Runoff Simulation Using Artificial Intelligent Techniques

In order to improve the computational accuracy for runoff simulation, an artificial intelligent technique, improved chaos genetic algorithm (ICGA) is proposed, in which initial population are generated by chaos mapping and searching range is automatically renewed with the excellent individuals obtained by ICGA. Its global convergence is analyzed. Its efficiency is verified by application of runoff simulation for three rainfall events. Compared with standard binary-encoded genetic algorithm (SGA), chaos genetic algorithm (CGA), ICGA has higher precision and rapider convergent speed. It is good for the global optimization in the practical runoff simulation.