Hydrology and Earth System Sciences
www.hydrol-earth-syst-sci.net
1027-5606
1607-7938
11
6
2007
10.5194/hess-11-1869-2007
http://www.hydrol-earth-syst-sci.net/11/1869/2007/
http://www.hydrol-earth-syst-sci.net/11/1869/2007/hess-11-1869-2007.html
http://www.hydrol-earth-syst-sci.net/11/1869/2007/hess-11-1869-2007.pdf
1869
1881
2007-12-04
Hydrological model coupling with ANNs
R. G. Kamp
robert.kamp@mx-groep.nl
H. H. G. Savenije
Section of Water Resources, Delft University of Technology, Delft, The Netherlands
MX. Systems B.V., Rijswijk, The Netherlands
There is an increasing need for model coupling. However, model coupling is
complicated. Scientists develop and improve models to represent physical
processes occurring in nature. These models are built in different software
programs required to run the model. A software program or application
represents part of the system knowledge. This knowledge is however
encapsulated in the program and often difficult to access.
<br><br>
In integrated water resources management it is often necessary to connect
hydrological, hydraulic or ecological models. Model coupling can in practice
be difficult for many reasons related to data formats, compatibility of
scales, ability to modify source codes, etc. Hence, there is a need for an
efficient and cost effective approach to model-coupling. Artificial neural
networks (ANNs) can be used as an alternative to replace a model and simulate
the model's output and connect it to other models.
<br><br>
In this paper, we investigate an alternative to traditional model coupling
techniques. ANNs are four different models: a rainfall runoff model, a river
channel routing model, an estuarine salt intrusion model, and an ecological
model. The output results of each model is simulated by a neural network that
is trained on corresponding input and output data sets. The models are
connected in cascade and their input and output variables are connected.
<br><br>
To test the results of the coupled neural network also a coupled system of
four sub-system models has been set-up. These results have been compared to
the results of the coupled neural networks. The results show that it is
possible to train neural networks and connect these models. The results of
the salt intrusion model was however not very accurate. It was difficult for
the neural network to represent both short term (tidal) and long term
(hydrological) processes.
Blom, G.: Licht onder water, Het belang van extinctiemetingen, LU Wageningen, Vakgroep Waterkwaliteitsbeheer en Aquatische Oecologie, Wageningen, 1992.
Babovic, V. and Abbott, M. B.: The evolution of equations from hydraulic data: Part I –Theory, J Hydraul. Res., 35(3), 1–14, 1997.
Campolo, M., Andreussi, P., and Soldati, A.: River flood forecasting with a neural network model, Water Resources Research, 35(4), 1191-1197, 1999.
Dibike, Y. B.: Model Induction from Data: Towards the next generation of computational engines in hydraulics and hydrology, IHE Delft, Delft, 2002.
Doan, C. D., Liong, S. Y., and Karunasinghe, D. S. K.: Derivation of effective and efficient data set with subtractive clustering method and genetic algorithm, J. Hydroinform., 7, 219–233, 2005.
Fenicia, F., Savenije, H. H. G., Matgen, P., and Pfister, L.: A comparison of alternative multiobjective calibration strategies for hydrological modeling, Water Resour. Res., 43, W03434, doi:10.1029/2006WR005098.
Hagan, T., Demuth, H. B., and Beale, M. H.: Neural Network Design, PWS Pub. Co., Boston, 1996.
Haykin, S.: Neural Networks, a comprehensive foundation, Prentice Hall, New Jersey, 1999.
Hunkins, K.: Salt dispersion in the Hudson Estuary, J. Phys. Oceanogr., 11(5), 729–738, 1981.
Kamp, R. G. and Savenije, H. H. G.: Optimising training data for ANNs with Genetic Algorithms, Hydrol. Earth Syst. Sci., 10, 603–608, 2006.
Koudstaal, R., Rijsberman, F. R., and Savenije, H. H. G.: Water and Sustainable Development, Natural Resources Forum, 16, 4, 277–290, 1992.
Lindström, G., Johansson, B., Persson, M., Gardelin, M., and Bergström, S.: Development and test of the distributed HBV-96 hydrological model, J Hydrol., 201, 272–288.
Minns, A. W. and Hall, M. J.: Artificial neural networks as rainfall-runoff models, Hydrolog. Sci. J., 41, 3, 399–417, 1996.
Pfister, L., Wagner, C., Vansuypeene, E., Drogue, G., and Hoffmann, L.: Atlas climatique du Grand-Duche de Luxembourg, Johnen-druck GmbH Co, Bernkastel-Kues, 2005.
Price, R. K., Samedov, J. N., and Solomatine, D. P.: An artificial neural network model of a generalised channel network, Proc. of 3rd Int. conf. on Hydroinformatics, Copenhagen, 1998.
Savenije, H. H. G.: Salt intrusion model for High Water Slack, Low Water Slack and Mean tide, on spreadsheet, J Hydrol., 85, 87–109, 1989.
Savenije, H. H. G.: Hatsi-kD, Voortplanting van hoogwatergolven in rivieren, Stromingen, 7(4), 45–47, 2001.
Savenije, H. H. G.: Predictive model for salt intrusion in estuaries, J Hydrol., 148, 203–218, 1993b.
Savenije, H. H. G.: Salinity and Tides in Alluvial Estuaries, 208, Elsevier, 2005.
Shrestha, R. G., Theobald, S., and Nestmann, F.: Simulation of flood flow in a river system using artificial neural networks, Hydrol. Earth Syst. Sci., 9, 313–321, 2005.
Stowa: Duflow Reference Manual, Stowa, version 3.3, 7–10, 2002.
Uncles, R. J., Bale, A. J., Howland, R. J. M., Morris, A. W., and Elliott, R. C. A.: Salinity in surface water in partially-mixed estuary, and its dispersion at low run-off, J. Phys. Oceanogr., 11(5), 729–738, 1981.
Vos, N. J. de and Rientjes, T. H. M.: Constraints of artificial neural networks for rainfall-runoff modeling: trade-offs in hydrological state representation and model evaluation, Hydrol. Earth Syst. Sci., 9, 111–126, 2005.
Zijderveld, A.: Neural network design strategies and modeling in hydroinformatics, Ph.D. thesis, Delft University of Technology, Delft, 2003.