Topic: Machine Learning in Earthquake Engineering

Researchers and practitioners in the earthquake engineering community have been exploring machine learning (ML) as a viable tool along a rapidly increasing research frontier, primarily to improve efficiency and accuracy of predictive models and tackle previously intractable problems. However, the exponential growth of efforts in this area is hampered by numerous challenges, such as data quality and interpretability. This Special Issue presents the state-of-art in the development and applications of ML in earthquake engineering, and is aimed at bringing forth exemplary works that will highlight the potential benefits, challenges, and limitations of ML-based approaches. Relevant topics include, but are not limited to:

• Ground motion prediction, classification, and generation;

• Probabilistic seismic hazard analysis;

• Soil liquefaction;

• Soil-structure interaction;

• Earthquake damage detection and classification;

• Structural health monitoring under seismic loading;

• Surrogate modeling;

• Seismic capacity prediction;

• Seismic fragility and risk assessment;

• Regional seismic risk and resilience assessment;

• Earthquake mitigation through smart materials, devices, and designs;

• Uncertainty quantification and propagation;

• ML and physics-based hybrid approaches.