Soil liquefaction is a major contributor to earthquake damage. Evaluating the potential for liquefaction by conventional experimental or empirical methods is both time-intensive and laborious. Utilizing a machine learning model capable of precisely forecasting liquefaction potential might diminish the time, effort, and expenses involved. This research introduces an innovative predictive model created in three phases. Initially, correlation analysis determines essential elements affecting liquefaction. Secondly, predictions are produced using Convolutional Neural Networks (CNN) and Deep Belief Networks (DBN), verified by K-fold cross-validation to guarantee resilience. Third, Ant Colony Optimization (ACO) improves outcomes by increasing convergence efficiency and circumventing local minima. The suggested EC + ACO model substantially surpassed leading approaches, such as SVM-GWO, RF-GWO, and Ensemble Classifier-GA, attaining a very low False Negative Rate (FNR) of 2.00 % when trained on 90 % of the data. A thorough performance evaluation shown that the model achieved a cost value of 1.133 % by the 40th iteration, exceeding the performance of other models such SVMGWO (1.412 %), RF-GWO (1.305 %), and Biogeography Optimized-Based ANFIS (1.7439 %). The model exhibited significant improvements in convergence behavior, with a steady decline in cost values, especially between the 20th and 50th iterations. Additional validation using empirical data from the Tohoku-oki, Great East Japan earthquake substantiated the EC + ACO model's enhanced accuracy and dependability in mirroring observed results. These findings underscore the model's resilience and efficacy, providing a dependable method for forecasting soil liquefaction and mitigating its seismic effects.