Submission Deadline: 30 April 2026 View: 444 Submit to Special Issue
Assoc. Prof. Mohammadreza Vafaei
Email: vafaei@utm.my
Affiliation: Faculty of Civil Engineering, Universiti Teknologi Malaysia, 81310 Skudai, Malaysia
Research Interests: seismic design and retrofitting, vibration control, structural health monitoring
Dr. Danial Jahed Armaghani
Email: danial.jahedarmaghani@uts.edu.au
Affiliation: School of Civil and Environmental Engineering, University of Technology Sydney, Ultimo, NSW 2007, Australia
Research Interests: rock mechanics, concrete technology, tunnelling, artificial intelligence and optimization algorithms
Assoc. Prof. Sophia C Alih
Email: sophiacalih@utm.my
Affiliation: Faculty of Civil Engineering, Universiti Teknologi Malaysia, 81310 Skudai, Malaysia
Research Interests: seismic design and retrofitting, vibration control
Machine learning has emerged as a profoundly impactful and increasingly indispensable tool in earthquake engineering. Its ability to process vast, complex datasets, identify subtle patterns, and generate predictive models has led to significant advances across seismic hazard assessment, structural performance evaluation, and post-earthquake damage detection. While the field has made remarkable strides, particularly in areas like semi-automated damage assessment and the characterization of material properties, inherent challenges remain. These include the scarcity and imbalance of high-quality, labeled earthquake data, the imperative for greater model interpretability to foster trust among engineers, and the complexities of integrating fundamental physics into data-driven models for real-world structural systems. Looking ahead, the future of earthquake engineering will be increasingly shaped by ML innovations. Strategic investments in advanced data fusion techniques and the development of open-access, multimodal datasets are critical. Continued exploration of next-generation deep learning architectures, coupled with a dedicated focus on explainable AI and physics-informed machine learning, will be paramount for developing models that are not only accurate but also transparent, robust, and physically consistent. Furthermore, the integration of ML with smart structures and advanced materials will enable a new era of intelligent, self-monitoring infrastructure. Ultimately, the full realization of ML's transformative potential hinges on sustained interdisciplinary research, the establishment of robust data infrastructure, and a concerted effort towards international collaboration and the adaptation of regulatory frameworks. By addressing these challenges and capitalizing on these opportunities, machine learning stands to profoundly enhance global seismic resilience, contributing to safer communities and a more robust built environment.
The aim of this Special Issue is to foster collaboration and disseminate the latest breakthroughs in the application of ML in earthquake engineering, including but not limited to the following areas:
· Seismic Hazard Assessment and Ground Motion Prediction
· Structural Response Prediction and Performance Evaluation
· Earthquake Damage Detection and Post-Earthquake Assessment
· Material Property Prediction and Pre-Earthquake Design
· Earthquake Prediction and Forecasting
· Structural Health Monitoring under seismic actions
· Topology Optimization for Seismic Actions
Login
Register
Submit a Paper
Propose a Special lssue