Improving irrigation water quality management is a pivotal factor in enhancing the stability and productivity of agricultural systems, particularly when unconventional water resources such as treated wastewater are utilized. This study was conducted to determine the optimal hydrochemical parameters of irrigation water (including EC, Na⁺, SAR, Ca²⁺, and Mg²⁺) for maximizing the yield of forage corn (Zea mays L. SC 704). The research was implemented in three principal phases: (i) exploratory and statistical analysis of raw field data (45 observations); (ii) fitting and evaluation of three regression models (linear, interaction, and quadratic); and (iii) multi algorithm optimization employing genetic algorithm (GA), particle swarm optimization (PSO), and simulated annealing (SA). The results revealed that the regression model incorporating interaction effects among the parameters, which achieved the highest adjusted coefficient of determination (R²ₐⱼ = 0.9197) and the lowest error (RMSE = 0.338 ton.ha⁻¹), was selected as the superior model. In the optimization process, the PSO algorithm outperformed GA and SA, yielding a mean predicted yield of 30.064 ton.ha⁻¹, a success rate of 100%, and the highest stability. The optimal values proposed by the algorithms fell within a range that is practically achievable under field conditions. By integrating the weights extracted from the correlation matrix of the parameters in the optimum region with the values optimized by PSO, a blending ratio of 62% treated wastewater and 38% well water was established as the operational optimum. The findings of this research demonstrate that intelligent optimization of the qualitative composition of irrigation water can simultaneously promote the sustainable use of unconventional water resources, such as wastewater, and increase forage corn yield.