In order to improve the accuracy of water demand forecasting and expand the application of growth model in water demand forecasting, a combined growth water demand prediction model based on artificial ecosystem optimization(AEO)algorithm was proposed. Combined with an example, six standard test functions were selected to simulate AEO algorithm in different dimensions, and the simulation results were compared with those of Whale optimization algorithm(WOA), gray wolf optimization(GWO), teaching optimization(TLBO)algorithm and traditional particle swarm optimization(PSO). Based on the combination of three single growth models(Weibull, Richards, and Usher), Weibull-Richards-Usher, Weibull-Richards, Weibull-Usher and Richards-Usher were constructed. The AEO algorithm was used to optimize the parameters and weight coefficients of the four combined growth models. The AEO-Weibull-Richards-Usher, AEO-Weibull-Richards, AEO-Weibull-Usher, AEO-Richards-Usher water demand forecasting models were proposed and AEO-Weibull, AEO-Richards, AEO-Usher, AEO-SVM, AEO-BP models were constructed for comparison. Taking the water demand forecast of Shanghai as an example, the combined models were trained and predicted by using the statistical data of the first 30 groups and the last 8 groups. The results show that the optimization accuracy of AEO algorithm is better than that of WOA, GWO, TLBO and PSO algorithms in different dimensions, and has better optimization accuracy and global search ability. The average absolute relative error and the average absolute error of the four combined models are 0.94%-1.17% and 30 million -37 million m³, respectively. The prediction accuracy is better than the other five models such as AEO-Weibull. The results show that the AEO algorithm can effectively optimize the parameters and weight coefficients of the combined growth model, and the combined growth model based on AEO algorithm is feasible and effective for water demand prediction.