Abstract
In mathematical simulation for flow prediction and water quality management, the inappropriate use of any model parameters, which cannot be directly acquired from measurements, may introduce large errors or result in numerical instability. In this paper, the use of a genetic algorithm for determining an appropriate combination of parameter values in flow and water quality modeling is presented. The percentage error of peak value, peak time, and total volume of flow and water quality constituents are important performance measures for model prediction. The parameter calibration is based on field data of tidal as well as water quality constituents collected over five year span from 1991 to 1995 in Pearl River. Another two-year records from 1996 to 1997 are utilized to verify these parameters. Sensitivity analysis on crossover probability, mutation probability, population size, and maximum number of generations is also performed to determine the most befitting algorithm parameters. The results demonstrate that the application of genetic algorithm is able to mimic the key features of the flow and water quality process and that the calibration of models is efficient and robust.
Similar content being viewed by others
References
Chau, K. W., Chen, W.: A Fifth Generation Numerical Modelling System in Coastal Zone. Applied Mathematical Modelling 25(10) (2001) 887–900
Chau, K. W, Jiang, Y. W.: 3D Numerical Model for Pearl River Estuary. Journal of Hydraulic Engineering, ASCE 127(1) (2001) 72–82
Chau, K. W., Jiang, Y. W.: Three-Dimensional Pollutant Transport Model for the Pearl River Estuary. Water Research 36(8) (2002) 2029–2039
Chau, K. W., Jin, H. S.: Eutrophication Model for a Coastal Bay in Hong Kong. Journal of Environmental Engineering ASCE 124(7) (1998) 628–638
Chau, K. W., Jin, H. S., Sin, Y. S.: A Finite Difference Model of Two-Dimensional Tidal Flow in Tolo Harbor, Hong Kong. Applied Mathematical Modelling 20(4) (1996) 321–328
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chau, K. (2002). Calibration of Flow and Water Quality Modeling Using Genetic Algorithm. In: McKay, B., Slaney, J. (eds) AI 2002: Advances in Artificial Intelligence. AI 2002. Lecture Notes in Computer Science(), vol 2557. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36187-1_69
Download citation
DOI: https://doi.org/10.1007/3-540-36187-1_69
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00197-3
Online ISBN: 978-3-540-36187-9
eBook Packages: Springer Book Archive