Building Damage Information Research Articles

Incorporating multi-source remote sensing in the detection of earthquake-damaged buildings based on logistic regression modelling

After an earthquake, efficiently and accurately acquiring information about damaged buildings can help reduce casualties. Earth observation data have been widely used to map affected areas after earthquakes. However, fine post-earthquake assessment results are needed to manage recovery and reconstruction and to estimate economic losses. In this paper, for quantification and precision purposes, a method of earthquake-induced building damage information extraction incorporating multi-source remote sensing data is proposed. The method consists of three steps： (1) Analysis of multisource features that describe texture, colour, and geometry, (2) rough set theory is carried out to further determine the feature parameters, (3) Logistic regression model (LRM) was built to describe the relationship between the occurrence and absence of destroyed buildings within an individual object. Old Beichuan County (centered at approximately 31.833︒N, 104.459° E), China, the area most devastated by the Wenchuan earthquake on May 12, 2008, is used to test the proposed hypothesis. Multi-source remote sensing imagery include optical data, synthetic aperture radar (SAR) data, and digital surface model (DSM) data generated by interpolating light detection and ranging (LiDAR) point cloud data. Through comparison with the ground survey, the experimental results show that the detection accuracy of the proposed method is 94.2 %; the area under the receiver operating characteristic (ROC) curve is 0.827. The efficiency of the proposed method is demonstrated using 6 modes of data combination acquired from the same area in old Beichuan County. The approach is one of the first attempts to extract damaged buildings through the fusion of three types of data with different features. The approach addresses multivariate regression methodologies and compares the potential of features for application in the damage detection field.

Cascaded framework for earthquake building damage detection combining spatial and frequency domain feature integration

Abstract. Building collapse is a major cause of casualties after an earthquake, so accurately extracting building damage information is critical for post-earthquake assessment and rescue. Currently, most deep learning methods focus on the end-to-end detection of building collapse. However, in real-world earthquake scenarios, the end-to-end computational process often lacks flexibility and struggles to meet the requirements of rapid emergency response. To address this issue, this paper proposes a cascaded framework that combines pre-earthquake building extraction and post-earthquake building damage classification. The proposed framework includes two sections: (1) Progressive building semantic segmentation model in the joint frequency domain. This model is designed to accurately extract buildings prior to an earthquake, with the goal of minimizing error propagation throughout the cascading process. The model addresses the spatial similarity of buildings under complicated backgrounds, as well as the high internal heterogeneity of buildings, by utilizing frequency domain techniques. It compensates for the shortcomings of traditional models in terms of incomplete information extraction through the effective integration of global and local information. Finally, the model employs edge priors for edge regularization. (2) Rapid building damage classification process. Based on the accurate building extraction results, a fast and efficient classification process is developed. This process uses a simple and lightweight classification network to effectively extract building damage information caused by the earthquake. The superiority of the proposed framework is validated through comparison with traditional cascading architectures and end-to-end models. The results show that the cascading framework not only provides accurate pre-earthquake building extraction, but also enables efficient and accurate post-earthquake damage classification, which meets the requirements of rapid post-earthquake emergency response. This balance of accuracy and speed is essential for effective disaster management and recovery.

BDHE-Net: A Novel Building Damage Heterogeneity Enhancement Network for Accurate and Efficient Post-Earthquake Assessment Using Aerial and Remote Sensing Data

Accurate and efficient post-earthquake building damage assessment methods enable key building damage information to be obtained more quickly after an earthquake, providing strong support for rescue and reconstruction efforts. Although many methods have been proposed, most have limited effect on accurately extracting severely damaged and collapsed buildings, and they cannot meet the needs of emergency response and rescue operations. Therefore, in this paper, we develop a novel building damage heterogeneity enhancement network for pixel-level building damage classification of post-earthquake unmanned aerial vehicle (UAV) and remote sensing data. The proposed BDHE-Net includes the following three modules: a data augmentation module (DAM), a building damage attention module (BDAM), and a multilevel feature adaptive fusion module (MFAF), which are used to alleviate the weight deviation of intact and slightly damaged categories during model training, pay attention to the heterogeneous characteristics of damaged buildings, and enhance the extraction of house integrity contour information at different resolutions of the image. In addition, a combined loss function is used to focus more attention on the small number of severely damaged and collapsed classes. The proposed model was tested on remote sensing and UAV images acquired from the Afghanistan and Baoxing earthquakes, and the combined loss function and the role of the three modules were studied. The results show that compared with the state-of-the-art methods, the proposed BDHE-Net achieves the best results, with an F1 score improvement of 6.19–8.22%. By integrating the DBA, BDAM, and MFAF modules and combining the loss functions, the model’s classification accuracy for severely damaged and collapsed categories can be improved.

Scalable and rapid building damage detection after hurricane Ian using causal Bayesian networks and InSAR imagery

Timely and accurate assessment of hurricane-induced building damage is crucial for effective post-hurricane response and recovery efforts. Recently, remote sensing technologies provide large-scale optical or Interferometric Synthetic Aperture Radar (InSAR) imagery data immediately after a disastrous event, which can be readily used to conduct rapid building damage assessment. Compared to optical satellite imageries, the Synthetic Aperture Radar can penetrate cloud cover and provide more complete spatial coverage of damaged zone in various weather conditions. However, these InSAR imageries often contain highly noisy and mixed signals induced by co-occurring or co-located building damage, flood, flood/wind-induced vegetation changes, as well as anthropogenic activities, making it challenging to extract accurate building damage information. In this paper, we introduced a causality-informed Bayesian network inference approach for rapid post-hurricane building damage detection from InSAR imagery. This approach encoded complex causal dependencies among wind, flood, building damage, and InSAR imagery using a holistic causal Bayesian network. Based on the causal Bayesian network, we further jointly inferred the large-scale unobserved building damage by fusing the information from InSAR imagery with prior physical models of flood and wind, without the need for ground truth labels. Furthermore, we validated our estimation results in a real-world devastating hurricane—the 2022 Hurricane Ian. We gathered and annotated building damage ground truth data in Lee County, Florida, and compared the introduced method’s estimation results with the ground truth and also benchmarked it against state-of-the-art models to assess the effectiveness of our proposed method. The results show that our method advances building damage assessment after hurricanes by accurately reflecting the complex dynamics between wind and flood impacts. Notably, it achieves this without the need for a ground truth label, which is a substantial step forward from traditional methods. Our model registers a 22.6% increase in the Area Under the Curve (AUC) and a 46.29% enhancement in the True Positive Rate (TPR). Moreover, it expedites the detection of building damage, cutting down processing times by up to 83.8%. These improvements mark a considerable leap in efficiency, demonstrating our method’s ability to streamline the assessment process markedly over conventional methods.

Automating Building Damage Reconnaissance to Optimize Drone Mission Planning for Disaster Response

Rapid reconnaissance of building damage is critical for disaster response and recovery. Drones have been utilized to collect aerial images of affected areas in order to assess building damage. However, there are two challenges. First, processing many aerial images to detect and classify building damage based on a consistent standard remains laborious and complex, necessitating a new automated solution to achieve accurate building damage detection and classification. Second, drone operations during disaster response rely primarily on human operators’ experience and seldom use the obtained building damage information to optimize drone mission planning. Therefore, this study proposes a new method, which automates building damage reconnaissance with drone mission planning for disaster response operations. Specifically, a deep learning method is developed to detect and classify building damages using a newly labeled dataset consisting of 24,496 distinct instances of building damage. This deep learning method is validated, achieving 71.9% mean average precision. In addition, building damage information is modeled and integrated into mission planning, in order to optimize drones’ task assignments and route calculations. A tornado disaster in Tennessee is used as a case study to quantitatively evaluate this methodology. The present study concludes that optimal drone mission planning during disaster response can be augmented using accurate building damage information acquired from deep learning methods.

Earthquake-induced building damage recognition from unmanned aerial vehicle remote sensing using scale-invariant feature transform characteristics and support vector machine classification

Building damage is the main cause of casualties and economic losses from earthquakes. Therefore, understanding building damage is critical for emergency handling. Current information acquisition methods for assessing earthquake damage using unmanned aerial vehicle (UAV) remote sensing systems offer great flexibility and high efficiency with the capability to obtain high-resolution images, which can reflect actual damage to affected areas intuitively. Consequently, UAV remote sensing has become a convenient and important means to acquire earthquake-induced building damage information. Although manual visual interpretation can achieve high recognition accuracy, it is extremely time-consuming. In contrast, although current automatic recognition methods require less time, they have relatively poor recognition accuracy. Neither approach can satisfactorily simultaneously meet efficiency and accuracy requirements for earthquake emergency handling. This article applies image classification algorithms based on the support vector machine (SVM) to earthquake-induced building damage recognition, and proposes a recognition method based on scale-invariant feature transform (SIFT) characteristics and SVM classification. We use the magnitude 6.4 earthquake at Yangbi (2021) as an example to validate the proposed method. Results verify that the proposed method can recognize earthquake damage quickly and accurately, providing effective support for decision-making regarding rescue actions.

A METHOD OF DISASTER-DAMAGED BUILDING SAMPLE LIBRARY CONSTRUCTION BASED ON TRANSFER LEARNING

Abstract. In recent years, the analysis of satellite remote sensing data using deep learning methods has become an important solution in the field of disaster response. The sample library can provide knowledge support for deep learning tasks in a research area, and its sample size and labeling accuracy directly determine the model effectiveness. However, the traditional sample library is often constructed by manual annotation, which is time-consuming and less automated. This research explores a transfer learning method to automate the construction of a sample library of building damage. We used models instead of manual work to automatically annotate the damage information of disaster images, combined with an auxiliary manual inspection to achieve high quality and dynamic optimization of the sample library. Following are three main aspects of research work. (1) This study extensively collected remote sensing images related to disaster events, and carried out data pre-processing work. (2) This study built a building damage information identification model based on the U-Net framework, which applied pre-trained backbone model and was formally trained on xBD dataset. (3) With CycleGAN to implement color style transfer between RS images collected from two different data sources, we constructed a high-quality building damage sample library, mainly by automatic machine labeling and supplemented by manual sampling verification. Finally, we successfully constructed a sample library of disaster-damaged building images, and conducted several rounds of manual precision sampling work and dynamic optimization work. The number of image slices in the sample library reached 12,834, and the overall accuracy is higher than 0.80 under the manual inspection of 200 samples.

Semantic segmentation recognition model for tornado-induced building damage based on satellite images

To address the problem of imbalanced data of damaged building samples generated after a tornado disaster in Kaiyuan, this paper proposes overlapping sampling and improved loss function to improve the performance of the study models in identifying building damage information. In this paper, UNet-Vgg16, UNet-Resnet50, DeepLabv3plus-Xception and DeepLabv3plus-MobileNetV2 semantic segmentation models are used to extract the damage information of buildings after the Kaiyuan tornado. Overlapping sampling can expand the sample size of positive building samples, while the removal of all negative samples in a dataset can further reduce the impact of data imbalance. It is proposed that Focal loss and Dice loss be combined as the loss function to solve the imbalance problem of the study sample. The mPA, mIoU and mF1-Score of the identification results for the dataset without overlapping sampling using Ce loss of Unet-Vgg16 were 74.9%, 65.35% and 79.55%, respectively. The UNet-Vgg16 model which combines both the Focal loss and Dice loss as the loss function identifies the dataset best with overlapping sampling; it removes all negative samples, with its mPA, mIoU and F1-score reaching 94.1%, 89.25% and 93.85%, respectively. The optimization method proposed in this paper for imbalanced data can improve the recognition performance of the model for building damage information.

Post-disaster building damage assessment based on improved U-Net

When a severe natural disaster occurs, the extraction of post-disaster building damage information is one of the methods to quickly obtain disaster information. The increasingly mature high-resolution remote sensing technology provides a solid foundation for obtaining information about building damage. To address the issues with inaccurate building positioning in existing building damage assessment methods, as well as poor classification due to similar minor and major damage characteristics in building damage classification. Based on U-Net, we designed a two-stage building damage assessment network. The first stage is an independent U-Net focused on building segmentation, followed by a Siamese U-Net focused on building damage classification. The Extra Skip Connection and Asymmetric Convolution Block were used for enhancing the network's ability to segment buildings on different scales; Shuffle Attention directed the network's attention to the correlation of buildings before and after the disaster. The xBD dataset was used for training and testing in the study, and the overall performance was evaluated using a balanced F-score (F1). The improved network had an F1 of 0.8741 for localization and F1 of 0.7536 for classification. When compared to other methods, it achieved better overall performance for building damage assessment and was able to generalize to multiple disasters.

Operational earthquake-induced building damage assessment using CNN-based direct remote sensing change detection on superpixel level

• Superpixel-based direct change detection is capable of finding damages efficiently. • Extra feature enhancement bands accelerate the process of damage assessment. • Channel-expanded CNN model benefits simultaneous building damage analysis. • The potential of the proposed method in post-earthquake emergency is recognized. Accurate and quick building damage assessment is an indispensable step after a destructive earthquake. Acquiring building damage information of the seismic area in a remotely sensed way enables a timely emergency response. Existing remote sensing building damage detection methods based on convolutional neural network (CNN) mainly need two-step processing or only use single post-event image, leading to low efficiency and inaccurate building boundary. Considering the practical needs of emergency rescue and post-disaster reconstruction, this study proposed a hierarchical building damage assessment workflow using CNN-based direct remote sensing change detection on superpixel level. First, vulnerable building areas close to the epicenter are extracted using extra feature enhancement bands (EFEBs) to narrow the extent of image processing. Then, fine scale building damage is detected in the extracted building areas based on a direct change detection method with pre-event superpixel constraint (PreSC) strategy to improve the precision and efficiency. Finally, a rapid remote sensing earthquake damage index (rRSEDI) is used to quantitatively assess the damage. Experimental results of the case study show that damaged buildings can be effectively and accurately localized and classified using the proposed workflow. Comparative experiments with single-temporal image and post-event segmentation further embody the superiority of the direct change detection. The damage assessment result matches the official report after Ludian earthquake, proving the reliability of the proposed workflow. For future natural hazard events, the workflow can contribute to formulating appropriate disaster management, prevention and mitigation policies.

Factors affecting earthquake responders’ building damage information needs and use

After an earthquake, many responding organizations need to understand the scale and distribution of building damage to react effectively. However, their building damage information needs and information use remain poorly understood, limiting the efficacy of information production, sharing, and research. To clarify those needs, we conducted a two-part survey, comprising semi-structured interviews and an online questionnaire, of building damage information users and providers. Based on the interview data and questionnaire responses, we characterize six post-disaster tasks that rely on building damage information by their timing and by the necessary qualities of the information they require. Through inductive analysis of the interview data, we show that responders’ use of building damage information also depends on factors beyond the building damage information itself—namely, trust, impediments to information sharing, their varying understandings of disaster, and their attitudes toward emerging technologies. These factors must be considered in the design of any effort to create and/or disseminate post-disaster building damage information.

Physical Flood Vulnerability Assessment using Geospatial Indicator-Based Approach and Participatory Analytical Hierarchy Process: A Case Study in Kota Bharu, Malaysia

The most devastating flood event in Kota Bharu was recorded in December 2014, which affected several properties worth millions of dollars and thousands of homes. Damage to physical properties, especially buildings, is identified as a significant contributor to flood disasters in Malaysia. Therefore, it is essential to address physical flood vulnerability by developing an integrated approach for modeling buildings’ flood vulnerability to decrease the flood consequences. This study aims at developing a flood vulnerability assessment approach using an indicator-based model (IBM) for individual buildings in Kota Bahru, Kelantan, Malaysia. An intensive literature review and expert opinions were used to determine suitable indicators that contribute to the physical flood vulnerability of buildings. The indicators were grouped into three components, i.e., flood hazard intensity (I), building characteristics (C), and effect of the surrounding environment (E). The indicators were further refined based on expert opinions and Relative Importance Index (RII) analysis. Based on their contribution to the Malaysia local building flood vulnerability, priority weight is assigned by the experts to each of the selected indicators using the participatory Analytical Hierarchy Process (AHP). A spatial database of buildings in Kota Bharu is developed through field surveys and manually digitizing building footprints from satellite imageries. The identified indicators and their weight are added to each building footprint. The Weighted Linear Combination (WLC) aggregation method combined the weight of indicators into a vulnerability index and maps. The results of a physical flood vulnerability were validated using building damage information obtained through interviews with the community that experienced previous flood in the study area. The result showed that about 98% of the study area’s buildings have either moderate or low vulnerability to flooding. The flood vulnerability map has an overall accuracy of 75.12% and 0.63 kappa statistics. In conclusion, the IBM approach has been used successfully to develop a physical flood vulnerability for buildings in Kota Bharu. The model contributes to support different structural and non-structural approaches in the flood mitigations process.

Damaged building extraction from post-earthquake PolSAR data based on the Fourier transform

ABSTRACT Due to the casualties and economic losses that can be caused by building collapse after an earthquake, building damage assessment is a very important part of earthquake disaster evaluation. As a result of the advantages of polarimetric synthetic aperture radar (PolSAR) imaging, both the accuracy and speed of the damage assessment can be guaranteed in the process of building damage identification using a single post-earthquake PolSAR image. The number of collapsed buildings is usually overestimated when adopting the traditional method, which is because the scattering mechanism is similar to that of intact oriented buildings. In view of this, the variable coefficient of angle domains based on the Fourier amplitude spectrum parameter (CV_AFI) is proposed to ameliorate the damaged building overestimation. By combining the improved Yamaguchi four-component decomposition method with the CV_AFI parameter, the proposed method can be used to extract building damage information from a single PolSAR image. With the Ms 7.1 Yushu earthquake in China as the research case, compared with the traditional method, the producer’s accuracy of the proposed method for undamaged buildings was increased by 38.87%. The proposed method can obtain a higher accuracy of building damage information extraction and significantly reduce building damage overestimation.

A machine learning damage prediction model for the 2017 Puebla-Morelos, Mexico, earthquake

The 2017 Puebla, Mexico, earthquake event led to significant damage in many buildings in Mexico City. In the months following the earthquake, civil engineering students conducted detailed building assessments throughout the city. They collected building damage information and structural characteristics for 340 buildings in the Mexico City urban area, with an emphasis on the Roma and Condesa neighborhoods where they assessed 237 buildings. These neighborhoods are of particular interest due to the availability of seismic records captured by nearby recording stations, and preexisting information from when the neighborhoods were affected by the 1985 Michoacán earthquake. This article presents a case study on developing a damage prediction model using machine learning. It details a framework suitable for working with future post-earthquake observation data. Four algorithms able to perform classification tasks were trialed. Random forest, the best performing algorithm, achieves more than 65% prediction accuracy. The study of the feature importance for the random forest shows that the building location, seismic demand, and building height are the parameters that influence the model output the most.

Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN Model

The building is an indispensable part of human life which provides a place for people to live, study, work, and engage in various cultural and social activities. People are exposed to earthquakes, and damaged buildings caused by earthquakes are one of the main threats. It is essential to retrieve the detailed information of affected buildings after earthquakes. Very high-resolution satellite imagery plays a key role in retrieving building damage information since it captures imagery quickly and effectively after the disaster. In this paper, the pretrained Visual Geometry Group (VGG)Net model was applied for identifying collapsed buildings induced by the 2010 Haiti earthquake using pre- and post-event remotely sensed space imagery, and the fine-tuned pretrained VGGNet model was compared with the VGGNet model trained from scratch. The effects of dataset augmentation and freezing different intermediate layers were also explored. The experimental results demonstrated that the fine-tuned VGGNet model outperformed the VGGNet model trained from scratch with increasing overall accuracy (OA) from 83.38% to 85.19% and Kappa from 60.69% to 67.14%. By taking advantage of dataset augmentation, OA and Kappa went up to 88.83% and 75.33% respectively, and the collapsed buildings were better recognized with a larger producer accuracy of 86.31%. The present study showed the potential of using the pretrained Convolutional Neural Network (CNN) model to identify collapsed buildings caused by earthquakes using very high-resolution satellite imagery.

Building Damage Assessment Based on the Fusion of Multiple Texture Features Using a Single Post-Earthquake PolSAR Image

After a destructive earthquake, most of the casualties are brought about by building collapse. Our work is focused on using a single postevent PolSAR (full-polarimetric synthetic aperture radar) imagery to extract the building damage information for effective emergency decision-making. PolSAR data is subject to sunlight and contains richer backscatter information. The undamaged buildings whose orientation is not parallel to the SAR flight pass and the collapsed buildings share similar dominated scattering mechanisms, i.e., volume scattering, so they are easily confused. However, the two kinds of buildings have different textures. For a more accurate classification of damaged buildings and undamaged buildings, the OPCE (optimization of polarimetric contrast enhancement) algorithm is employed to enhance the contrast ratio of the textures for the two kinds of buildings and the precision-weighted multifeature fusion (PWMF) method is proposed to merge the multiple texture features. The experiment results show that the accuracy of the proposed novel method is improved by 8.34% compared to the traditional method. In general, the proposed PWMF method can effectively merge the multiple features and the overestimation of the building collapse rate can be reduced using the proposed method in this study.

THE DETERMINATION METHOD OF EXTREME EARTHQUAKE DISASTER AREA BASED ON THE DUST DETECTION RESULT FROM GF-4 DATA

Abstract. The remote sensing has played an important role in many earthquake emergencies by rapidly providing the building damage, road damage, landslide and other disaster information. The earthquake in the mountains often caused to the loosening of the mountains and the blowing of the dust in the epicentre area. The dust particles are more serious in the epicentre area than the other disaster area. Basis on the analysis of abnormal spectrum characteristics, the dust detection methods from medium and high resolutions satellite imagery are studied in order to determinate the extreme earthquake disaster area. The results indicate the distribution of extreme disaster can be acquired using the dust detection information from imagery, which can provide great help for disaster intensity assessment.

BUILDING DAMAGE EXTRACTION TRIGGERED BY EARTHQUAKE USING THE UAV IMAGERY

Abstract. When extracting building damage information, we can only determine whether the building is collapsed using the post-earthquake satellite images. Even the satellite images have the sub-meter resolution, the identification of slightly damaged buildings is still a challenge. As the complementary data to satellite images, the UAV images have unique advantages, such as stronger flexibility and higher resolution. In this paper, according to the spectral feature of UAV images and the morphological feature of the reconstructed point clouds, the building damage was classified into four levels: basically intact buildings, slightly damaged buildings, partially collapsed buildings and totally collapsed buildings, and give the rules of damage grades. In particular, the slightly damaged buildings are determined using the detected roof-holes. In order to verify the approach, we conduct experimental simulations in the cases of Wenchuan and Ya’an earthquakes. By analyzing the post-earthquake UAV images of the two earthquakes, the building damage was classified into four levels, and the quantitative statistics of the damaged buildings is given in the experiments.

THE EXTRACTION OF POST-EARTHQUAKE BUILDING DAMAGE INFORMATIOM BASED ON CONVOLUTIONAL NEURAL NETWORK

Abstract. The seismic damage information of buildings extracted from remote sensing (RS) imagery is meaningful for supporting relief and effective reduction of losses caused by earthquake. Both traditional pixel-based and object-oriented methods have some shortcoming in extracting information of object. Pixel-based method can’t make fully use of contextual information of objects. Object-oriented method faces problem that segmentation of image is not ideal, and the choice of feature space is difficult. In this paper, a new stratage is proposed which combines Convolution Neural Network (CNN) with imagery segmentation to extract building damage information from remote sensing imagery. the key idea of this method includes two steps. First to use CNN to predicate the probability of each pixel and then integrate the probability within each segmentation spot. The method is tested through extracting the collapsed building and uncollapsed building from the aerial image which is acquired in Longtoushan Town after Ms 6.5 Ludian County, Yunnan Province earthquake. The results show that the proposed method indicates its effectiveness in extracting damage information of buildings after earthquake.

Building damage assessment using a single post-earthquake PolSAR image: a case of the 2010 Yushu earthquake

Earthquakes are one of the most destructive natural disasters. Efficiently and quickly acquiring building earthquake damage information can help to reduce the casualties after an earthquake. In this paper, building damage information is extracted using a single post-earthquake PolSAR image. In PolSAR images, since the undamaged oriented buildings characterized by volume scattering with weaker scattering power are very similar to collapsed buildings, the collapsed buildings are difficult to extract accurately. In this paper, the difference in the relative contribution change rate of scattering components before and after polarization orientation angle (POA) compensation is proposed to enhance the difference between collapsed buildings and oriented buildings, in order that the collapsed buildings can be extracted more accurately. The “4.14” Yushu earthquake, which occurred in Yushu County, Qinghai province of China, is used as the case study to test the proposed method, and an airborne high-resolution PolSAR image of the urban region of Yushu County is used in the experiment. The experimental results show that the accuracy of building damage information extraction can be improved by the use of the proposed method, compared with the traditional polarimetric classification.