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.
Abstract.A research project is introduced in which a modelling system is being developed to quantify risks of extreme flooding in large river basins. In the system, computer models and modules are coupled to simulate the functional chain: hydrology -hydraulics -polder diversion -dyke failureflooding -damage estimate -risk assessment. In order to reduce uncertainty in flood frequency analyses, data sets are complimented with information from historical chronicles and artwork. Probable maximum precipitation and discharge are calculated to indicate upper bounds of meteorological and hydrological extremes. Uncertainty analysis is investigated for different degrees of model complexity and compared at different basin scales.
Detecting effects of mining on the hydrology 46 Interbasin diversions 46 Redistribution of flow 47 Additional studies 48 Summary 49 References cited 50 PLATE 1. Maps showing geology, average annual precipitation, concentration of dissolved solids in ground water, and data collection sites in the Price River basin, Utah (in pocket) FIGURES 1. Map showing location of Price River basin 2 2. Map showing seepage-study sites and quality of ground and surface water in the Mud Creek drainage basin, 1979-80 8 3. Graph showing relationship between the concentration of dissolved solids and discharge for selected streams in the Price River basin, 1980 water year 10 4. Map showing location of water-quality and core-sampling sites in the Scofield Reservoir area 12 5. Photographs of bed material, and graphs showing particle-size distribution for sites on Fish, Mud, and Soldier Creeks, 1979 16 6-11. Graphs showing: 6. Mineralogic composition of bed material at sites in the Soldier Creek area and Mud Creek drainage basin, 1976 and 1979 18 7. Relationship of relative lead-210 activity and depth of sediment in Scofield Reservoir, 1980 20 8. Vertical distribution of coal in sediment cores from Scofield Reservoir, 1980 21 9. Relationship of concentration of suspended sediment and water discharge during thunderstorm runoff at gaging station on Soldier Creek (site S59), July 19, 1979 22 10. Relationship of benthic-invertebrate diversity and particle size for selected sites, 1979 22 11. Range of benthic-invertebrate diversity index at selected sites, 1979-80 23 12. Recession hydrographs of selected springs and a well in the Beaver and Mud Creek drainages and the Soldier Creek area, 1980 26 13. Hydrographs of streams in the Soldier Creek area and separation of base flow from the Flagstaff Limestone and the Blackhhawk Formation, Castlegate Sandstone, and Price River and North Horn Formations 30 14. Graph showing relationship between the discharge of Soldier Creek and the concentration of dissolved chemical constituents in Soldier Creek and in ground water, 1979-80 32 15. Map showing geology, data-collection sites for ground water, and potentiometric surface for the Star Point Sandstone in the Mud Creek drainage basin,
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.