Title :
Extracting a Set of Robust Pareto-Optimal Parameters for Hydrologic Models using NSGA-II and SCEM
Author :
Nazemi, Alireza ; Yao, Xin ; Chan, Andrew H.
Author_Institution :
Birmingham Univ., Birmingham
Abstract :
In this paper, we will present a heuristic method in order to combine the information about the parametric space of a conceptual hydrologic model from two different sources. On one hand, multi-objective evolutionary optimization algorithm NSGA-II is used to find a set of pareto optimal solutions. On the other hand, a Markov Chain Monte Carlo-based algorithm, i.e. Shuffled Complex Evolution Metropolis (SCEM) is used to highlight a set of parameters with higher posterior distribution. By covering the interval between the most crowded locations in the parametric space extracted by both algorithms, we will identify a set of pareto optimal solutions which is more robust than the initial non-dominated set extracted by only NSGA-II.
Keywords :
Markov processes; Monte Carlo methods; Pareto optimisation; evolutionary computation; hydrology; Markov chain Monte Carlo based algorithm; NSGA-II; SCEM; heuristic method; hydrologic models; multiobjective evolutionary optimization algorithm; parameter extraction; robust pareto-optimal parameters; shuffled complex evolution metropolis; Calibration; Civil engineering; Data mining; Electronic mail; Evolutionary computation; Pareto optimization; Predictive models; Response surface methodology; Robustness; Uncertainty;
Conference_Titel :
Evolutionary Computation, 2006. CEC 2006. IEEE Congress on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9487-9
DOI :
10.1109/CEC.2006.1688539