Early Report of the Source Characteristics, Ground Motions, and Casualty Estimates of the 2023 Mw 7.8 and 7.5 Turkey Earthquakes

Chen, Wenkai; Rao, Gang; Kang, Dengjie; Wan, Zhifan; Wang, Dun

doi:10.1007/s12583-023-1316-6

Cited by 37 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Near‐fault pulse‐like ground motion is one of the hot spot issues in earthquake engineering since it potentially causes more severe damage to structures than ordinary ground motion (termed nonpulse ground motion in this study) 1–3 . This phenomenon was first discovered at the Port Hueneme earthquake in 1957, 4 and further verified by following near‐source earthquakes, such as 1995 Kobe Earthquake, 5 1999 Chi‐Chi Earthquake, 6 2018 Hualien Earthquake, 7 and 2023 Turkey‐Syria Earthquake 8 . These near‐fault earthquakes effectively expand the pulse‐like ground motion database and advance relevant research, such as the seismological mechanism of pulse generation, 9 pulse‐like ground motion identification, 10,11 and simulation, 12,13 and seismic damage analysis 1,14 .…”

Section: Introductionmentioning

confidence: 79%

Seismic damage analysis due to near‐fault multipulse ground motion

Chen,

Yang,

Wang

et al. 2023

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

Near‐fault pulse‐like ground motion is a significant class of seismic records since it tends to cause more severe damage to structures than ordinary ground motions. However, previous researches mainly focus on single‐pulse ground motions. The multipulse ground motions that exist in records receive rare attention. In this study, an analysis procedure is proposed to investigate the effect of multipulse ground motions on structures by integrating finite element analysis and an identification method that features each pulse in the multipulse ground motion satisfying the same evaluation criteria. First, the Arias intensity, wavelet‐based cumulative energy distribution, and response spectra of identified non‐, single‐, and multipulse ground motions are compared. Then, the seismic damage on frame structures, a soil slope, and a concrete dam under non‐, single‐, and multipulse ground motions are analyzed. Results show that the spectral velocity of multipulse ground motions is significantly greater than those of non‐ and single‐pulse ground motions and potentially contains multiple peaks in the long‐period range. Seismic damage evaluation indicates that the maximum interstory drift of frame structures with high fundamental periods under multipulse ground motions is about twice that of nonpulse ground motions. Similar characteristics also exist in the soil slope and the concrete dam. Therefore, multipulse ground motions potentially cause more severe damage to structures compared to non‐ and single‐pulse ground motions. The findings of this study facilitate the recognition of the increased seismic demand imposed by the multipulse ground motion in engineering practices, provide new possibilities for ground motion selection in seismic design validation, and shed new light on seismic hazard and risk analysis in near‐fault regions.

show abstract

Section: Introductionmentioning

confidence: 79%

Seismic damage analysis due to near‐fault multipulse ground motion

Chen,

Yang,

Wang

et al. 2023

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

show abstract

“…These metrics are formally defined by true positive (TP), false negative (FN), false positive (FP), and true negative (TN), as illustrated in Figure 2. Accuracy, an overall metric that evaluates the performance of all categories, is defined by the proportion of correctly predicted samples, i.e., TP and TN, to the total number, as presented in Equation (6). The classification performance of a specific category can be evaluated by precision and recall.…”

Section: Machine Learning Evaluation Metricsmentioning

confidence: 99%

“…In 2015, an earthquake with an M w of 7.8 struck Gorkha, Nepal, resulting in over 30,000 people dead or injured, eight million people displaced, 500,000 houses destroyed, and another 250,000 houses damaged [5]. In 2023, a 7.8 M w earthquake happened in Turkey and Syria, where there were around 55,000 fatalities, 130,000 injuries, and 50,000 destroyed or badly damaged structures as a result of the tragedy, which affected approximately 18 million people [6,7]. Given the above shocking and alarming facts, it would be useful to be able to rapidly identify buildings with severe and light damage after an earthquake to implement proper rescue and reconstruction, facilitating the sustainable development of cities.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Assessment of Damage Grade for Post-Earthquake Buildings: A Three-Stage Approach Directly Handling Categorical Features

Li,

Jia,

Chen

et al. 2023

Sustainability

View full text Add to dashboard Cite

The rapid assessment of post-earthquake building damage for rescue and reconstruction is a crucial strategy to reduce the enormous number of human casualties and economic losses caused by earthquakes. Conventional machine learning (ML) approaches for this problem usually employ one-hot encoding to cope with categorical features, and their overall procedure is neither sufficient nor comprehensive. Therefore, this study proposed a three-stage approach, which can directly handle categorical features and enhance the entire methodology of ML applications. In stage I, an integrated data preprocessing framework involving subjective–objective feature selection was proposed and performed on a dataset of buildings after the 2015 Gorkha earthquake. In stage II, four machine learning models, KNN, XGBoost, CatBoost, and LightGBM, were trained and tested on the dataset. The best model was judged by comprehensive metrics, including the proposed risk coefficient. In stage III, the feature importance, the relationships between the features and the model’s output, and the feature interaction effects were investigated by Shapley additive explanations. The results indicate that the LightGBM model has the best overall performance with the highest accuracy of 0.897, the lowest risk coefficient of 0.042, and the shortest training time of 12.68 s due to its relevant algorithms for directly tackling categorical features. As for its interpretability, the most important features are determined, and information on these features’ impacts and interactions is obtained to improve the reliability of and promote practical engineering applications for the ML models. The proposed three-stage approach can provide a reference for the overall ML implementation process on raw datasets for similar problems.

show abstract

“…The QCNN model is trained using past earthquake‐induced damage images of RC buildings. The performance of this trained model is evaluated based on its performance on unseen damaged images, which are collected after the recent Turkey earthquake in February 2023 (W. Chen et al., 2023). Moreover, the comparison is made between the QCNN model performance with the results of various deep CNN architectures, such as AlexNet, Visual Geometric Group with 16 convolutional layers (VGG‐16) and 19 convolutional layers (VGG‐19), Residual Network with 50 deep layers (ResNet50), InceptionV2, InceptionV3, MobileNetV2, Xception, and DenseNet.…”

Section: Introductionmentioning

confidence: 99%

“…The occurrence of large‐scale earthquake events is often associated with the vital damage to the built environment, along with their impacts on human life and the economy, for example, the 2023 Turkey earthquake (W. Chen et al., 2023) and the 2015 Nepal earthquake (H. Chen et al., 2017). Over the past few decades, such massive events have become more common and intense around the globe (Khajwal et al., 2023).…”

Section: Introductionmentioning

confidence: 99%

Multiclass seismic damage detection of buildings using quantum convolutional neural network

Bhatta,

Dang

2023

Computer aided Civil Eng

View full text Add to dashboard Cite

The traditional visual inspection technique for damage assessment of buildings immediately after an earthquake can be time‐consuming, labor‐intensive, and risky. Numerous studies have been carried out using deep learning techniques, particularly convolutional neural network (CNN), to evaluate the damage to building structures after an earthquake using buildings’ damage images. Quantum computing, on the other hand, is a computing environment that can exploit superposition and entanglement, which are not available in classical computing environments, to achieve higher performance using parallelism between qubits. This paper presents a novel quantum CNN (QCNN) approach to detect damage to reinforced concrete (RC) buildings from images after the earthquake. The QCNN model is developed and trained using the RC building damaged images collected from past earthquakes. The performance of this model is evaluated based on the multiclass damage detection ability of the real‐world RC building damaged images collected from the recent earthquake in Turkey in February 2023. Furthermore, the seismic damage detection accuracy obtained from the QCNN model is compared with various CNN architecture results.

show abstract

Early Report of the Source Characteristics, Ground Motions, and Casualty Estimates of the 2023 Mw 7.8 and 7.5 Turkey Earthquakes

Cited by 37 publications

References 29 publications

Seismic damage analysis due to near‐fault multipulse ground motion

Seismic damage analysis due to near‐fault multipulse ground motion

Machine Learning Assessment of Damage Grade for Post-Earthquake Buildings: A Three-Stage Approach Directly Handling Categorical Features

Multiclass seismic damage detection of buildings using quantum convolutional neural network

Contact Info

Product

Resources

About