• Intelligent prediction models of carbonation depth of fly ash concrete are developed based on machine learning techniques. • Binder content, fly-ash replacement level, water-to-binder ratio, CO 2 concentration, relative humidity and time of exposure are considered as effective influenced factors for carbonation depth. • Support vector regression combined with chicken swarm optimization algorithms achieved the best comprehensive prediction results. Carbonation is one of the utmost serious issues affecting the long-term durability of reinforced concrete. When H 2 O is present, a reaction between CO 2 gas and Ca(OH) 2 occurs, forming powdered CaCO 3 , which affects the microstructure of the concrete by lowering the pH level and causing corrosion, shortening the structure's service life. The complexity of the interaction between important parameters is difficult to capture for conventional carbonation prediction models. As a result, implementing powerful machine learning (ML) algorithms to overcome a lack of understanding of the consequences of such governing input parameters is critical. ML-based carbonation prediction models that blend four metaheuristic algorithms with Support Vector Regression (SVR) were developed to increase the accuracy and methodology of the prediction. 300 datasets from previous researches were used to develop, train, and test the SVR model. For the estimate of carbonation depth using experimental data, the possible hybrid SVR, which is made up of a Chicken Swarm Optimization (CSO), Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and Seagull Optimization Algorithm (SOA), was used. The modelling accuracy was verified using four distinct performance indexes: Coefficient of determination (R2), Mean Square Error (MSE), Mean Absolute Error (MAE), and Variance Accounted For (VAF). The training and test sets of AI models (CSO-SVR, GWO-SVR, PSO-SVR, and SOA-SVR) exhibit a strong correlation (R2 > 0.95) between the actual and predicted carbonation depth values. The application of this model for numerical research on the parameters affecting the carbonation depth in fly-ash concrete is successful, according to this study, and it gives scientific direction for durability design.