About this Research Topic
With the accumulation of data from longstanding and new sources, the rapid growth in computational resources and data storage capacity and the recent development of advanced algorithms, artificial intelligence (AI, including machine learning and deep learning) is already broadly applied in many disciplines, e.g., computer vision. AI has been proven to be a formidable tool in addressing many traditionally challenging tasks, for instance, in automation, modelling and scientific discovery.
The modelling of the earthquake response of soil-structure systems (from the soil to the foundation and superstructure) is an active subfield of earthquake engineering. The modelling of earthquake response is an essential element of seismic risk analyses and requires the accurate characterization of site and structure responses, as well as soil-structure interactions. However, the dynamic responses of actual soil-structure systems are, in most cases, too complex to be accurately described by a set of differential equations. Thus, AI is gaining traction in the earthquake engineering community. Though promising results have been achieved, the application of AI in geotechnical and structural earthquake engineering is still in its infancy.
AI is certainly not a panacea and has its limitations. In some cases, we may have a small sample size, which poses challenges to developing robust data-driven models. Sometimes we have a sufficient number of instances that have a skewed distribution, e.g., a limited number of near-fault recordings from very large earthquakes. In some other applications, we need to deal with the paucity of gold-standard ground truth (for supervised learning), or noisy (especially for ground-motion recordings of small earthquakes), incomplete (e.g., sensor failure during devastating earthquakes), inhomogeneous (e.g., from different sources with different spatial-temporal resolutions) and uncertain data. Moreover, the multivariate, nonlinear and non-stationary nature of the seismic response of soil-structure systems further complicates the issue. In addition, the “black box” nature of some AI algorithms is among the obstacles prohibiting a more widespread adoption of AI in the community.
Can we overcome these limitations and harness the opportunities brought by AI? In this Research Topic, we cordially welcome submissions on the application of AI in geotechnical and structural earthquake engineering, especially those using novel approaches to address the data challenges, physical consistency, interpretability, generality and uncertainty of AI models.
Topics of interest include but are not limited to:
• The development of large and open benchmark datasets for AI, e.g., from well-constrained validated numerical simulations and experiments/observations;
• Soil characterization/site classification;
• Site-specific modelling of linear site response, soil nonlinearity, topographic and basin effects;
• Regional site-response mapping;
• Liquefaction assessment;
• Performance-based seismic design;
• Surrogate models for structural seismic analysis;
• Soil-structure interaction;
• Seismic fragility and vulnerability assessment of structures;
• Seismic structural health monitoring and early/rapid damage assessment;
• Interdependency of smart infrastructures.
Keywords: Artificial intelligence, Geotechnics, Structure, Earthquake, Benchmark dataset, Site response, Structural response, Performance-based design, Soil-structure interaction, Seismic fragility, Vulnerability assessment
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.