The use of artificial intelligence (AI) techniques in conjunction with electrocoagulation-flocculation (ECF) for the sustainable treatment of landfill leachate (LCH) was examined The research focuses on reducing critical pollutants, including biochemical oxygen demand (BOD), chemical oxygen demand (COD), and color. Experimental data were modeled and optimized using Response Surface Methodology (RSM) and Artificial Neural Networks (ANN). While RSM was effective in identifying key parameter interactions and optimal conditions, ANN exhibited higher predictive accuracy, with R2 values of 0.941, 0.9412, and 0.9723 for BOD, COD, and color reduction, respectively. The EC process, using aluminum electrodes, achieved notable pollutant reductions of up to 75.44% for BOD, 80.89% for COD, and 84.12% for color, closely aligning with the predicted values at an initial pH of 2.08, current density of 1.01 A, electrolysis time of 9.98 min, settling time of 30.34 min, and a temperature of 63.92 °C. Although this study primarily focused on integrating AI with ECF, the findings open opportunities for future incorporation of IoT technologies. IoT-enabled sensors could provide real-time monitoring and data acquisition for dynamic process optimization, further enhancing the efficiency and sustainability of ECF systems. By integrating EC with AI-driven tools, this study provided a reliable and efficient framework for improving pollutant removal and promoting environmentally sustainable water treatment solutions. The results highlighted the potential of AI-based optimization to enhance the design and performance of complex environmental processes.