Building Damage Assessment Research Articles

Application of high adaptive models in building damage assessment: case studies of earthquake in Turkey and hurricane in Louisiana

Application of high adaptive models in building damage assessment: case studies of earthquake in Turkey and hurricane in Louisiana

Rapid post-earthquake damage assessment of building portfolios through deep learning-based component-level image recognition

Frequent seismic events significantly heighten the likelihood of the building structure being impacted throughout its operational lifecycle. Seismic effects on these structures result in a notable reduction in structural safety and serviceability. Enabling the post-earthquake recovery of building structures necessitates a precise and swift assessment of earthquake-induced damage. The conventional method for assessing building damage involves collecting data through close manual observation or contact inspection. Although it can obtain relatively accurate results by combining evaluation specifications, it is time-consuming and labour-intensive. Deep learning (DL) is data-driven and employs computational methods for data processing. The image classification function of convolutional neural network (CNN) in DL brings great convenience to image data processing. It has been applied to various aspects of structural health monitoring/post-disaster assessment. However, most of the current studies focus on the component level and lack of a comprehensive perspective on the whole structure, which is not conducive to the judgment of the overall condition. Consequently, this paper proposes a rapid assessment method of the overall damage level of post-earthquake buildings based on component images and DL. Two component-level image classification models, component type and damage level, are firstly trained. Then, the images of the buildings to be evaluated after the earthquake are collected and classified. Combined with the weights of different component types and damage levels proposed, the overall condition scores and grades of the structures can be obtained by weighted calculation. The proposed method realizes an overall evaluation of the structural damage condition after seismic events, and further extends to the building portfolios, providing actionable guidance for subsequent personnel and fund allocation, rescue, and maintenance measures. Due to limitations in the dataset, such as the potential biases in the training dataset, the trained model is not perfect and faces challenges in distinguishing between minor and moderate damage. In the future, the dataset should update and ideally cover a wide range of building types, component types, and damage levels to ensure the model's robustness and applicability to various real-world scenarios.

Methodology for Object-Level Change Detection in Post-Earthquake Building Damage Assessment Based on Remote Sensing Images: OCD-BDA

Remote sensing and computer vision technologies are increasingly leveraged for rapid post-disaster building damage assessment, becoming a crucial and practical approach. In this context, the accuracy of employing various AI models in pixel-level change detection methods is significantly dependent on the consistency between pre- and post-disaster building images, particularly regarding variations in resolution, viewing angle, and lighting conditions; in object-level feature recognition methods, the low richness of semantic details of damaged buildings in images leads to a poor detection accuracy. This paper proposes a novel method, OCD-BDA (Object-Level Change Detection for Post-Disaster Building Damage Assessment), as an alternative to pixel-level change detection and object-level feature recognition methods. Inspired by human cognitive processes, this method incorporates three key steps: an efficient sample acquisition for object localization, labeling via HGC (Hierarchical and Gaussian Clustering), and model training and prediction for classification. Furthermore, this study establishes a change detection dataset based on Google Earth imagery of regions in Hatay Province before and after the Turkish earthquake. This dataset is characterized by pixel inconsistency and significant differences in photographic angles and lighting conditions between pre- and post-disaster images, making it a valuable test dataset for other studies. As a result, in the experiments of comparative generalization capabilities, OCD-BDA demonstrated a significant improvement, achieving an accuracy of 71%, which is twice that of the second-ranking method. Moreover, OCD-BDA exhibits superior performance in tasks with small sample amounts and rapid training time. With only 1% of the training samples, it achieves a prediction accuracy exceeding that of traditional transfer learning methods with 60% of samples. Additionally, it completes assessments across a large disaster area (450 km²) with 93% accuracy in under 23 min.

Enhanced satellite imagery analysis for post-disaster building damage assessment using integrated ResNet-U-Net model

Enhanced satellite imagery analysis for post-disaster building damage assessment using integrated ResNet-U-Net model

HRTBDA: a network for post-disaster building damage assessment based on remote sensing images

ABSTRACT Efficient building damage assessment after disasters is vital for emergency response and loss evaluation, but the task is complicated by diverse building structures and complex environments. Traditional methods using Convolutional Neural Networks (CNNs) struggle to capture global contextual features, limiting damage categorization accuracy. To address this, we introduce the High-Resolution Transformer Architecture for Building Damage Assessment (HRTBDA), which enhances multi-scale feature extraction. A Cross-Attention-Based Spatial Fusion (CSF) module is proposed to utilize the attention mechanism, improving the model’s ability to identify detailed associations in damaged buildings. Additionally, we propose a deep convolution network matching optimization strategy that integrates a multilayer perceptron and expands the receptive field, enhancing global feature perception. HRTBDA’s performance was evaluated on two public datasets and compared with five recent frameworks. The model achieved an F1-score of 86.0% in building localization and 78.4% in damage assessment, with a 4.8% improvement in detecting minor damages. These results demonstrate HRTBDA’s potential for improving building damage assessment and highlight its significant advancements over existing methods.

Rapid Urban-Scale Building Collapse Assessment Based on Nonlinear Dynamic Analysis and Earthquake Observations

Rapid damage assessment after an earthquake is crucial for allocating and prioritizing emergency actions. Building damage due to an earthquake depends on the seismic hazard and the building’s strength. While it is now possible to promptly access acceleration data as seismic input through online strong motion networks in urban areas, good models are necessary to evaluate the damage in different zones of the affected area. This study aims to present a rapid method for such an urban-scale building collapse evaluation by conducting a nonlinear dynamic analysis of modeled buildings. Based on the Nagato and Kawase model, this study estimates the yield shear strength of 3-story steel buildings, 3-story reinforced concrete buildings, and 1-story masonry buildings in Sarpol-e-Zahab City after the 2017 Mw7.3 earthquake. The damage ratio is calculated through nonlinear dynamic analyses using estimated records from the main earthquake shock in different city zones. The research found that the seismic yield shear strength of steel and reinforced concrete buildings might be weaker than that of the Iranian seismic code’s standard value. Conversely, masonry-building resistance is stronger than the guidelines assumed. The constructed numerical models can be used for the rapid building damage assessment immediately after a damaging earthquake.

Convolutional neural network-based multimodal image information fusion for moisture damage assessment of cultural heritage buildings

Water is an essential factor causing the deterioration of historical and cultural heritage, and identifying and quantifying moisture damage is essential for conserving cultural heritage buildings. This study combines infrared thermography (IRT) and microwave technology to investigate moisture-induced diseases and the variation of the spatial distribution of water content in the Yungang Grottoes of China, a World Heritage Site. Information on building humidity distribution was extracted and combined from IRT and microwave information. Furthermore, multi-feature image fusion combines different types of monitoring information through the Convolutional Neural Network (CNN), which is used to diagnose moisture distribution and content accurately. The features obtained from different non-destructive methods were then jointly analyzed using statistical analysis methods such as absolute contrast, noise ratio (SNR), and spatial stability to quantify the artifact moisture defect data, thus improving the accuracy and range of features for detecting water-damaged pathologies. The results show that the combination of IRT and microwave information technology not only qualitatively but also quantitatively analyses the moisture in the building, significantly using microwave moisture meters to study water distribution at different depths and surface characterization by IRT. The use of non-destructive monitoring tools helps to guide the diagnosis of moisture damage, restoration of heritage buildings, and the planning of intervention strategies.

Effectiveness of Generative AI for Post-Earthquake Damage Assessment

After an earthquake, rapid assessment of building damage is crucial for emergency response, reconstruction planning, and public safety. This study evaluates the performance of various Generative Artificial Intelligence (GAI) models in analyzing post-earthquake images to classify structural damage according to the EMS-98 scale, ranging from minor damage to total destruction. Correct classification rates for masonry buildings varied from 28.6% to 64.3%, with mean damage grade errors between 0.50 and 0.79, while for reinforced concrete buildings, rates ranged from 37.5% to 75.0%, with errors between 0.50 and 0.88. Fine-tuning these models could substantially improve accuracy. The practical implications are significant: integrating accurate GAI models into disaster response protocols can drastically reduce the time and resources required for damage assessment compared to traditional methods. This acceleration enables emergency services to make faster, data-driven decisions, optimize resource allocation, and potentially save lives. Furthermore, the widespread adoption of GAI models can enhance resilience planning by providing valuable data for future infrastructure improvements. The results of this work demonstrate the promise of GAI models for rapid, automated, and precise damage evaluation, underscoring their potential as invaluable tools for engineers, policymakers, and emergency responders in post-earthquake scenarios.

Machine learning-based rapid visual screening for building damage assessment: study of Joshimath town of Garhwal Himalaya, India

Machine learning-based rapid visual screening for building damage assessment: study of Joshimath town of Garhwal Himalaya, India

Multivariable fragility surfaces for earthquake-induced damage assessment of buildings integrating structural features

Multivariable fragility surfaces for earthquake-induced damage assessment of buildings integrating structural features

Mbda-net: a building damage assessment model based on a multi-scale fusion network

Mbda-net: a building damage assessment model based on a multi-scale fusion network

Remote Sensing Building Damage Assessment Based on Machine Learning

Abstract After the occurrence of various types of disasters, including natural disasters and man-made damage, aid workers need accurate and timely data, such as the damage status of buildings, in order to take effective measures for rescue. So as to solve this problem, this paper researches and designs a building damage classification system based on machine learning. The damage assessment system consists of two network models (building extraction network and damage classification network). This article analyzes and designs the structure of each network model, and discusses the principles related to computer vision in machine learning. Buildings in satellite images are segmented through Siamese Convolutional Neural Network, the BottleNeck Module and Feature Pyramid Network are used in the damage classification assessment network to detect damage to buildings in sub-temporal remote sensing images. Subsequently, the model was trained and tested on different disaster events on the xBD dataset. The results show that the building damage detection system based on Siamese-CNN achieves good detection accuracy, and the system has the advantages of simple operation, good timeliness and low resource consumption, and can well meet the needs of disaster assessment.

Flood damage models and flood damage factors in a data-scarce river basin, Nigeria

ABSTRACT To evaluate the effectiveness of various adaptation strategies, it is critical to develop a flood damage function that considers building characteristics for future risk evaluation. This study analysed the contributions of some important flood and household characteristics in flood damage processes and developed a new, more accurate, multi-variable flood loss model for flood damage assessment for residential buildings and contents, considering different house types in Ogun River Basin, Nigeria. A detailed household questionnaire survey was conducted to collect data (149 samples). Depth-damage functions were developed to estimate direct flood damage to building structures and contents using the nonlinear logistic and power (concave) models, and the model parameters were estimated using the Gauss–Newton algorithm. The performance of all flood damage regression analysis functions for building structures and building contents under different construction materials and basement floors was evaluated by comparing predicted damages and after-flood survey damages, which demonstrated acceptable comparativeness. In the event of a flood disaster in the area, the models can be used to forecast future damages and devise risk-mitigation strategies. The study’s findings will aid in developing flood protection adaptation measures.

Impact of ground motion uncertainty evolution from post-earthquake data on building damage assessment

Accurate damage assessment after an earthquake is crucial for effective emergency response. Using ground motion information enables rapid building damage assessment when detailed damage data are unavailable. While uncertainty in earthquake parameters plays a significant role in the accuracy of rapid estimations, it is usually treated as a constant parameter rather than as a dynamic parameter that considers the amount of ground motion data collected that evolve over time. This work investigates the impact of incorporating evolving ground motion uncertainty in ground motion estimations from US Geological Survey’s (USGS) ShakeMap on post-disaster damage assessments from two methodologies: the revised Thiel–Zsutty (TZR) model and Federal Emergency Management Agency’s (FEMA) Hazus. Using data from the 2020 Indios earthquake in Puerto Rico and the 2014 Napa earthquake, we find that changes in uncertainty in estimates of peak ground acceleration reach 65% between early and late versions of the ShakeMap. We propose a process to integrate this evolution with the two damage assessment methodologies through a Monte Carlo simulation-based approach, demonstrating that it is critical to introduce dynamic ground motion uncertainty in the damage assessment process to avoid propagating unreliable measures. Both methodologies show that resulting damage estimates can be characterized by narrower distributions, indicative of reduced uncertainty and increased precision in damage estimates. For the TZR model, an improved estimate of post-disaster loss is achieved with narrower bounds in distributions of expected high scenario loss. For Hazus, the results show potential changes in the most probable damage state with an average change of 13% in the most probable damage state. The described methodology also demonstrates how uncertainty in the resulting damage state distributions can be reduced compared with the use of the current Hazus methodology.

Field survey assessment of flood loads and related building damage from the July 2021 event in the Ahr Valley (Germany)

Field survey assessment of flood loads and related building damage from the July 2021 event in the Ahr Valley (Germany)

Bi-DAUnet: Leveraging BiFormer in a Unet-like Architecture for Building Damage Assessment

Abstract In recent years, Convolutional Neural Networks (CNNs) have become an important research direction in the field of building damage assessment. Particularly, deep neural networks based on the U-shaped architecture and skip connections have achieved significant breakthroughs in the task of architectural damage assessment. Despite the impressive performance of CNNs, effectively capturing global and long-range semantic information remains a challenge due to the local nature of their convolutional operations. To address this issue, we propose a novel architectural damage assessment model called Bi-DAUnet, which adopts a BiFormer structure similar to U-Net. In this model, we employ a U-shaped encoder-decoder architecture based on BiFormer and combine it with skip connections to achieve global semantic feature learning. Specifically, we utilize a hierarchical BiFormer with a dual-layer routing attention mechanism as the encoder to extract contextual features of architectural images. In the symmetric decoder, a BiFormer Block is introduced to fuse shallow and deep features of the feature maps and learn the correlation between pixels at distant locations. Experimental results indicate that the U-shaped encoder-decoder network based on BiFormer achieves superior performance in the task of architectural damage assessment compared to fully convolutional methods.

Large-scale building damage assessment based on recurrent neural networks using SAR coherence time series: A case study of 2023 Turkey–Syria earthquake

The Turkey–Syria earthquakes that occurred on February 6, 2023, have caused significant human casualties and economic damage. Emergency services require quick and accurate assessments of widespread building damage in affected areas. This can be facilitated by using remote sensing methods, specifically all-day and all-weather Synthetic Aperture Radar (SAR). In this study, we aimed to improve the detection of building anomalies in earthquake-affected areas using SAR images. To achieve this, we employed Recurrent Neural Network (RNN) to train coherence time series and predict co-seismic coherence. This approach allowed us to generate a Damage Proxy Map (DPM) for building damage assessment. The results of our study indicated that the estimated proportion of building damage in Kahramanmaras was approximately 24.08%. These findings were consistent with the actual damage observed in the field. Moreover, when utilizing the mean and standard deviation of coherence time series, our method achieved higher accuracy (0.761) and a lower false alarm rate (0.136) compared to directly using coherence with only two views of SAR data. Overall, our study demonstrates that this method provides an accurate and reliable approach for post-earthquake building damage assessment.

Building Damage Assessment in Aftermath of Disaster Events by Leveraging Geoai (Geospatial Artificial Intelligence): Review

Building Damage Assessment in Aftermath of Disaster Events by Leveraging Geoai (Geospatial Artificial Intelligence): Review

Integrating Machine Learning and Remote Sensing in Disaster Management: A Decadal Review of Post-Disaster Building Damage Assessment

Integrating Machine Learning and Remote Sensing in Disaster Management: A Decadal Review of Post-Disaster Building Damage Assessment

Optimising synthetic datasets for machine learning-based prediction of building damage due to tunnelling

Assessment of tunnelling-induced building damage is a complex Soil-Structure Interaction (SSI) probelm, influenced by numerous geometric and material parameters of both the soil and structures, and is characterised by strong non-linear behaviour. Currently, there is a trend towards developing data-driven models using Machine Learning (ML) to capture this complex behaviour. Given the scarcity of real data, which typically comes from specific case studies, many researchers have turned to creating extensive synthetic datasets via sophisticated and validated numerical models like Finite Element Method (FEM). However, the development of these datasets and the training of advanced ML algorithms present significant challenges. poses significant challenges. Reliance solely on parameter domains and ranges derived from case studies can lead to imbalanced data distributions and subsequently poor performance of models in less populated regions. In this paper, we introduce a strategy for designing optimal high-confidence datasets through an iterative procedure. This process begins with a systematic literature review to determine the importance of parameters, their ranges, and dependencies as they pertain to building damage induced by SSI. Starting with several hundred FEM simulations, we generate an initial dataset and assess its quality and impact through Sensitivity Analysis (SA) studies, statistical modelling, and re-sampling in statistically significant regions. This evaluation allows us to refine the model’s input space, seeking scenarios that mitigate output distribution imbalances. The procedure is repeated until the datasets achieve a satisfactory balance for training metamodels, minimising bias effectively. Our findings highlight the success of this approach in identifying an optimal and feasible input space that significantly reduces imbalanced distributions of output features. This approach not only proves effective in our study but also offers a versatile methodology that could be adapted to other disciplines aiming to generate high-quality synthetic datasets.