Evaluation of Neural Network Streamflow Forecasting on 47 Watersheds
Authors:
- 1 January 2005
- journal article
- Published by American Society of Civil Engineers (ASCE) in Journal of Hydrologic Engineering
- Vol. 10 (1) , 85-88
Abstract
This study is designed to compare 1 day ahead streamflow forecasting performance of multiple-layer perceptron (MLP) networks implemented at a daily time step for 47 watersheds spread across France and Central United States. In order to keep the task to manageable proportions, a large sample of test watersheds asks for a reduction of the number of steps in the network implementation procedure. This is achieved by eliminating the long trial and error process of input selection. Results show that it is feasible to obtain good 1 day ahead streamflow forecasting performance from simple MLPs and input vectors consisting solely of the last observed streamflow and a predetermined range of precipitation observations that is roughly equal to the time of concentration of the watersheds. Also, intuitive preprocessing such as differencing the streamflow noticeably improves the forecasting performance in almost all instances. On the other hand, consideration of the potential evapotranspiration as an additional input de...Keywords
This publication has 23 references indexed in Scilit:
- Impact of the length of observed records on the performance of ANN and of conceptual parsimonious rainfall-runoff forecasting modelsEnvironmental Modelling & Software, 2004
- A soil moisture index as an auxiliary ANN input for stream flow forecastingJournal of Hydrology, 2004
- Performance of Neural Networks in Daily Streamflow ForecastingJournal of Hydrologic Engineering, 2002
- Multivariate Reservoir Inflow Forecasting Using Temporal Neural NetworksJournal of Hydrologic Engineering, 2001
- Hydrological modelling using artificial neural networksProgress in Physical Geography: Earth and Environment, 2001
- Artificial Neural Networks in Hydrology. I: Preliminary ConceptsJournal of Hydrologic Engineering, 2000
- Artificial Neural Networks in Hydrology. II: Hydrologic ApplicationsJournal of Hydrologic Engineering, 2000
- River flood forecasting with a neural network modelWater Resources Research, 1999
- A comparison between neural-network forecasting techniques-case study: river flow forecastingIEEE Transactions on Neural Networks, 1999
- Prévision hydrologique par réseaux de neurones artificiels : état de l'artCanadian Journal of Civil Engineering, 1999