Abstract
A neural network is used to simulate folw and water levels in a sewer system. The calibration of th neural network is based on a few measured events and the network is validated against measureed events as well as flow simulated with the MOUSE model (Lindberg and Joergensen, 1986). The neural network is used to compute flow or water level at selected points in the sewer system, and to forecast the flow from a small residential area. The main advantages of the neural network are the build-in self calibration procedure and high speed performance, but the neural network cannot be used to extract knowledge of the runoff process. The neural network was found to simulate 150 times faster than e.g. the MOUSE model.
Original language | English |
---|---|
Title of host publication | NOVATECH 95 : 2nd International Conference on Innovative Technologies in Urban Storm Drainage |
Number of pages | 8 |
Publisher | GRAIE |
Publication date | 1995 |
Pages | 395-402 |
ISBN (Print) | 295093370X |
Publication status | Published - 1995 |
Event | International Conference on Innovative Technologies in Urban Storm Drainage - Lyon, France Duration: 30 May 1995 → 1 Jun 1995 Conference number: 2 |
Conference
Conference | International Conference on Innovative Technologies in Urban Storm Drainage |
---|---|
Number | 2 |
Country/Territory | France |
City | Lyon |
Period | 30/05/1995 → 01/06/1995 |
Keywords
- MOUSE model
- Runoff model
- Neural networks