Metaheuristic Algorithms and Machine Learning for Next-Generation Structural Engineering

Recent advances in artificial intelligence and computational optimization are transforming structural engineering by enabling more efficient analysis, design, prediction, and decision-making. Metaheuristic algorithms, including evolutionary, swarm-based, and nature-inspired methods, have demonstrated significant potential for solving complex nonlinear, multi-objective, and computationally intensive structural engineering problems. At the same time, machine learning and deep learning techniques are increasingly being used for structural response prediction, damage detection, system identification, uncertainty assessment, and data-driven design. The integration of optimization and artificial intelligence provides new opportunities to develop intelligent, adaptive, and computationally efficient engineering methodologies. These developments are particularly relevant to seismic engineering, structural control, resilient infrastructure, and structural health monitoring, where conventional approaches may face limitations associated with computational cost, high-dimensional design spaces, and complex structural behavior.The goal of this Research Topic is to bring together recent developments in metaheuristic optimization, machine learning, and artificial intelligence for next-generation structural engineering. Despite substantial progress in individual optimization and data-driven techniques, important challenges remain in improving their robustness, interpretability, computational efficiency, generalization capability, and practical applicability to real-world structures. The Research Topic aims to address these challenges by promoting innovative optimization algorithms, hybrid AI–optimization frameworks, surrogate and predictive models, and intelligent computational methodologies. Particular emphasis will be placed on approaches that can improve structural performance, safety, resilience, sustainability, and decision-making under uncertainty. Contributions combining numerical simulations, experimental investigations, monitoring data, and real structural applications are especially encouraged. The topic also seeks to explore emerging directions such as physics-informed machine learning, digital twins, explainable AI, multi-objective optimization, and data-driven structural control.The Research Topic welcomes original research articles, review papers, methodological studies, and case studies addressing the application or development of metaheuristic algorithms and machine learning in structural engineering. Relevant themes include, but are not limited to:Metaheuristic, evolutionary, swarm-based, and nature-inspired optimization, Machine learning and deep learning for structural engineering, AI-driven structural design and multi-objective optimization, Predictive and surrogate modeling of structural response, Structural health monitoring, damage detection, and system identification, Structural control and vibration mitigation, Seismic analysis, optimization, and resilient structural design, Structural reliability, uncertainty quantification, and risk assessment, Digital twins and intelligent infrastructure, Physics-informed, explainable, and hybrid AI methods, Sustainable and computationally efficient structural optimization. Authors are encouraged to demonstrate the effectiveness and practical relevance of proposed methodologies through numerical, experimental, or real-world applications. Topic editors: Gebrail Bekdaş, Sinan Melih Nigdeli, Ümit Işıkdağ Source: https://www.frontiersin.org/research-topics/85332/metaheuristic-algorithms-and-machine-learning-for-next-generation-structural-engineering