data-driven surrogate models have gained increasing attention in structural engineering for their ability to approximate complex system responses efficiently. this review article examines the application of surrogate models in structural engineering, highlighting the various models and their domains of use. the study analyzes 91 journal articles published from 2003 onwards, focusing on data-driven surrogate modeling techniques. the results show that these models offer significant benefits due to their flexible computational methods that produce accurate outcomes. however, there are still significant research gaps in the existing literature that require further investigation. the article aims to provide recommendations for practitioners in selecting appropriate surrogate models and to highlight the current state-of-the-art in this area. the review covers various surrogate models such as polynomial chaos expansions, genetic programming, bayesian networks, multivariate adaptive regression splines, response surface models, support vector regression, artificial neural networks, and others. the study also discusses the challenges in selecting the appropriate model and the need for more comprehensive research in this field. overall, the review emphasizes the importance of data-driven surrogate models in structural engineering and their potential to improve the efficiency and accuracy of engineering calculations.data-driven surrogate models have gained increasing attention in structural engineering for their ability to approximate complex system responses efficiently. this review article examines the application of surrogate models in structural engineering, highlighting the various models and their domains of use. the study analyzes 91 journal articles published from 2003 onwards, focusing on data-driven surrogate modeling techniques. the results show that these models offer significant benefits due to their flexible computational methods that produce accurate outcomes. however, there are still significant research gaps in the existing literature that require further investigation. the article aims to provide recommendations for practitioners in selecting appropriate surrogate models and to highlight the current state-of-the-art in this area. the review covers various surrogate models such as polynomial chaos expansions, genetic programming, bayesian networks, multivariate adaptive regression splines, response surface models, support vector regression, artificial neural networks, and others. the study also discusses the challenges in selecting the appropriate model and the need for more comprehensive research in this field. overall, the review emphasizes the importance of data-driven surrogate models in structural engineering and their potential to improve the efficiency and accuracy of engineering calculations.