Case-Based Reasoning for Estuarine Model Design

Sara Passone1, Paul W.H. Chung2, and Vahid Nassehi1

1Chemical Engineering Department, Loughborough University, Leicestershire, LEl 1 3TU
United Kingdom
{S.Passone, V.Nassehi}@Lboro.ac.uk
2Computer Science Department, Loughborough University, Leicestershire, LE1 1 3TU
United Kingdom
P.W.H.Chung@Lboro.ac.uk



Abstract. Estuaries are complex natural water systems. Their behaviour depend
on many factors, which are possible to analyse only by adopting different study
approaches. The physical processes within estuaries, such as floods and
pollutant dispersion, are generally investigated through computer modelling. In
this paper the application of case-based reasoning technology to support the
design of estuarine models is described. The system alms to provide a non-expert 
user in modelling with the necessary guidance for selecting a model that
matches his goal and the nature of the problem to be solved. The system is
based on three components: a case-based reasoning scheme, a genetic algorithm
and a library of numerical estuarine models. An example based on the Upper
Milford Haven estuary (UK) is used to demonstrate the efficacy of the systems
structure for supporting estuarmne model design.
References

1.	Dyer, K.R.: Estuaries a Physical Introduction. 2nd edn. John Wiley & Sons, New
York (1997)
2.	Kennish, M.J.: Ecology of Estuaries, Vol.1: Physical and chemical aspects. CRC
Press, Boca Raton, Florida, U.S.A. (1990)
3.	French, J. R., Clifford, N. J.: Hydrodynamic Modelling as a Basis for Explaining
Estuarine Environmental Dynamics: Some Computational and Methological
Issues. Hydrological Process 14 (2000) 2089-2108
4.	OKane, J.P.: Conflicting Views of the Role of Models. In: Wilson, J.G., Halcrow,
W. (eds): Estuarine Management and Quality Assessment. Plenum Press, New
York London (1985)
5.	Dyke, P.: Modelling Marine Processes. Prentice Hall, London (1996)
6.	Goldberg, D.E.: Genetic Algorithm in Search, Optimization, and Machine
Learning. Addison-Wesley Publishing Company, Massachusetts, U.S.A. (1989)
7.	Ramsey, C., Grefensttete, J.: Case-Based Initialization of Genetic Algorithms. In:
Forrest, S., (eds.): Proceedings of the Fifth International Conference on Genetic
Algorithms. Morgan Kauffman, San Mateo (1993) 84-91
8.	Davidson, N.C., DA Laffoley, D., Doody, J.P., Way, L.S., Gordon, J., Key, R.,
Pienkoski, M.W.,Mitchell, R., Duff, K.: Nature Conservation and Estuaries in
Great Britain, Nature Conservancy, Peterborough, UK (1991)
9.	Chung P.W.H. and Inder R.: Handling Uncertainty in Accessing Petroleum
Exploration Data. Revue de LInstitut Francais du Petrole, 47 (1992) 305-314
10.Bikangaga, J.H., Nassehi, V.: Application of Computer Modelling Techniques to
the Determination of Optimum Effluent Discharge Policies in Tidal Water
Systems. Water Resources 10 (1995) 2367-2375
11. 	Hinwood J.B., Wallis, I.G.: Classification of Models of Tidal Waters. Journal of
the Hydraulics Division, Proc. A.S.C.E. 101 (1975) HYl0 1315-1351.
12.	Lawson J., Gunn, I.J.: Guidelines for the Use of Computational Model in Coastal
and Estuarial Studies. Report SR 450, HR Wallingford, Oxon, UK (1996)
13.	Jeng, B.C., Liang, T.P.: Fuzzy Indexing and Retrieval in Case-Based Systems.
Expert Systems With Applications, 8 (1995) 135-142
14.	Louis, S.J., Johnson, J.: Solving Similar Problems Using Genetic Algorithms and
Case-Base Memory. Proceeding or the Seventh International conference on
Genetic Algorithms. Morgan Kauffman, San Mateo (1997) 101-127.
15.	Babovic, V., Abbott, M.B.: The Evolution of Equations from Hydraulic Data, I.
Theory. Journal of Hydraulic Research 3 (1997) 397-410
