Derivation of Pareto front with genetic algorithm and neural network

It is common knowledge that the optimal values of the calibrated parameters of a rainfall-runoff model for one model response may not be the optimal v alues for another model response. Thus, it is highly desirable to derive a Pareto front or trade-off curve on which each point represents a set of opt imal values satisfying the desirable accuracy levels of each of the model r esponses. This paper presents a new genetic algorithm (GA) based calibratio n scheme, accelerated convergence GA (ACGA), which generates a limited numb er of points on the Pareto front. A neural network (NN) is then trained to compliment ACGA in the derivation of other desired points on the Pareto fro nt by mimicking the relationship between the ACGA-generated calibration par ameters and the model responses. The calibration scheme, ACGA, is linked wi th HydroWorks and tested on a catchment in Singapore, Results show that ACG A is more efficient and effective in deriving the Pareto, front compared to other established GA-based optimization techniques such as vector evaluate d GA, multiobjective GA, and nondominated sorting GA. Verification of the t rained NN forecaster indicates that the trained network reproduces ACGA gen erated points on the Pareto front accurately. Thus, ACGA-NN is a useful and reliable tool to generate additional points on the Pareto front.