Field Of Earthquake Engineering Research Articles

Advances and challenges in friction pendulum bearings for seismic isolation systems

Friction pendulum bearings (FPBs) have emerged as critical structural isolation devices in the field of earthquake engineering. Extensive research and development efforts have led to the exploration and refinement of these bearings, resulting in the creation of various models with unique structural configurations and superior mechanical properties. This paper offers an in-depth review of the friction materials employed in FPBs, alongside an analysis of the mechanical performance and advancements in research regarding single-pendulum, double-pendulum, multiple-pendulum, and other types of friction bearings. Characterized by their low sensitivity and high stability, these bearings are adept at resisting seismic forces, thus providing dependable isolation protection for structures. This review also includes a succinct examination of the seismic performance and engineering applications of these isolation structures. With robust self-centering capabilities, excellent isolation, and energy dissipation mechanisms, FPBs are capable of quickly resuming normal operations post-seismic events. This reduces structural damage and maintenance expenses, significantly improving the seismic resilience of structures. Moreover, the paper outlines the current challenges in the research and development of FPBs and suggests future research directions, including optimizing friction materials, enhancing the design and performance of isolation structures, and improving the seismic performance and engineering application efficiency of FPBs. By identifying underexplored areas and synthesizing findings differently, this review provides a comprehensive and novel perspective that advances the field of earthquake engineering.

Survival probability surfaces of hysteretic fractional order structures exposed to non-stationary code-compliant stochastic seismic excitation

A novel first-passage probability stochastic incremental dynamics analysis (SIDA) methodology tailored for hysteretic fractional order structural systems under a fully non-stationary seismic excitation vector consistently designated with contemporary aseismic codes provisions (e.g., Eurocode 8) is developed. Specifically, the vector of the imposed seismic excitations is characterised by evolutionary power spectra that stochastically align with aseismic codes elastic response acceleration spectra, defined for specified modal damping ratios and scaled ground accelerations. Leveraging the concepts of stochastic averaging and statistical linearization, the approximative non-stationary response displacement joint probability density function (PDF) is derived, retaining the particularly coveted attribute of computational efficacy. Subsequently, the coupling with the survival probability model allows for the efficient determination of the response first-passage time probability density surfaces and the survival probability surfaces across various limit-state rules and scalable intensity measures. The first-passage time probability serves as a robust engineering demand parameter, effectively monitoring structural behaviour by considering both intensity and timing information, while inherently aligned with pertinent limit-state requirements. Notably, the associated low computational cost and the ability to handle a wide range of complex nonlinear/hysteretic structural behaviours, coupled with its compliance with modern aseismic codes, underscore its potential for applications in the fields of structural and earthquake engineering. A nonlinear system endowed with fractional derivative elements is used to exemplify the method’s reliability. The accuracy of the proposed method is validated in a Monte Carlo-based context, conducting nonlinear response time–history analyses with an extensive ensemble of accelerograms compatible with Eurocode 8 response acceleration spectra.

Focal mechanics and disaster characteristics of the 2024 M 7.6 Noto Peninsula Earthquake, Japan

On January 1, 2024, a devastating M 7.6 earthquake struck the Noto Peninsula, Ishikawa Prefecture, Japan, resulting in significant casualties and property damage. Utilizing information from the first six days after the earthquake, this article analyzes the seismic source characteristics, disaster situation, and emergency response of this earthquake. The results show: 1) The earthquake rupture was of the thrust type, with aftershock distribution showing a north-east-oriented belt-like feature of 150 km. 2) Global Navigation Satellite System (GNSS) and Interferometric synthetic aperture radar (InSAR), observations detected significant westward to north-westward co-seismic displacement near the epicenter, with the maximum horizontal displacement reaching 1.2 m and the vertical uplift displacement reaching 4 m. A two-segment fault inversion model fits the observational data well. 3) Near the epicenter, large Peak Ground Velocity (PGV) and Peak Ground Acceleration (PGA) were observed, with the maxima reaching 145 cm/s and 2681 gal, respectively, and the intensity reached the highest level 7 on the Japanese (Japan Meteorological Agency, JMA) intensity standard, which is higher than level 10 of the United States Geological Survey (USGS) Modified Mercalli Intensity (MMI) standard. 4) The observation of the very rare multiple strong pulse-like ground motion (PLGM) waveform poses a topic worthy of research in the field of earthquake engineering. 5) As of January 7, the earthquake had left 128 deaths and 560 injuries in Ishikawa Prefecture, with 1305 buildings completely or partially destroyed, and had triggered a chain of disasters including tsunamis, fires, slope failures, and road damage. Finally, this paper summarizes the emergency rescue, information dissemination, and other disaster response and management measures taken in response to this earthquake. This work provides a reference case for carrying out effective responses, and offers lessons for handling similar events in the future.

Risk‐based student performance prediction model for engineering courses

AbstractHigh academic failure and dropout rates in engineering courses are significant worldwide concerns attributed to various factors, with academic performance being a critical variable. This article provides a methodology to estimate the performance risk of students in engineering schools. Risk analysis is a strategy to evaluate academic success, which provides a set of methods to analyze, understand, and predict student outcomes before enrolling in specific majors or challenging college courses. This article develops a methodology to estimate fragility curves for students entering an engineering course. The fragility function concept, borrowed from the earthquake engineering field, estimates the likelihood of success in a course, given relevant student metadata, such as the grade point average, thus comprehensively addressing student performance variability. A student academic success prediction model enables instructional designers to make informed decisions. For example, fragility curves can help achieve two goals: (i) assessing the population at risk for a course to take actions to improve student success rates and (ii) assessing a course's relative difficulty based on its fragility function parameters. We demonstrate this methodology through a case study comparing the relative difficulty of two engineering courses, Statics and Solid Mechanics, at a university in Colombia. Given that Statics serves as a prerequisite for Solid Mechanics, deficiencies in the former can significantly impact student performance in the latter. The case study results reveal that Solid Mechanics poses a higher risk of academic failure than Statics, underscoring the importance of a strong foundation in prerequisite courses.

Integrating post-event very high resolution SAR imagery and machine learning for building-level earthquake damage assessment

AbstractEarthquakes have devastating effects on densely urbanised regions, requiring rapid and extensive damage assessment to guide resource allocation and recovery efforts. Traditional damage assessment is time-consuming, resource-intensive, and faces challenges in covering vast affected areas, often limiting timely decision-making. Space-borne synthetic aperture radars (SAR) have gained attention for their all-weather and day-night imaging capabilities. These advantages, coupled with wide coverage, short revisits and very high resolution (VHR), have created opportunities for using SAR data in disaster response. However, most SAR studies for post-earthquake damage assessment rely on change detection methods using pre-event SAR images, which are often unavailable in operational scenarios. Limited studies using solely post-event SAR data primarily concentrate on city-block-level damage assessment, thus not fully exploiting the VHR SAR potential. This paper presents a novel method integrating solely post-event VHR SAR imagery and machine learning (ML) for regional-scale post-earthquake damage assessment at the individual building-level. We first used supervised learning on case-specific datasets, and then introduced a combined learning approach, incorporating inventories from multiple case studies to assess generalisation. Finally, the ML model was tested on unseen study areas, to evaluate its flexibility in unfamiliar contexts. The method was implemented using datasets collected during the Earthquake Engineering Field Investigation Team (EEFIT) reconnaissance missions following the 2021 Nippes earthquake and the 2023 Kahramanmaraş earthquake sequence. The results demonstrate the method’s ability to classify standing and collapsed buildings, achieving up to 72% overall accuracy on unseen regions. The proposed method has potential for future disaster assessments, thereby contributing to more effective earthquake management strategies.

An Efficient Algorithm to Identify Strong Pulse-Like Ground Motions Based on the Smoothed Significant Velocity Half-Cycles

ABSTRACT This study proposes a new algorithm based on the smoothed Significant Velocity Half-Cycles for efficient and accurate identification of pulse-like velocity ground motions. The empirical-mode decomposition (EMD) based algorithm is initially employed with providing some valuable insights into its failure. Next, a concept of riding waves is presented and two additional criteria are established. The proposed algorithm is demonstrated to successfully exclude the ambiguous records with insignificant pulse characteristics when compared with six benchmark identification methods. This article also provides a dataset of 325 strong pulse-like records identified from the NGA-West2 database, which is practical importance in earthquake engineering field.

Spectrum-consistent [formula omitted]-based fragility curves

In the field of earthquake engineering, Fragility Curves (FCs) have become indispensable for regional risk assessments due to their efficacy in estimating the failure probabilities of diverse structures, including buildings and bridges, based on certain intensity measures. FCs are typically derived from either mechanical simulations or on-site observations, encapsulating crucial information about local stratigraphy and topography. The dependency of FCs on these local parameters, such as soil and topographic conditions, may vary depending on the selected intensity measure. When a spectral ordinate at a specific period is used as an intensity measure, FCs tend to be largely site-independent. On the other hand, if the intensity measure is chosen to be the acceleration ag at the bedrock substrate, as often occurs, then the FC is site-dependent. This distinction implies that identical structures at different locations, or even the same location with different soil and topographic conditions, have different FCs. This can significantly influence the results of regional risk studies, as using FCs for a specific building type at diverse locations with different hazards, stratigraphy, and topography can result in significantly different failure probabilities. The goal of this study is to develop a method so that ag-based FCs, developed at a certain location, can be used at any other location and on any other soil, preserving consistency in terms of spectral ordinate. This is done by a fully analytical approach, using a spectrum-consistent transformation. As an application, risk maps for Italy are generated and compared with an alternative method based on shifting the hazard curve.

Time-Dependent Probabilistic Seismic Hazard Analysis for Seismic Sequences Based on Hybrid Renewal Process Models

ABSTRACT Probabilistic seismic hazard analysis (PSHA) is a methodology with a long history and has been widely implemented. However, in the conventional PSHA and sequence-based probabilistic seismic hazard analysis (SPSHA) approaches, the occurrence of mainshocks is modeled as the homogeneous Poisson process, which is unsuitable for large earthquakes. To account for the stationary occurrence of small-to-moderate (STM) mainshocks and the nonstationary behavior of large mainshocks, we propose a time-dependent sequence-based probabilistic seismic hazard analysis (TD-SPSHA) approach by combining the time-dependent mainshock probabilistic seismic hazard analysis (TD-PSHA) and aftershock probabilistic seismic hazard analysis, consisting of four components: (1) STM mainshocks, (2) aftershocks associated with STM mainshocks, (3) large mainshocks, and (4) aftershocks associated with large mainshocks. The approach incorporates an exponential-magnitude, exponential-time model for STM mainshocks, and a renewal-time, characteristic-magnitude model for large mainshocks to assess the time-dependent hazard for mainshocks. Then nonhomogeneous Poisson process is used to model the occurrence of associated aftershocks, in which the aftershock sequences can be modeled using the Reasenberg and Jones (RJ) model or the epidemic-type aftershock sequence (ETAS) model. To demonstrate the proposed TD-SPSHA approach, a representative site of the San Andreas fault is selected as a benchmark case, for which five time-dependent recurrence models, including normal, lognormal, gamma, Weibull, and Brownian passage time (BPT) distributions, are chosen to determine the occurrence of large mainshocks. Then sensitivity tests are presented to show the effects on TD-SPSHA, including (1) time-dependent recurrence models, (2) mainshock magnitude, (3) rupture distance, (4) aftershock duration, (5) escaped time since the last event, and (6) future time interval. Furthermore, the bimodal hybrid renewal model is utilized by TD-SPSHA for another case site. The comparison results illustrate that the sequence hazard analysis approach ignoring time-varying properties of large earthquakes for long periods and the effects of associated aftershocks will result in a significantly underestimated hazard. The TD-SPSHA-based hazard curves using the ETAS model are larger than those of the RJ model. The proposed TD-SPSHA approach may be of significant interest to the field of earthquake engineering, particularly in the context of structural design or seismic risk analysis for the long term.

Analysis of stress mechanism in a new prefabricated SRC composite column

The superior seismic performance of prefabricated steel-concrete composite structures has recently become a major research focus in the earthquake engineering field. This study proposes an off-site precast steel reinforced concrete (PSRC) column base joint. This joint has a high bearing capacity, efficient assembly, and a fuse function for plastic deformation accumulation at the middle connection. Besides, multiple finite element models are built and calibrated based on the test results using ABAQUS. The research discusses the influence of various parameters on failure modes and seismic performance. The results indicated that the failure position is primarily concentrated in the middle connection, whereas the stress distribution differs within the middle connection. The axial compression ratio and the middle connection position height significantly affect the initial stiffness. The bearing capacity is considerably influenced by various parameters, excluding the thickness of the stiffening plate and cover plate. It is recommended to use an optimal axial compression ratio of 0.45 and a shear span ratio between 2.0 and 2.8 while controlling the stiffening and cover plate thicknesses between 10 and 16 mm. The shear mechanism of the PSRC column base joint mainly includes a steel plate shear wall mechanism and a T-shaped steel frame mechanism. The simplified bearing capacity model results for the proposed PSRC column base joint match well with the experimental and FEM results, and the calculation results are good.

EDITORIAL SCOPE: GEOTECHNICAL EARTHQUAKE ENGINEERING EDITION

One of the main civil engineering disciplines is currently the focus area of the Journal of Civil Engineering, Science, and Technology (JCEST): geotechnical and earthquake engineering. We are honoured to present this editorial focusing on the dynamic and evolving field of geotechnical earthquake engineering, with an emphasis on seismic soil-structure interaction (SSI). These studies offer valuable insights into novel design methodologies, materials, and analysis approaches, which are crucial for ensuring the safety and resilience of infrastructure. This editorial paper collected information from the freely-accessible SCOPUS database to identify common keywords used in published papers pertaining to geotechnical earthquake engineering from 2015 to 2023. The analysis reveals that the ‘seismic’ and ‘structure’ terms are the most frequently utilised keyword in articles related to this field. As the editors of our esteemed journal, it is our privilege to shed light on this critical area of research that plays a pivotal role in ensuring the safety and resilience of civil infrastructure subjected to seismic forces.

MLPER: A Machine Learning-Based Prediction Model for Building Earthquake Response Using Ambient Vibration Measurements

Deep neural networks (DNNs) have gained prominence in addressing regression problems, offering versatile architectural designs that cater to various applications. In the field of earthquake engineering, seismic response prediction is a critical area of study. Simplified models such as single-degree-of-freedom (SDOF) and multi-degree-of-freedom (MDOF) systems have traditionally provided valuable insights into structural behavior, known for their computational efficiency facilitating faster simulations. However, these models have notable limitations in capturing the nuanced nonlinear behavior of structures and the spatial variability of ground motions. This study focuses on leveraging ambient vibration (AV) measurements of buildings, combined with earthquake (EQ) time-history data, to create a predictive model using a neural network (NN) in image format. The primary objective is to predict a specific building’s earthquake response accurately. The training dataset consists of 1197 MDOF 2D shear models, generating a total of 32,319 training samples. To evaluate the performance of the proposed model, termed MLPER (machine learning-based prediction of building structures’ earthquake response), several metrics are employed. These include the mean absolute percentage error (MAPE) and the mean deviation angle (MDA) for comparisons in the time domain. Additionally, we assess magnitude-squared coherence values and phase differences (Δφ) for comparisons in the frequency domain. This study underscores the potential of the MLPER as a reliable tool for predicting building earthquake responses, addressing the limitations of simplified models. By integrating AV measurements and EQ time-history data into a neural network framework, the MLPER offers a promising avenue for enhancing our understanding of structural behavior during seismic events, ultimately contributing to improved earthquake resilience in building design and engineering.

Structural Characteristics of the Earthquake-Prone Building Stock in Istanbul and Prioritization of Existing Buildings in Terms of Seismic Risk-A Pilot Project Conducted in Istanbul

ABSTRACT Earthquakes have caused catastrophic results in cities since the beginning of settled life, and the cumulative experience of these events has indicated that the lack of seismic resilience brings enormous economic losses and threatens human life. Consequently, the importance of seismic risk mitigation of earthquake-prone structures has arisen to reduce the primary and secondary losses resulting from seismic events in the last decades as developments in the earthquake engineering field occur. The first step for ensuring seismic resilience is the identification of risky buildings, which is a difficult challenge for metropolises like Istanbul since the building stock consists of over a million buildings. Applying code-based detailed assessments to so many buildings is not practical in terms of time and cost. Moreover, the current code-based detailed assessment methodologies such as Provisions for the Seismic Risk Evaluation of Existing Buildings under Urban Renewal Law (2019) and Turkish Building Earthquake Code (2018) provide discrete predictions for existing buildings as either risky or non-risky or satisfying life safety/controlled damage or not. However, a ranking system based on a reliable and realistic risk classification to prioritize the buildings is needed. Therefore, as a pilot project, nearly 23,000 reinforced concrete buildings in 37 different districts of Istanbul have been investigated by Istanbul Metropolitan Municipality (IMM) through PERA2019 performance-based rapid assessment methodology by considering the Design Level and Scenario-Based Earthquake cases. This is the most up-to-date and comprehensive site survey and analysis conducted in Istanbul up to now. In this paper, the characteristics of the building stock in Istanbul based on the conducted site work and the outcomes of the rapid seismic safety assessment efforts are summarized. Then, a discussion on the seismic risk evaluation of the existing residential buildings based on the prioritization of the examined buildings is presented through the results obtained for the Design Level and Scenario-Based Earthquake cases.

Combining remote sensing techniques and field surveys for post-earthquake reconnaissance missions

Remote reconnaissance missions are promising solutions for the assessment of earthquake-induced structural damage and cascading geological hazards. Space-borne remote sensing can complement in-field missions when safety and accessibility concerns limit post-earthquake operations on the ground. However, the implementation of remote sensing techniques in post-disaster missions is limited by the lack of methods that combine different techniques and integrate them with field survey data. This paper presents a new approach for rapid post-earthquake building damage assessment and landslide mapping, based on Synthetic Aperture Radar (SAR) data. The proposed texture-based building damage classification approach exploits very high resolution post-earthquake SAR data integrated with building survey data. For landslide mapping, a backscatter intensity-based landslide detection approach, which also includes the separation between landslides and flooded areas, is combined with optical-based manual inventories. The approach was implemented during the joint Structural Extreme Event Reconnaissance, GeoHazards International and Earthquake Engineering Field Investigation Team mission that followed the 2021 Haiti Earthquake and Tropical Cyclone Grace.

Earthquake data augmentation using wavelet transform for training deep learning based surrogate models of nonlinear structures

Machine learning methods have gained traction in the civil engineering community for analysis of civil infrastructures. A major field of application is in development of surrogate models for non-linear dynamic analysis for civil infrastructures. These data-driven models generally consist of a large number of parameters which need to be estimated from available data. However, due to limited availability of data in the field of earthquake engineering, often, it is difficult to develop stable models that can predict structural response by taking into account both material and earthquake uncertainty. To this end, the authors propose a discrete wavelet transform (DWT) enabled surrogate modeling framework for prediction of nonlinear structural response while accounting for material and earthquake uncertainty. DWT is used for earthquake data augmentation and feature extraction, which, along with constitutive material parameters, are used to train a deep neural network (DNN). It is shown that DWT can efficiently augment existing small earthquake datasets while the DNN can capture the non-linear structural response. The framework is validated by applying it to successfully predict structural response of 3DOF nonlinear spring–mass–damper system and non-linear three-story steel moment-resisting frame for unseen earthquakes with a median error less than 12%.

Classification of buildings' potential for seismic damage using a machine learning model with auto hyperparameter tuning

The research on the application of machine learning (ML) methods in the field of earthquake engineering shows a continuous and rapid progress in the last two decades. ML methods and models belonging to the category of supervised, unsupervised and semi-supervised learning are applied for the assessment of seismic vulnerability of structures and estimation of the expected level of seismic damage. These models lead to the classification of seismic damage into predefined classes through the extraction of patterns from data collected from various sources. However, the lack of detailed knowledge can affect their performance and ultimately reduce their reliability, as well as the generalizability that should characterize them. Towards this direction, the present paper attempts to compare and evaluate for the first time the ability of an extensive number of ML methods in the correct classification of R/C buildings at the first stage pre- and post-seismic inspection considering three seismic damage categories. A database consisting of 5850 training samples is used for this evaluation. This database is generated by solving 90 R/C buildings for 65 actual seismic excitations applying nonlinear time history analyses. For each one of the training samples the maximum interstory drift ratio is calculated as a damage index. In addition, a major contribution of this paper is the presentation and extensive documentation of the procedures required for the preprocessing of the data. Finally, an auto hyperparameter tuning method for the winning algorithm is proposed, so that the hyperparameters are automatically optimized utilizing Bayesian Optimization. The most significant conclusion extracted is that the studied ML algorithms extract very different classification results. In addition, the Support Vector Machine - Gaussian Kernel algorithm extracted the most accurate results of all the studied ML algorithms.

Self-adaptive physics-driven deep learning for seismic wave modeling in complex topography

Solving for the scattered wavefield is a key scientific problem in the field of seismology and earthquake engineering. Physics-informed neural networks (PINNs) developed in recent years have great potential in possibly increasing the flexibility and efficacy of seismic modeling and inversion. Inspired by self-adaptive physics-informed neural networks (SA-PINNs), we introduce a framework for modeling seismic waves in complex topography The relevant theoretical model construction was performed using the one-dimensional (1D) wave equation as an example. Using SA-PINNs and combining them with sparse initial wavefield data formed by the spectral element method (SEM), we carry out a numerical simulation of two-dimensional (2D) SH wave propagation to realize typical cases such as infinite/semi-infinite domain and arc-shaped canyon/hill topography. For complex scattered wavefields, a sequential learning method with time-domain decomposition was introduced in SA-PINNs to improve the scalability and solution accuracy of the network. The accuracy and reliability of the proposed method to simulate wave propagation in complex topography were verified by comparing the displacement seismograms calculated by the SA-PINNs method with those calculated by the SEM. The results show that the SA-PINNs have the advantage of gridless and fine-grained simulation and can realize numerical simulation conditions, such as free surface and side-boundary wavefield transmission.

Analysis of Seismic Collapse-Resistant Influencing Factors of RC Frame Structure

The RC frame structure is widely applied in China due to its flexible layout and good anti-collapse capacity during an earthquake. However, a lot of RC frame structures collapsed in the strong earthquake zone during the Wenchuan earthquake. The collapse resistance of the RC frame structures during an actual earthquake is inconsistent to the designed seismic collapse resistance in a project. So the collapse resistance of reinforced concrete (RC) frame structures during an earthquake and its influencing factors are a hot research topic in the field of earthquake engineering. Based on the research results of scholars in recent years, this paper briefly discusses the evaluation criteria of structural collapse, the structural collapse mechanism during a real earthquake and the influence of nonstructural components. Finally, the influencing factors are summarized in terms of design methods, plastic hinges and nonstructural members, which have certain reference significance for the seismic collapse resistance design.

A comparative study of the novel externally-attached precast SRC braced-frames for seismic retrofitting under near-field spectrum-compatible non-stationary stochastic earthquake

Seismic retrofitting is a hot issue in the field of earthquake engineering, and the externally-attached substructure approach is a well-known solution due to its no-disturbing construction and high-efficiency improvement. In this paper, a comparative study of a novel externally-attached precast steel-reinforced-concrete (SRC) braced-frames for seismic retrofitting is performed, and the near-field spectrum-compatible non-stationary stochastic earthquakes are generated as the excitation to reflect the input uncertainty. The construction and simulation approaches of the novel substructure are first introduced, and then the generation theories of near-field spectrum-compatible non-stationary stochastic earthquake are explained. The comparative study of five scenarios is conducted, via a 3-span-5-story existing reinforced concrete frame, and a series of performance indices are adopted for analysis, including the inter-story deformation, inter-story shear force, section-mechanical performance, and energy-consumption capacity. In general, the comparison study verifies the effectiveness of the novel externally-attached SRC braced-frames for retrofitting, and the external frame obviously reduces the axial force of the existing beams and columns, which indicates that the shear demand is transferred to the external substructures and the damage accumulation is well controlled after retrofitting. Although the inter-story performance and energy-dissipation capacity of the external substructures are not as direct as the bare brace scenarios, the external frames alleviate the potential premature damage of the existing joints and avoid the infills or facades of the existing building to place external braces, which provides a practical reference for the engineering application and future research.

Dimensionality reduction techniques in structural and earthquake engineering

Dimensionality reduction (DR) techniques are becoming increasingly important in engineering and scientific applications for feature extraction and data visualization purposes. This problem gets significantly more demanding when encountering class-imbalanced data sets with a disproportionate ratio of observations in each class. The main objective of this paper is to thoroughly evaluate the performance of various dimensionality reduction techniques for analyzing a cognate set of computational and experimental data in the field of structural and earthquake engineering with varying numbers of classes. Notably, a data set is generated using a computer simulation that characterizes risks posed by earthquakes to structures. Depending on the severity of damage in the simulations, data is classified into three, five, and eight classes. This research study also uses three existing multi-class imbalanced data sets that have been developed independently. For each problem, Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and t-Distributed Stochastic Neighbor Embedding (t-SNE) are used, to cover a wide range of linear/non-linear and supervised/unsupervised DR techniques. To overcome the class-imbalance problem, the efficacy of the Synthetic Minority Oversampling (SMOTE) technique considering various classifiers, including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Trees (DT), Random Forest (RF), MLPClassifier (MLP), and AdaBoost are investigated. It is observed that combining SMOTE and LDA shows promising results for training classifiers on the reduced data. In light of the findings of this study, it is recommended to train DT classifiers after reducing the dimensionality of the input data. It is through this process that the scientific data is transformed into a two-dimensional space for visualizing decision surfaces, which is helpful for practitioners to understand the performance of classifiers.

Machine Learning-based Seismic Fragility Curves for RC Bridge Piers

A significant part of ongoing studies in the field of earthquake engineering is directed toward the seismic risk assessment of buildings and infrastructures at a territorial scale. This task is usually accomplished by grouping the structures into homogenous classes in terms of typology, for which seismic fragility curves are then obtained for different limit states via numerical simulations or from the statistical analysis of observational data when available. Particularly, the development of typological fragility curves for bridges under earthquake is useful for assessing the reliability and resilience of transportation networks in seismic areas and can be also effective decision-making support. Within this framework, the proposed study establishes a machine learning-based paradigm for the closed-form prediction of the main statistical parameters required to obtain relevant seismic fragility curves for reinforced concrete bridge piers. Initially, a huge training dataset has been obtained by Monte Carlo simulations and displacement-based bridge pier assessments by assuming data representative of the Italian highway transportation network. Next, symbolic nonlinear regression formulae for estimating the main statistical parameters of seismic fragility curves have been generated. With the aid of those formulae, the effort of calculating the seismic fragility curves is greatly reduced since the corresponding main statistical parameters can be directly calculated from a set of commonly available attributes. Therefore, the proposed study provides a helpful tool for the rapid preliminary assessment of damage and risk level of existing highway transportation networks exposed to seismic hazards.