Application of Artificial Neural Networks for estimating index floods

Open access

Abstract

This article presents an application of Artificial Neural Networks (ANNs) and multiple regression models for estimating mean annual maximum discharge (index flood) at ungauged sites. Both approaches were tested for 145 small basins in Slovakia in areas ranging from 20 to 300 km2. Using the objective clustering method, the catchments were divided into ten homogeneous pooling groups; for each pooling group, mutually independent predictors (catchment characteristics) were selected for both models. The neural network was applied as a simple multilayer perceptron with one hidden layer and with a back propagation learning algorithm. Hyperbolic tangents were used as an activation function in the hidden layer. Estimating index floods by the multiple regression models were based on deriving relationships between the index floods and catchment predictors. The efficiencies of both approaches were tested by the Nash-Sutcliffe and a correlation coefficients. The results showed the comparative applicability of both models with slightly better results for the index floods achieved using the ANNs methodology.

Acreman M. C., Sinclair C. D. 1986: Classification of drainage basins according to their physical characteristics; an application for flood frequency analysis in Scotland. J. Hydrol., 84, 365-380.

Aqil M., Kita I., Yano A., Nishiyama S., 2007: A comparative study of artificial neural networks and neuro-fuzzy in continuous modeling of the daily and hourly behaviour of runoff. Journal of Hydrology, 337, 1-2, 22-34.

Anctil F., Michel C., Perrin C., Andreassian V., 2004: A soil moisture index as an auxiliary ANN input for stream flow forecasting. Journal of Hydrology, 286, 1-4, 155-167.

Ayalew L., Möller D. P. F., Reik G., 2007: Using Artificial Neural Networks (ANN) for Real Time Flood Forecasting: the Omo River Case in Southern Ethiopia. In Sum­mer Computer Simulation Conference: The Society for Modeling and Simulation International. San Diego, California, 2007.

Dalrymple T., 1960: Flood frequency analyses. US Geological Survey, Water Supply Paper, 1543-A.

Dawson C. W., Abrahart R. J., Shamseldin A. Y., Wilby R. L., 2006: Flood estimation at ungauged sites using artificial neural networks. Journal of Hydrology, 319, 1-4, 391-409.

Chatfield Ch., 1993: Neural networks: forecasting breakthrough or passing fad. In: Inter­national Journal Forecasting, 1-3.

Elshorbagy A., Simonovic S. P., 2000: Performance evaluation of artificial neural networks for runoff prediction. Journal of Hydrologic Engineering, ASCE 5, 4, 424-427.

FEH, 1999: Flood Estimation Handbook. Part 3. Statistical procedures for flood fre­quency estimation, IH Wallingford, 1999, 325 p.

Fernando D. A., Jayawardena A. W., 1998: Runoff forecasting using RBF networks with OLS algorithm. Journal of Hydrologic Engineering, ASCE 3, 3, 203-209.

Garcia A. L., Shigidi A., 2006: Using neural networks for parameter estimation in ground water. In: Journal of Hydrology, 318, 1-4, 215-231.

Hosking J. R. M., Wallis J. R., 1997: Regional frequency analysis: an approach based on L-moments. Cambridge University Press, Cambridge; New York; Oakleigh. 224 p. ISBN 0-521-43045-3.

Kohnová S., Szolgay J. 2002: Practical applicability of regional methods for design flood computation in Slovakia. In: Weingartner R., Sperafico M., eds.: Proceedings of International Conference on Flood Estimation, CHR Report II-17, Bern 2002, 529­539.

Kohnová S., Szolgay J., Solín Ľ., Hlavčová K., 2006: Regional methods for prediction in ungauged basins. Key Publishing, Ostrava, 113 p., ISBN 80-87071-02-6.

McCulloch W. S., Pitts W., 1943: A logical calculus of the ideas imminent in nervous activity. Bulletin and Mathematical Biophysics, 5, 115-133.

Meigh J. R., Farquharson F. A. K., Sutcliffe J. V., 1997: A world-wide comparison of regional flood estimation methods and climate. Hydrol. Sci. J., 42, 2, 225-244.

Moradkhani, Hamid, Kuo-lin Hsu, Hoshin, Gupta V., Sorooshian S., 2004: Improved streamflow forecasting using self-organizing radial basis function artificial neural networks. Journal of Hydrology, 295, 1-4, 246-262.

Pekár J., Pekárová P., Škoda P., Bačová-Mitková V., Holko L., Kostka Z., 2012: Historické povodne, regionalizácia a návrhové hodnoty N-ročných prietokov s krátkou dobou pozorovania v regióne Západných Tatier. Acta Hydrologica Slovaca, 13, 1, 153-164 (in Slovak).

Pekárová P., Svoboda A., Miklánek P., Škoda P., Halmová D., Pekár J., 2012: Estimating flash flood peak discharge in Gidra and Parná basin: case study for the 7-8 June 2011 flood. J. Hydrol. Hydromech., 60, 3, 206-216. doi:10.2478/v10098-012-0018-z.

Rumelhart D. E., Hinton G. E., Wiliams R. J., 1986: Learning representations by back-propagating errors. Nature, 323, 533-536.

Rumelhart D. E., McClelland J. L., the PDP Research Group, 1986: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 1: Founda­tions, Cambridge, MA: MIT Press.

Solín Ľ., 2008: Analysis of floods occurrence in Slovakia in the period 1996-2006. J. Hydrol. Hydromech., 56, 2, 95-115.

Rajurkar M. P., Kothyari U. C., Chaube U. C., 2004: Modeling of the daily rainfall-runoff relationship with artificial neural network. Journal of Hydrology, 285, 1-4, 96-113.

Taufer I., Drbek O., Seidl P., 2006: Artificial Neural Network - The Ground of a Theory and Application. In: CHEMagazin, XVI, 6, 31-33 (in Czech).

Tokar A. S., Markus M., 2000: Precipitation-runoff modeling using artificial neural net­works and conceptual models. Journal of Hydrologic Engineering, 5, 2, 156-161.

Volná E., 2002: Neural Networks 1: Diploma Thesis. Ostrava University, Philosophical Faculty, 85 p.

Zealand C. M., Burn D. H., Simonovic S. P., 1999: Short term stream flow forecasting using artificial neural networks. Journal of Hydrology, 214, 1-4, 32-48.

Zrinji Z., Burn D. H., 1994: Flood frequency analysis for ungauged sites using a region of influence approach. J. Hydrol., 153, 1-21.

Contributions to Geophysics and Geodesy

The Journal of Geophysical Institute of Slovak Academy of Sciences

Journal Information


CiteScore 2017: 0.36

SCImago Journal Rank (SJR) 2017: 0.199
Source Normalized Impact per Paper (SNIP) 2017: 0.216

Metrics

All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 231 230 19
PDF Downloads 97 96 9