The promise of implementing machine learning in earthquake engineering: A state-of-the-art review

Abstract

Machine learning (ML) has evolved rapidly over recent years with the promise to substantially alter and enhance the role of data science in a variety of disciplines. Compared with traditional approaches, ML offers advantages to handle complex problems, provide computational efficiency, propagate and treat uncertainties, and facilitate decision making. Also, the maturing of ML has led to significant advances in not only the main-stream artificial intelligence (AI) research but also other science and engineering fields, such as material science, bioengineering, construction management, and transportation engineering. This study conducts a comprehensive review of the progress and challenges of implementing ML in the earthquake engineering domain. A hierarchical attribute matrix is adopted to categorize the existing literature based on four traits identified in the field, such as ML method, topic area, data resource, and scale of analysis. The state-of-the-art review indicates to what extent ML has been applied in four topic areas of earthquake engineering, including seismic hazard analysis, system identification and damage detection, seismic fragility assessment, and structural control for earthquake mitigation. Moreover, research challenges and the associated future research needs are discussed, which include embracing the next generation of data sharing and sensor technologies, implementing more advanced ML techniques, and developing physics-guided ML models.

Encoding Time-Series Ground Motions as Images for Convolutional Neural Networks-Based Seismic Damage Evaluation

“…Traditional seismic fragility curves based on a scalar intensity measure (IM) have been widely used to generate fragility estimates in earthquake events (Hwang et al, 2001;Baker and Cornell, 2005;Cimellaro et al, 2010;Xu et al, 2020a). Although they are affected by geometry and material uncertainties, seismic fragility estimates are dominated by the earthquake uncertainty (Kwon and Elnashai, 2006;Padgett and DesRoches, 2007;Jalayer et al, 2014;Mangalathu et al, 2018;Xie et al, 2020). The traditional seismic fragility curves using one IM to propagate the primary earthquake uncertainty have several disadvantages.…”

Neural Networks and Imbalanced Learning for Data-Driven Scientific Computing With Uncertainties

“…In the remainder of this section, we review the current literature regarding the insertion of ML models into the field of seismic risk and reliability analysis of structures to reduce the cost of numerical simulations. In a recent review paper by [17], the authors provided a comprehensive survey of existing ML-based methods, including traditional learning algorithms and artificial neural networks (NNs). To mention the most relevant works, several papers [18]- [20] employed traditional learning algorithms, such as support vector machines, for predicting structural responses under uncertainties associated with ground motions.…”

Machine Learning Techniques for the Estimation of Limit State Thresholds and Bridge-Specific Fragility Analysis of R/C Bridges

“…Very recently [3], the potential exploitation of Artificial Intelligence algorithms and Machine Learning (ML) techniques in earthquake engineering, (i.e., seismic hazard analysis, system identification and damage detection, seismic fragility assessment, and structural control for earthquake mitigation) has been explored; it is still at a rather early stage, but a promising development. ML algorithms can be classified into supervised learning and unsupervised learning type.…”

“…Supervised learning uses prior knowledge of the labeled data set to learn a function that best approximates the relationship between input and labeled output in the data. In contrast, unsupervised learning aims to infer the natural structure from a set of data points that have no target labels [3].…”