To efficiently and accurately estimate the model parameters of the soilcrop system under drip irrigation conditions, a genetic algorithm (GA) was integrated with the twodimensional soil water and crop growth simulation model (SWNCM-2D) to establish an optimization model for soil hydraulic parameters and crop growth parameters under drip irrigation conditions. The objective was to minimize the standard root-mean-square error (RMSE) between the measured and simulated soil water contents as well as crop dry matter quality. By utilizing observed data on soil water content, crop growth dynamics, and yield under drip irrigation treatment in southern Xinjiang, the soil hydraulic parameters and crop growth parameters were optimized by using the SWNCM-2D model coupled with GA. These optimized model parameters were then utilized to predict cotton yield and water productivity under various drip irrigation management scenarios. The results demonstrated that parameter optimization using the SWNCM-2D model coupled with GA yielded favorable outcomes. The RMSE, nRMSE and d values between simulated and measured soil water contents in different layers ranged from 0.0095cm3/cm3 to 0.0370cm3/cm3, 5% to 27%, and 0.6518 to 0.9642 respectively;while nRMSE for dry matter accumulation and LAI were within the range of 8%~17% and 6.2%~23.0%, d all exceeded 0.97 threshold value.Cotton lint yield was increased with the increase of irrigation levels while water productivity was decreased accordingly;lint yield was decreased as irrigation intervals lengthened whereas water productivity was initially increased before declining with longer intervals.In conclusion, simulations based on optimized parameters provided accurate representation of dynamic changes in soil moisture throughout the entire growth period along with precise depiction of crop development processes.Considering cotton yield alongside water productivity, the recommended irrigation regime for this region was a watering interval of 7 days at a rate of 120% ETc.