Earthquake Damage Prediction Research Articles

Building information extraction and earthquake damage prediction in an old urban area based on UAV oblique photogrammetry

Building information extraction and earthquake damage prediction in an old urban area based on UAV oblique photogrammetry

An empirical analysis of hyperparameter tuning impact on ensemble machine learning algorithm for earthquake damage prediction

An empirical analysis of hyperparameter tuning impact on ensemble machine learning algorithm for earthquake damage prediction

Impact of earthquake’s epicenter distance to failure of the embankment – A seismic prediction

Cracks in clayey soil cause a reduction in the seismic loading capacity which can lead to structural failures. Seismic acceleration is the primary cause of crack propagation and damage to the earth's structure. This study investigated the impact of the earthquake's epicenter distance on the embankment model with a pre-existing crack in the embankment's core. The research adopted the numerical modeling method of soil categorized as a no-tensile material to explain displacement in selected points of the model using the extended finite element method (XFEM). Artificial Neural Networks (ANNs) were used to predict displacement obtained by XFEM. It was observed that the failure pattern and the maximum displacement time of the model change with the associated distance of the earthquake's epicenter. The key study objective is to understand the model's failure mode and introduce a new classification in earthquake damage prediction.

EMPIRICAL VULNERABILITY ANALYSIS OF RAILWAY BRIDGE SEISMIC DAMAGE BASED ON 2022 MENYUAN EARTHQUAKE

A 6.9 magnitude earthquake at a depth of 10 km struck Menyuan County, Haibei Prefecture, Qinghai Province, China, on January 8, 2022. This earthquake damaged some railway bridges on the Lanzhou-Xinjiang Passenger Dedicated Line. This study combines relevant historical earthquake damage experience, considers the effects of earthquake intensity, site soil classification, superstructure type, foundation failure factor, number of spans, and total bridge length, and develops empirical formulas for seismic damage prediction of railway bridges using ordinal logistic regression model in SPSS software. The seismic damage matrix, as were the anticipated multi-intensity mean damage index and the empirical vulnerability curve based on the two-parameter lognormal distribution function, were generated on this basis. According to the conclusions, although the suggested particular equations and vulnerability curves do not apply to the remainder of the region owing to geographical uniqueness, the technical approach is valid. It may be used as a reference for seismic damage prediction and vulnerability evaluation in other regions. The empirical vulnerability analysis based on the earthquake damage prediction matrix derived from the regression analysis can provide reasonable and fast forecasts before the next earthquake.

Rapid Assessment of Seismic Risk for Railway Bridges Based on Machine Learning

When an earthquake occurs, railway bridges will suffer from different degrees of seismic damage, and it is necessary to assess the seismic risk of bridges. Unfortunately, the majority of studies were done on highway bridges without taking into account railway bridge characteristics; hence they are not applicable to railway bridges. Furthermore, current research methods for risk assessment cannot be performed quickly, and suffer from the problems of subjective personal experience, complicated calculations, and time-consuming. This paper we use machine learning for earthquake damage prediction and empirical vulnerability curves to represent risk assessment results, creating a rapid risk assessment procedure. We gathered and tallied seismic damage data from 335 railway bridges that were damaged in the Tangshan and Menyuan earthquakes, found six variables that had a substantial impact on seismic risk outcomes, and categorized the damage levels into five categories. It is essentially a multi-classification and prediction problem. In order to solve this problem, four algorithms were tested: Random Forest (RF) Back Propagation Artiifcial Neural Network (BP-ANN), PSO-Support Vector Machine (PSO-SVM), and K Nearest Neighbor (KNN). It was found that RF is the most effective method, with an accuracy rate of up to 93.31% for the training set and 89.39% for the test set. Then this study describes the new procedure in detail for rapidly assessing seismic risk to 269 bridges chosen at random from the sample pool. Firstly, the seismic damage data of bridges are collated, then the seismic damage rating is predicted using RF, and finally the empirical vulnerability curve is drawn using a two-parameter normal distribution function for the purpose of seismic damage risk assessment. The study’s findings can be used as a guide for choosing a machine learning approach and its inputs to build a rapid assessment model for railway bridges.

Research on a methodology for intelligent seismic performance evaluation and optimization design of buildings based on IFC and ontology

Seismic loss prediction and performance assessment for buildings have already been hot spots for resilience after earthquakes with the emergence of the concepts of digital twins. However, because a large amount of multisource heterogeneous data and a real-time accurate prediction model are required to implement the process, the popularization and implementation of these technologies are hampered. Based on performance-based seismic design (PBSD) theory, this study introduces BIM and ontology and other emerging technologies to carry out methodology research on intelligent earthquake damage prediction and seismic performance evaluation for individual buildings. First, based on FEMA P-58 (Seismic Performance Assessment of Buildings), this paper uses BIM technology to integrate and transmit component-level engineering information. Ontology method is used to express the assessment content and logic, and a multidimensional semantic ontology model based on IFC is proposed to form the linked data foundation to organize, store, associate and interact the multisource heterogeneous data required for assessment in a unified way to realize the semi-automated seismic performance assessment for individual RC frame building. On this basis, the seismic optimization design under the guidance of the “investment - benefit” criterion is regarded as the problem of seeking the balance between the initial construction cost and the expectation of seismic loss. The multi-objective genetic algorithm (NSGA-II) is used to realize the optimization iteration at the component level. According to the results of the case study, the new method in this paper significantly improves the quality of seismic performance assessment and seismic design optimization.

Design of highway pavement earthquake damage prediction method considering horizontal earthquake force

Due to the influence of geographical environment and horizontal seismic force, it is difficult to predict the seismic damage of urban highway pavement. In addition, poor engineering characteristics will cause damage to the stability of the subgrade and extremely easy to deformation. The above situation has become an important problem in highway construction. To improve the accuracy of earthquake damage prediction of highway pavement, a method of earthquake damage prediction considering horizontal seismic force is proposed. This method is based on the fuzzy comprehensive evaluation, taking the highway bridge, subgrade and pavement, roadside environment and highway tunnel as the main factors, and establishing the post-earthquake damage evaluation model of the highway system. Based on the analysis of the relevant data, the power polynomial prediction model is proposed, and the feasibility and parameter determination method of the power polynomial are analyzed. The stability of highway pavement under earthquake is predicted. The results show that the design method can predict the seismic damage of highway pavement. In addition, the proposed surface model can also simulate the settlement value and predict the settlement law.

Real-time prediction of earthquake potential damage: A case study for the January 8, 2022 MS 6.9 Menyuan earthquake in Qinghai, China

It is critical to determine whether a site has potential damage in real-time after an earthquake occurs, which is a challenge in earthquake disaster reduction. Here, we propose a real-time Earthquake Potential Damage predictor (EPDor) based on predicting peak ground velocities (PGVs) of sites. The EPDor is composed of three parts: (1) predicting the magnitude of an earthquake and PGVs of triggered stations based on the machine learning prediction models; (2) predicting the PGVs at distant sites based on the empirical ground motion prediction equation; (3) generating the PGV map through predicting the PGV of each grid point based on an interpolation process of weighted average based on the predicted values in (1) and (2). We apply the EPDor to the 2022 MS 6.9 Menyuan earthquake in Qinghai Province, China to predict its potential damage. Within the initial few seconds after the first station is triggered, the EPDor can determine directly whether there is potential damage for some sites to a certain degree. Hence, we infer that the EPDor has potential application for future earthquakes. Meanwhile, it also has potential in Chinese earthquake early warning system.

Earthquake damage and rehabilitation intervention prediction using machine learning

Predicting damage grade and rehabilitation interventions is important, especially in the aftermath of moderate to strong earthquakes as prioritization of post-earthquake housing recovery needs information regarding the damage extent. Damage prediction is generally performed using fragility functions, which are generally associated with large uncertainties. Moreover, availability and representativeness of fragility functions for a region affected by an earthquake is not always a given. A more realistic prediction of damage might be obtained from methods that rely on relevant attributes of affected buildings. Artificial intelligence-based formulations have huge prospect in this regard. Using the ground shaking intensity measure and detailed building specific features of 549,251 buildings affected by the 2015 Gorkha earthquake in Nepal, this paper assesses efficacy of four common machine learning algorithms for damage grade and rehabilitation intervention prediction. Decision tree, random forest, XGBoost, and logistic regression algorithms are used to prepare machine learning models and test their performance. The XGBoost algorithm is found to predict building collapse and strengthening more accurately than the other algorithms. Moreover, feature importance from the XGBoost model identifies 19 of the top 20 most important features as relevant for both damage grade and rehabilitation intervention prediction.

Prediction of Tunnel Earthquake Damage Based on a Combination Weighting Analysis Method

To reduce or evaluate the damage of tunnels in seismically active areas when earthquakes happen, it is very important to quickly predict the tunnel damage. This study proposes an anti-entropy–fuzzy analytic hierarchy process (FAHP) combination weighting method for tunnel earthquake damage prediction. The tunnel cross section is a symmetrical structure. The method uses tunnel damage data from the tunnels in a region where earthquake disasters have occurred as sample data to calculate the standard earthquake damage index. The weights of evaluation factors are determined by combining the FAHP and anti-entropy weighting. The correction coefficient of each evaluation factor is obtained by considering the degree of each evaluation factor’s influence on the average damage index. Then, the earthquake damage and the corresponding damage degree of each tunnel are obtained by weighting calculation. In this study, 55 tunnels in the Wenchuan earthquake-affected area are taken as analysis cases. In these cases, 45 cases of damage tunnels are used as sample data, and 10 random tunnels are used as training cases. The calculated results are compared with the observed results. The proposed method is confirmed simple and easy to implement, which can greatly reduce the workload of field investigation, calculation and analysis. The results is of great significance to the rapid earthquake emergency assessment and post earthquake recovery of tunnels.

Seismic Coefficients and Earthquake Damage Predictions for a Space Truss with a Supporting Structure

Seismic Coefficients and Earthquake Damage Predictions for a Space Truss with a Supporting Structure

A neural network-based multivariate seismic classifier for simultaneous post-earthquake fragility estimation and damage classification

A scalar intensity measure (IM) could be insufficient to represent the earthquake intensity and variety in fragility estimation. Introducing multiple IMs to conventional regression of fragility functions can be computationally demanding and require priori assumptions of functional forms. In this study, multivariate seismic classifiers with multiple IMs as inputs are developed based on artificial neural networks (ANNs) to address the above disadvantages of traditional regression approaches. Case studies of a four-story code-conforming benchmark building indicate that fragility estimates from multi-IM ANN classifiers lead to higher accuracy (5.0% to 7.7%) in system-level and element-level damage classification than the single-IM traditional fragility curves. Further studies of IM combinations show that the ANN performance can be improved by more IMs correlated with structural responses while compromised by redundant irrelevant IMs. The optimal IM set should be determined by correlation ranking and ANN predictive performance together. Moreover, the ANN configuration of the case-study building is optimized with five readily available IMs as inputs, which enable a near real-time (within 0.3 ms) prediction of future earthquake damage while maintain high predictive performance. Overall, the multivariate ANN seismic classifier can be a promising tool for simultaneous seismic fragility estimation and damage assessment.

Research on Seismic Vulnerability of High-Pier and Long-Span Bridges Based on Improved IMK Resilience Model

After the fragility curve is established, the probability of structural damage reaching each level of damage under the action of the ground motion can be determined according to the ground motion parameters, so as to calculate the direct and indirect loss caused by the structural damage and complete the earthquake damage prediction. This paper combines the improved IMK resilience model to study the seismic vulnerability of high-pier and long-span bridges. Moreover, this paper obtains the parameter calculation model based on the regression analysis of PEER’s 255 column specimen data. The improved IMK model needs to modify the elastic stiffness and strain hardening rate of the rotating spring to ensure the accuracy of the lateral stiffness of the component. The experimental research shows that the seismic vulnerability research model of high-pier and long-span bridges based on the improved IMK restoring force model has a certain analytical effect.

Seismic Fragility Assessment for Korean High-Rise Non-Seismic RC Shear Wall Apartment Buildings

Seismic fragility was assessed for non-seismic reinforced concrete shear walls in Korean high-rise apartment buildings in order to implement an earthquake damage prediction system. Seismic hazard was defined with an earthquake scenario, in which ground motion intensity was varied with respect to prescribed seismic center distances given an earthquake magnitude. Ground motion response spectra were computed using Korean ground motion attenuation equations to match accelerograms. Seismic fragility functions were developed using nonlinear static and dynamic analysis for comparison. Differences in seismic fragility between damage state criteria including inter-story drifts and the performance of individual structural members were investigated. The analyzed building had an exceptionally long period for the fundamental mode in the longitudinal direction and corresponding contribution of higher modes because of a prominently insufficient wall quantity in such direction. The results showed that nonlinear static analyses based on a single mode tend to underestimate structural damage. Moreover, detailed assessments of structural members are recommended for seismic fragility assessment of a relatively low performance level such as collapse prevention. On the other hand, inter-story drift is a more appropriate criterion for a relatively high performance level such as immediate occupancy.

Numerical simulation of the seismic response and soil\u2013structure interaction for a monitored masonry school building damaged by the 2016 Central Italy earthquake

Despite significant research advances on the seismic response analysis, there is still an urgent need for validation of numerical simulation methods for prediction of earthquake response and damage. In this respect, seismic monitoring networks and proper modelling can further support validation studies, allowing more realistic simulations of what earthquakes can produce. This paper discusses the seismic response of the “Pietro Capuzi” school in Visso, a village located in the Marche region (Italy) that was severely damaged by the 2016–2017 Central Italy earthquake sequence. The school was a two-story masonry structure founded on simple enlargements of its load-bearing walls, partially embedded in the alluvial loose soils of the Nera river. The structure was monitored as a strategic building by the Italian Seismic Observatory of Structures (OSS), which provided acceleration records under both ambient noise and the three mainshocks of the seismic sequence. The evolution of the damage pattern following each one of the three mainshocks was provided by on-site survey integrated by OSS data. Data on the dynamic soil properties was available from the seismic microzonation study of the Visso village and proved useful in the development of a reliable geotechnical model of the subsoil. The equivalent frame (EF) approach was adopted to simulate the nonlinear response of the school building through both fixed-base and compliant-base models, to assess the likely influence of soil–structure interaction on the building performance. The ambient noise records allowed for an accurate calibration of the soil–structure model. The seismic response of the masonry building to the whole sequence of the three mainshocks was then simulated by nonlinear time history analyses by using the horizontal accelerations recorded at the underground floor as input motions. Numerical results are validated against the evidence on structural response in terms of both incremental damage and global shear force–displacement relationships. The comparisons are satisfactory, corroborating the reliability of the compliant-base approach as applied to the EF model and its computational efficiency to simulate the soil–foundation–structure interaction in the case of masonry buildings.

Research on earthquake damage prediction of stone structure in southern Fujian based on fuzzy comprehensive evaluation

Based on fuzzy mathematics method, earthquake damage prediction of stone structure houses in Southern Fujian is studied. The subsets of earthquake damage affecting factors applicable to stone structures and their fuzzy relation with earthquake damage levels are established. Furthermore, the earthquake damage prediction model of stone structure houses in southern Fujian is developed based on fuzzy comprehensive evaluation method. Taking the two-storey stone structure house as an example, the model is applied to predict and evaluate the damage state of the two-storey stone structure house after earthquake damage. The results show that, according to the fuzzy comprehensive prediction and evaluation model, the stone structure house suffers serious damage degree in the earthquake damage, the evaluation grade of earthquake damage is C, and the evaluation result is consistent with the actual damage state. The model of earthquake damage prediction is clear and easy to calculate, which provides a theoretical basis for earthquake damage prediction and reinforcement and maintenance of stone structure houses in southern Fujian.

Construction of a Site- and Period-Specific Seismic Hazard Map for the Korean Peninsula

The 2016 Gyeongju and 2017 Pohang earthquakes caused casualties and economic damage in the surrounding areas. Therefore, the importance of earthquake damage prediction and seismic design in the Korean peninsula has increased. Probabilistic seismic hazard analysis (PSHA) is one of the well-known methods for predicting earthquake damage. The objective of this study is to construct Korean Peninsula seismic hazard maps of 5% damped response spectrum acceleration and peak ground acceleration, using PSHA. To consider the local effects for each site's classification, seismic hazard maps were constructed by considering the site amplification model. To conduct seismic design, uniform hazard response spectra (UHRS) were also constructed for the Korean peninsula.

Seismic vulnerability comparison between rural Weinan and other rural areas in Western China

Generally, the anti-seismic capacity of rural buildings in China is poor due to their irregular design and construction. On the basis of historical destructive earthquake records, corresponding earthquake loss evaluation compilations (1993–2016), field investigations, and remote sensing interpretation, building structures in rural Weinan are classified into two types and analyzed to acquire the seismic vulnerability matrices by employing the fitting method of beta probability density function (BPDF). Results show that BPDF can well reveal the probability density distribution of seismic damage index, and also the damage ratio obtained agrees well with the description of damage degrees in Chinese macroseismic intensity scale.The vulnerability indexes in rural areas of Yunnan, Sichuan, Qinghai provinces and in Weinan City (Shaanxi province) were calculated and a comparison of aseismic ability was made. Results show that, among the rural areas in Western China, the aseismic abilities of traditional buildings in rural Weinan are the lowest while those of masonry buildings are highest. Moreover, potential losses in rural Weinan are estimated on the assumption that a scenario earthquake with a magnitude Ms 6¾ hit Weinan City, proposed by the UK-China Collaboration programme ‘‘Increasing Resilience to Natural Hazards in Earthquake-Prone regions in China”. It was found that the damage ratios obtained captured the distribution of the aseismic abilities of the rural buildings and therefore improved the accuracy of the loss assessment, which provides scientific basis for the scenario narratives. What we discovered in this paper is also helpful in future earthquake damage prediction and enhancement of public awareness on earthquake resistance.

Shallow crustal earthquake models, damage, and loss predictions in Banda Aceh, Indonesia

The city of Banda Aceh stands on Holocene fluvial basin sediment, surrounded by the Aceh and Seulimeum fault segments where large magnitude earthquakes can occur at any time. Such earthquakes could cause extensive physical infrastructure damages, injuries, and economic loss. This research aims to produce several earthquake scenarios, to determine the damage ratio of the buildings and its distribution in these different scenarios and to estimate the number of potential casualties and economic loss. Data analysis in this research includes modelling an earthquake by applying a ground motion model for shallow crustal earthquakes to yield an intensity map after the correction for site effects. The damage ratios for different types of buildings were calculated using the fragility curves of buildings that were developed by other researchers. Building occupants at different times, building damage ratios, and injury ratios were used to determine the number of injured residents in the earthquake scenario. The results show that Banda Aceh could be potentially experience earthquake ground motion within the intensity range from MMI VII to IX due to earthquakes of Mw 6.5 to Mw 7.0. The Mw 7.0 earthquake on the Aceh segment is the worst case scenario, causing building damage throughout Banda Aceh with casualty rates of 3.5–20% of the population in buildings in general if it happened during daytime, with economic loss about 3320 million USD. Mitigation and preparedness programs for the Banda Aceh community are therefore very important in order to reduce the potential level of damage, personal injury, and economic loss due to future earthquakes.

Prediction of V s30 in Datong Basin and Amplification Effect of Site Ground Motion Based on Typical Geological Characteristics Analysis

Shear wave velocity of soil layer is an important dynamic parameter, which is of great significance for site classification, determination of ground motion parameters and prediction of ground motion. Based on the analysis of shear wave velocity data of 1429 geological boreholes in Datong Basin, this paper studies the relationship between V S and geological characteristics such as soil type, geological unit type, SPT blow number and compactness degree. Based on the correlation analysis of shear wave velocity ratio of soil, soil compactness coefficient and thickness of Quaternary upper overburden, this paper presents a soil V S30 prediction model. The goodness of fit R 2 > 0.90 and the prediction accuracy is very high under the overall sample condition. Based on the abundant strong earthquake records and drilling information of KiK-net and K-net networks in Japan, V S30 and site period T S are selected as the two quantitative indexes of the amplification effect of site ground motion. The correlation between V S30 and PGA amplification coefficient and site period T S is established. The distribution characteristics of PGA amplification coefficient and site period T S based on V S30 distribution are given. The results show that the maximum values of PGA amplification coefficient and TS distribution characteristics of site period are consistent with the geological location of the earthquake swarm with M6.1 in 1989 in Datong Basin. It shows that the characteristics of the site ground motion effect estimated by V S30 can indicate the occurrence of earthquakes. The occurrence of earthquakes is affected by active faults and local conditions of the site at the same time, which fully proves the feasibility of this research method and the accuracy of the research results. The shear wave velocity ratio and the soil compactness coefficient are proposed for the first time, and they are applied to the prediction of V S30 with the thickness of the upper overburden of the quaternary system. This paper provides a good research idea for V S30 prediction of non-shear wave velocity test site, study of amplification effect of site ground motion, study and judgment of earthquake location. The research results can provide important technical support for urban earthquake prevention and mitigation planning, large earthquake scenario construction, earthquake risk analysis, earthquake damage prediction and regional earthquake safety evaluation in Taiyuan Basin.