Simulation of flood flow in a river system using artificial neural networks
Artificial neural networks (ANNs) provide a quick and flexible means of developing flood flow simulation models. An important criterion for the wider applicability of the ANNs is the ability to generalise the events outside the range of training data sets. With respect to flood flow simulation, the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2005-01-01
|
| Series: | Hydrology and Earth System Sciences |
| Online Access: | http://www.hydrol-earth-syst-sci.net/9/313/2005/hess-9-313-2005.pdf |
| _version_ | 1818013518006321152 |
|---|---|
| author | R. R. Shrestha R. R. Shrestha S. Theobald F. Nestmann |
| author_facet | R. R. Shrestha R. R. Shrestha S. Theobald F. Nestmann |
| author_sort | R. R. Shrestha |
| collection | DOAJ |
| description | Artificial neural networks (ANNs) provide a quick and flexible means of developing flood flow simulation models. An important criterion for the wider applicability of the ANNs is the ability to generalise the events outside the range of training data sets. With respect to flood flow simulation, the ability to extrapolate beyond the range of calibrated data sets is of crucial importance. This study explores methods for improving generalisation of the ANNs using three different flood events data sets from the Neckar River in Germany. An ANN-based model is formulated to simulate flows at certain locations in the river reach, based on the flows at upstream locations. Network training data sets consist of time series of flows from observation stations. Simulated flows from a one-dimensional hydrodynamic numerical model are integrated for network training and validation, at a river section where no measurements are available. Network structures with different activation functions are considered for improving generalisation. The training algorithm involved backpropagation with the Levenberg-Marquardt approximation. The ability of the trained networks to extrapolate is assessed using flow data beyond the range of the training data sets. The results of this study indicate that the ANN in a suitable configuration can extend forecasting capability to a certain extent beyond the range of calibrated data sets. |
| first_indexed | 2024-04-14T06:34:11Z |
| format | Article |
| id | doaj.art-ff0382f77d5a42f78129ea4e604d7386 |
| institution | Directory Open Access Journal |
| issn | 1027-5606 1607-7938 |
| language | English |
| last_indexed | 2024-04-14T06:34:11Z |
| publishDate | 2005-01-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Hydrology and Earth System Sciences |
| spelling | doaj.art-ff0382f77d5a42f78129ea4e604d73862022-12-22T02:07:32ZengCopernicus PublicationsHydrology and Earth System Sciences1027-56061607-79382005-01-0194313321Simulation of flood flow in a river system using artificial neural networksR. R. ShresthaR. R. ShresthaS. TheobaldF. NestmannArtificial neural networks (ANNs) provide a quick and flexible means of developing flood flow simulation models. An important criterion for the wider applicability of the ANNs is the ability to generalise the events outside the range of training data sets. With respect to flood flow simulation, the ability to extrapolate beyond the range of calibrated data sets is of crucial importance. This study explores methods for improving generalisation of the ANNs using three different flood events data sets from the Neckar River in Germany. An ANN-based model is formulated to simulate flows at certain locations in the river reach, based on the flows at upstream locations. Network training data sets consist of time series of flows from observation stations. Simulated flows from a one-dimensional hydrodynamic numerical model are integrated for network training and validation, at a river section where no measurements are available. Network structures with different activation functions are considered for improving generalisation. The training algorithm involved backpropagation with the Levenberg-Marquardt approximation. The ability of the trained networks to extrapolate is assessed using flow data beyond the range of the training data sets. The results of this study indicate that the ANN in a suitable configuration can extend forecasting capability to a certain extent beyond the range of calibrated data sets.http://www.hydrol-earth-syst-sci.net/9/313/2005/hess-9-313-2005.pdf |
| spellingShingle | R. R. Shrestha R. R. Shrestha S. Theobald F. Nestmann Simulation of flood flow in a river system using artificial neural networks Hydrology and Earth System Sciences |
| title | Simulation of flood flow in a river system using artificial neural networks |
| title_full | Simulation of flood flow in a river system using artificial neural networks |
| title_fullStr | Simulation of flood flow in a river system using artificial neural networks |
| title_full_unstemmed | Simulation of flood flow in a river system using artificial neural networks |
| title_short | Simulation of flood flow in a river system using artificial neural networks |
| title_sort | simulation of flood flow in a river system using artificial neural networks |
| url | http://www.hydrol-earth-syst-sci.net/9/313/2005/hess-9-313-2005.pdf |
| work_keys_str_mv | AT rrshrestha simulationoffloodflowinariversystemusingartificialneuralnetworks AT rrshrestha simulationoffloodflowinariversystemusingartificialneuralnetworks AT stheobald simulationoffloodflowinariversystemusingartificialneuralnetworks AT fnestmann simulationoffloodflowinariversystemusingartificialneuralnetworks |