 21 model is employed to compute the water levels and velocities of the ABCD floodplain, and then the MIKE 21 model result is used as a reference for comparison with the ANN model. By using the same boundary conditions, the ANN model is calibrated and verified using the computed water levels and velocities at various stations inside the floodplain. The ANN model is found to reproduce the results of MIKE 21 model very closely with very satisfactory performance. In the second stage of this study, the ANN model is applied to a real case, Klong Dam Irrigation Project Area located in southeast of Bangkok. Hydrological input data are the daily flood levels, rainfall, and pumping discharges in year 1995, 1996, and 2001. Water levels during flood period (August to November) at five water gates inside the project area are simulated and predicted by using ANN model. Very satisfactory results of simulation and forecasting based on past records are obtained in the Klong Darn floodplain area. Model sensitivity of ANN is analyzed to detect which parameters are critical to ANN model performance and what kind of effects they impose to the model. Recommendations for this research work are given based on the results from the two case studies of both the ABCD hypothetical floodplain and the Klong Darn Irrigation Project area. Compared to the hypothetical case study, it is rather difficult to simulate a real case due to a more complicated of irrigation channel networks, the floodplain, and pumping operations. Since time delay effect of rainfall to flow in floodplain and irrigation canals, a moving average technique is employed to pre-process the input rainfall data so that the optimal model output can be achieved. In addition, more investigation and data analysis are recommended for improving ANN model accuracy. |
| Year | 2002 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Civil and Infrastucture Engineering (DCIE) |
| Academic Program/FoS | Water Engineering and Management (WM) |
| Chairperson(s) | Tawatchai Tingsanchali; |
| Examination Committee(s) | Luketina, David Andrew ;Mark, Ole ;Babel, M. S. ; |
| Scholarship Donor(s) | Government of People's Republic of China; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 2002 |