Degree Of Building Damage Research Articles

Building Damage Degree Recognition Based on Temporal Attention Features

Natural disasters pose significant harm to society. As an important place for social activities and economic development, the degree of damage to building areas is directly related to disaster loss assessment and emergency rescue. Remote sensing image data, characterized by its wide coverage and multi-temporal features, provides important data support for post-disaster loss assessment. However, imaging differences caused by factors such as shooting time, imaging angle, and different sensors can interfere with the extraction of damage features and loss assessment. This paper proposes a Dual-Exchange-Attention U-Net (DERU-Net) model, which transforms the identification of building damage levels into intra-class semantic change detection. The DFMA feature attention fusion module is introduced to enhance the ability of dual-temporal feature extraction and achieve end-to-end assessment of building damage. The proposed method is comprehensively evaluated and tested on the xBD dataset. Experimental results show that compared with other methods, the DERU-Net proposed in this paper exhibits better stability and evaluation accuracy in assessing the degree of building damage.

Classification of Building Damage Using a Novel Convolutional Neural Network Based on Post-Disaster Aerial Images.

The accurate and timely identification of the degree of building damage is critical for disaster emergency response and loss assessment. Although many methods have been proposed, most of them divide damaged buildings into two categories—intact and damaged—which is insufficient to meet practical needs. To address this issue, we present a novel convolutional neural network—namely, the earthquake building damage classification net (EBDC-Net)—for assessment of building damage based on post-disaster aerial images. The proposed network comprises two components: a feature extraction encoder module, and a damage classification module. The feature extraction encoder module is employed to extract semantic information on building damage and enhance the ability to distinguish between different damage levels, while the classification module improves accuracy by combining global and contextual features. The performance of EBDC-Net was evaluated using a public dataset, and a large-scale damage assessment was performed using a dataset of post-earthquake unmanned aerial vehicle (UAV) images. The results of the experiments indicate that this approach can accurately classify buildings with different damage levels. The overall classification accuracy was 94.44%, 85.53%, and 77.49% when the damage to the buildings was divided into two, three, and four categories, respectively.

Exploring the relationship between InSAR coseismic deformation and earthquake-damaged buildings

Strong ground vibration triggered by seismic waves is one of the most significant factors that causes building damage during a seismic event. The interferometric synthetic aperture radar (InSAR) technique can efficiently and quickly provide seismic deformation information. There is no clear relationship model between seismic deformation and the degree of building damage.Considering the earthquake that hit Wenchuan (China) on May 12, 2008, in this work, a method to evaluate the degree of building damage based on coseismic deformation is presented. Based on 51 building area samples selected, taking the Deformation normalization index(DNI) as the independent variable and the earthquake damage index (EDI) of the field survey data provided by the China Earthquake Administration (CEA) as the dependent variable, the relationships between seismic damage survey data and the seismic deformation of adobe structures, brick-wood structures, brick-concrete structures and reinforced concrete frame structures are analysed. There are linear relationships between the normalized deformation indices of adobe and brick-concrete structure types and the EDIs of buildings. There are quadratic relationships between the normalized seismic deformation indices of brick-wood structures and reinforced concrete frame construction types and the EDIs of buildings. Additionally, the regional curve estimates of the comprehensive building damage index and the normalized index of seismic deformation show that there is a quadratic relationship between the comprehensive building damage index and the normalized index of seismic deformation. The validity of the modelling method was verified by data from the Yushu earthquake in 2010. The results can provide an accurate and reliable reference basis for post-earthquake rescue and decision making.The work represents a new concept and method for the rapid assessment of building damage data from the perspective of surface deformation movement by addressing methodological steps, highlighting the potential of using the coseismic deformation field obtained during building damage assessment, and discussing the potential and limitations of InSAR technology in the field of damage detection.

Investigation of civil building damage and its spatial characteristics under 2019 ML6.0 Changning earthquake

An ML6.0 earthquake occurred at 22:55 on June 17, 2019, in Changning County, Yibin City, Sichuan Province, China. The Changning earthquake killed 13 people and affected an area of 3075 km2. The disaster caused by the earthquake is mainly the damage of civil buildings in the affected area. A field investigation on civil building damage was conducted by the authors after the earthquake occurrence. The destruction forms and damage area of civil buildings in 44 villages from different seismic intensity regions were collected and it was found that there are significant differences in the severity of building damage of different structure types. In order to analyse the spatial correlation between building damage and influencing factors, nine indicators are selected including structure type, PGA, elevation, slope angle, population density, per capita GDP, distance to river, distance to fault and NDVI, and damage ratio is defined to measure the degree of building damage in each village. The spatial correlation between civil building damage and influencing factors is analysed in GIS using histogram statistics and correlation analysis. The results show that PGA has the strongest correlation with civil building damage. In the area with greater seismic motion, the civil building damage is more serious. Structure type and economy level also have significant linear relationship with building damage.

Decision making on post-disaster rescue routing problems from the rescue efficiency perspective

The efficiency of emergency responses is at the heart of post-disaster rescue routing problems. Previous rescue models address the efficiency issue primarily by minimizing the total travel time, while not taking into account other significant factors in the rescue process, such as the number of affected people and the degree of building damage. To overcome these shortcomings, this paper aims to solve the rescue routing problem by maximizing the arc-based rescue efficiency, which is redefined as the ratio between the primary rescue input and output factors to represent the efficiency of the rescue operations. Therefore, a systematic methodology is proposed to decompose the original rescue routing problem into two decision making phases. First, an extended data envelopment analysis (DEA) model is constructed to evaluate the rescue efficiency along each arc. Specifically, a group decision constraint cone, which refers to the combined output of a group decision from experts, is constructed to distinguish the features and rescue focus of each disaster. Second, an efficiency-based routing model is developed to determine a feasible rescue tour for the entire transportation network, thus achieving the goal of maximizing the total rescue efficiency. An empirical example of a real earthquake disaster in Wenchuan, China, is provided to demonstrate the novelty and practical capabilities of the proposed approach in post-disaster emergency rescue operations. Finally, a comparison analysis is conducted with the traditional time-oriented routing method, and the results show that the method proposed in this study can improve the rescue performance by 21.2%.

Building damage mapping based on Touzi decomposition using quad-polarimetric ALOS PALSAR data

Building damage assessment is of great significance to disaster monitoring. Polarimetric Synthetic Aperture Radar (SAR) can record the polarization scattering measurement matrix of ground objects and obtain more abundant ground object information, meaning that they can be used for assessing damage to buildings. In this paper, a new approach is proposed to assess building damage using the Touzi incoherent decomposition and SAR-based characteristics of buildings before and after damage. The March 11th, 2011 earthquake that struck the coast of northeast Japan serves as the demonstration of the technique using quad-polarimetric ALOS PALSAR data acquired before and after the disaster. The analysis shows that after the buildings are damaged, there is a clear decrease in the αs1 (the dominant scattering-type magnitude) components and the degree of this reduction corresponds to the degree of building damage. This means that the αs1 components obtained by Touzi decomposition can effectively reflect the degree of building damage. On this basis, a model based on Touzi decomposition was established to evaluate the degree of damage to buildings, and the accuracy of the model was validated using high-resolution optical data acquired before and after the earthquake. The experimental results show that Touzi decomposition can be effectively used for damage assessment mapping in built-up areas.

Assessment of the Degree of Building Damage Caused by Disaster Using Convolutional Neural Networks in Combination with Ordinal Regression

We propose a new convolutional neural networks method in combination with ordinal regression aiming at assessing the degree of building damage caused by earthquakes with aerial imagery. The ordinal regression model and a deep learning algorithm are incorporated to make full use of the information to improve the accuracy of the assessment. A new loss function was introduced in this paper to combine convolutional neural networks and ordinal regression. Assessing the level of damage to buildings can be considered as equivalent to predicting the ordered labels of buildings to be assessed. In the existing research, the problem has usually been simplified as a problem of pure classification to be further studied and discussed, which ignores the ordinal relationship between different levels of damage, resulting in a waste of information. Data accumulated throughout history are used to build network models for assessing the level of damage, and models for assessing levels of damage to buildings based on deep learning are described in detail, including model construction, implementation methods, and the selection of hyperparameters, and verification is conducted by experiments. When categorizing the damage to buildings into four types, we apply the method proposed in this paper to aerial images acquired from the 2014 Ludian earthquake and achieve an overall accuracy of 77.39%; when categorizing damage to buildings into two types, the overall accuracy of the model is 93.95%, exceeding such values in similar types of theories and methods.

Earthquake damage and related factors associated with the 2016 ML = 5.8 Gyeongju earthquake, southeast Korea

The Gyeongju area covers the intersection of two major young structural features in Korea: the Yangsan and Ulsanfaults. More than 60 Quaternary fault sites have recently been reported along these fault zones, which are thus considered major active tectonic features in southeast Korea. An earthquake of local magnitude ML = 5.8 struck the Gyeongju area on September 12, 2016; the largest instrumental earthquake recorded in South Korea. We performed detailed investigation for severely damaged buildings and houses in villages around the epicenter, and determined the characteristics and controlling factors of the earthquake damage. The distribution of damaged buildings is relatively scattered around the epicenter, which may be related to the relatively deep focal depth of approximately 13–15 km. The radius of the reported damage area affected by ground motion is approximately 17 km from the epicenter, which is almost equal to the focal depth. Old buildings with traditional styles are more seriously damaged than modern buildings, suggesting that the damage intensity depends on the building structure, material properties, and seismic design. Interestingly, in a small village, the degree of building damage is clearly divided by a small stream. Based on an electrical resistivity survey for the local geological condition, we found that the degree of building damages also strongly depends on the local unconsolidated alluvium thickness. Moreover, the orientation of tilted or damaged buildings is closely related to the general trend of the related faults indicating the propagation direction of ground motion. Although focal depth, building style, and foundation condition are the main controlling factors to the building damages caused during the 2016 Gyeongju earthquake, other minor factors could also be involved. This information will be useful to design proper construction codes for reinforced buildings and for hazard studies against future earthquakes in potential earthquake prone areas.

Numerical modeling of interactions between a flow slide and buildings considering the destruction process

Flow slide is a flow-type landslide, which has high mobility and is destructive to the downstream infrastructures and buildings. In this study, a numerical method is presented to simulate the runout process of flow slide, and the interactions between flow slide and buildings on three-dimensional terrain considering the destruction process. In this proposed method, the flow slide is simulated by smoothed particle hydrodynamics (SPH) and the buildings are simulated by the finite element method (FEM). A node-to-surface contact algorithm is adopted to transfer displacements and contact forces between the flow slide and the buildings. An element erosion algorithm is adopted to simulate the destruction process. The method is validated using an analytical solution to dam break problem and the experimental results in two flume tests. A catastrophic flow slide involving building destruction is then simulated to further test the model performance. The flow depth, flow velocity, deposition area, and building damage degree are all reasonably simulated. The typical destruction process of buildings and patterns of the flow slide are also identified. The method will contribute to a better understanding of flow-structure interactions and is a promising tool for hazard analysis and mitigation.

Damage Detection Method for Buildings with Machine-Learning Techniques Utilizing Images of Automobile Running Surveys Aftermath of the 2016 Kumamoto Earthquake

In order to understand the damage situation immediately after the occurrence of a disaster and to support disaster response, we developed a method to classify the degree of building damage in three stages with machine-learning using road-running survey images obtained immediately after the Kumamoto earthquake. Machine-learning involves a learning phase and a discrimination phase. As training data, we used images from a camera installed in the travel direction of an automobile, in which the degree of damage was visually categorized. In the learning phase, class separation is carried out by support vector machine (SVM) on a basis of a feature calculated from training patch images for each extracted damage category. In the discrimination phase, input images are provided with raster scan so that the class separation is carried out in units of the patch image. In this manner, learning, discrimination, and parameter tuning are repeated. By doing so, we developed a damage-discrimination model for each patch image and validated the discrimination accuracy using a cross-validation method. Furthermore, we developed a method using an optical flow for preventing double counting of damaged areas in cases where an identical building is captured in multiple photos.

Using high-resolution satellite imagery to provide a relief priority map after earthquake

After the earthquake occurrence, collecting correct information about the extent of damage is essential for managing critical conditions and allocating limited resources. The prepared building damage maps sometimes bring about waste of time required for rescuing individuals under the rubble by wrongly conducting rescue teams toward regions with a lower rescue priority. In this research, an algorithm based on using a proposed standard at database level was developed to prioritize damaged buildings by considering five key elements of land use type, the degree of damage to buildings, the land use differentiation index, time of the highest population density in each land use, and time of disaster’s incidence. The steps of the proposed method which was implemented in the MATLAB environment include: detecting buildings on the pre- and post-event imagery, implementing texture features for each candidate building, choosing the optimal features by genetic algorithm, determining the degree of building damage in three classes of negligible damage, substantial damage, and heavy damage by using the difference between chosen features as inputs of the designed neurofuzzy inference system. Data collected from field observations were compared to the output obtained from the proposed algorithm. This comparison presented a general accuracy of 88% and Kappa coefficient of 79% in the classification of buildings into three damage classes. The proposed standard then was used for classifying damaged buildings into relief priorities of high, medium, and low. Findings revealed that the relief priority map could be a basis for correct guidance of relief and rescue teams during crucial times following earthquakes.

Building Damage Extraction from Post‐earthquake Airborne LiDAR Data

AbstractBuilding collapse is a significant cause of earthquake‐related casualties; therefore, the rapid assessment of buildings damage is important for emergency management and rescue. Airborne light detection and ranging (LiDAR) can acquire point cloud data in combination with height values, which in turn provides detailed information on building damage. However, the most previous approaches have used optical images and LiDAR data, or pre‐ and post‐earthquake LiDAR data, to derive building damage information. This study applied surface normal algorithms to extract the degree of building damage. In this method, the angle between the surface normal and zenith (0) is used to identify damaged parts of a building, while the ratio of the standard deviation to the mean absolute deviation () of θ is used to obtain the degree of building damage. Quantitative analysis of 85 individual buildings with different roof types (i.e., flat top or pitched roofs) was conducted, and the results confirm that post‐earthquake single LiDAR data are not affected by roof shape. Furthermore, the results confirm that θ is correlated to building damage, and that represents an effective index to identify the degree of building damage.

Building Damage Detection Using Object-Based Image Analysis and ANFIS From High-Resolution Image (Case Study: BAM Earthquake, Iran)

Building damage detection after earthquake would help to rapid relief and response of disaster. In this study, an efficient method was proposed for building damage detection in urban area after earthquake using pre-event vector map and postevent pan-sharpened high spatial resolution image. At first, preprocessing was applied on the postevent satellite image. Second, results of pixel- and object-based classifications were integrated. In the following, geometric features of buildings were extracted including area, rectangular fit ( $\text {rect\_fit}$ ), and convexity. A decision-making system based on these features and an adaptive network-based fuzzy inference system (ANFIS) model was designed to attain building damage degree. A comprehensive sensitivity analysis was carried out to find proper parameters of the ANFIS model leading to accurate damage results. The proposed method was tested over earthquake data set of Bam city in Iran. The results of our method indicate that an overall accuracy of 76.36% and kappa coefficient of 0.63 were achieved to identify building damage degree. The obtained results indicate that the postevent geometrical features (relative change of different damage levels with respect to each other) along with the ANFIS model can help to reach better results in building damage detection.

2015年ゴルカ，ネパール地震の衛星情報に対するグラウンド・トゥルース — 被害分布と旧市街の建物全棟調査 —

2015年ゴルカ，ネパール地震の衛星情報に対するグラウンド・トゥルース — 被害分布と旧市街の建物全棟調査 —

The physical vulnerability of different types of building structure to debris flow events

Vulnerability assessment of elements at risk is a key component for risk assessment. The representative element at risk for debris flow is a residential building in downstream mountain, and the physical vulnerability of such a building depends on the structural characteristics of a building. The main objective of this paper was to construct physical vulnerability curves for different types of building structures in Korea to enable a quantitative assessment of debris flow risks. The physical characteristics of debris flows were analyzed based on 11 debris flow events that occurred in July and August, 2011. A total of 25 buildings that were damaged during these events were investigated in detail to determine the characteristics and patterns of damage. This study analyzes the relationship between the degree of building damage and the intensity of the debris flows through field survey data, spatial data, and empirical formula. Three different empirical vulnerability curves were obtained as functions of the debris flow depth, the flow velocity, and the impact pressure. Furthermore, the vulnerability function was characterized according to the structural type of the buildings. In the case of non-RC buildings, complete destruction occurred with an impact pressure greater than 30 kPa. For RC buildings, slight damage occurred with impact pressures less than 35 kPa. The impact pressure of debris flows corresponding to slight damage to RC buildings could result in complete destruction of non-RC buildings. The physical vulnerability curves suggested here have potential applications in quantitative assessment of the structural resistance of buildings to debris flow events.

토석류에 의한 건물의 물리적 취약함수 특성

2011년 7월과 8월 사이에 발생한 총 8개 토석류 재해 지역에 대한 재해이력 사례를 분석하여 각 재해지역의 토석류 물리적 특성을 파악하였다. 또한 각 재해지역에서 피해를 입은 15개 건물에 대한 손상 특성 분석을 수행하였다. 토석류의 물리적 특성과 건물 손상정도를 바탕으로 토석류의 높이, 속도 및 충격압력으로 구성된 취약함수를 구하였다. 또한 보강 콘크리트 구조와 비 콘크리트 구조와 같은 건물의 구조 형식에 따른 취약함수를 각각 산출하였다. 비 콘크리트 건물의 경우 토석류 충격압이 30 kpa 이상일 때 완전 파괴, 15~30 kPa일 때 심각한 손상, 0~15 kPa일 때 경미한 손상이 발생하는 것으로 분석되었다. 이에 비해 보강 콘크리트 건물의 경우 100 kPa 이상에서 심각한 손상, 35~100 kpa일 때 보통 손상, 0~35 kPa일 때 경미한 손상을 입는 것으로 파악되었다. 콘크리트 건물의 경미한 손상에 대응하는 토석류 충격압은 비 콘크리트 건물에서는 완전 파괴에 해당되는 손상을 가져다 줄 수 있음을 의미한다. 건물 구조형식과 토석류 물리적 특성에 따른 취약곡선을 비선형 회귀분석을 수행하여 함수형태로 나타내었다. 이러한 토석류 취약함수는 토석류 재해로 피해가 발생할 가능성이 있는 지역의 건물손상 정도를 정량적으로 평가하는 방법으로 이용할 수 있다. The physical characteristics of debris flows were analyzed from a total of 8 cases of debris flow disasters occurred in between July and August, 2011. 15 buildings damaged in these events were also investigated in detail to study the characteristics and patterns of building damages by debris flows. Physical vulnerability was obtained from the relationship of the degree of building damage and the physical characteristics of debris flow. Three different empirical vulnerability curves were obtained, which were functions of debris flow height, flow velocity and impact pressure, respectively. Furthermore, the vulnerability function was characterized according to the structural types of the building. In the case of non-concrete building, a complete destruction occurred at the impact pressure of more than 30 kPa, an extensive damage at the impact pressure between 15 and 30 kPa, a slight damage at the impact pressure below 15 kPa. In the case of reinforced-concrete buildings, an extensive damage occurred at the impact pressure of more than 100 kPa, a moderate damage at the impact pressure between 35 and 100 kPa, a slight damage at the impact pressure below 35 kPa. The impact pressure of debris flow corresponding to a slight damage to the reinforced-concrete building produced a complete damage for the case of non-concrete building, Nonlinear regression analysis was performed according to the physical characteristics of debris flow and the building structural type. The proposed physical vulnerability curves could be used as a quantitative assessment of the structural resistance of buildings affected by a debris flow event.

Energy conservation validates deformation mechanisms around model cantilever wall excavations in sand

Based on soil movement measurements in two centrifuge models simulating cantilever wall excavation in dense and loose sand respectively, simplified deformation mechanisms are proposed on both sides of the wall. Negative dilation angles are used in the mechanism to model sand volume change at a moderate strain level corresponding with the typical serviceability limit of facilities on the retained ground within the zone of influence of the wall. An energy calculation is then performed for each of the two centrifuge tests to check the internal consistency of the inferred deformation mechanisms, and the adequacy of the stress–strain model used for the sand. It is found that energy balances within an error of 7% in both tests. The major energy flow happens on the active side of the wall, where the potential energy loss is roughly equal to the work done due to sand shear and contraction. The energy stored in wall bending and the energy lost due to boundary friction are small in comparison. The validated model of the settlement and shearing of the retained ground is then used to illustrate how to assess the degree of building damage in relation to angular distortion and tensile strain in the retained ground supporting its shallow foundations.

Potential damage assessment in buildings undergoing tilt

Estimation of the degree of building damage is a complex problem, because the potential sources of damage are various. The main components of building movement for damage assessment are tilt, angular distortion, horizontal strain and deflection ratio. Some of these parameters are interrelated. In this study, damage criteria are developed that correlate the building damage with the most critical components of movement, namely deflection ratio, horizontal strain and tilt. The building wall is idealised as a simply supported elastic deep beam loaded by both vertical and horizontal forces. Equations of maximum tensile strain within the beam are developed under the concept of limiting tensile strains in order to study the onset of cracking in buildings with various wall dimensions and material properties. A number of case studies of tilted buildings are used to verify the approach.

Assessment of the degree of building damage caused by the 2010 Yushu, China earthquake using satellite and airborne data

Until now, prevention of earthquakes is rarely achieved and earthquakes continue to pose an increasing threat to life and property. For search and rescue operations, rapid, accurate and reliable information about the building damage and damage distribution is in great need in the critical post-event hours. Fortunately, remote sensing data from satellites and airborne platforms can provide valuable information for detecting the building damage due to earthquakes. In this study, satellite and airborne images were processed to assess the degree of building damage caused by the Yushu, China earthquake on 14 April 2010. The selected study area enclosed part of Jiegu town, which was one of the areas most strongly hit by the earthquake. Combining with the pre-earthquake data of Yushu County from a Google Earth screenshot, we visually interpreted post-earthquake and pre-earthquake buildings in every region, and acquired the degree of building damage. The result shows that in every region of the study area, buildings with brick-clay or brick-wood structures showed characteristics of complete damage over a large area. The alluvial cone has a flat and solid surface but the lower soil is soft, so its structure is not stable enough to withstand a serious earthquake.

Post-earthquake assessment of building damage degree using LiDAR data and imagery

Various methods have been developed to detect and assess building’s damages due to earthquakes using remotely sensed data. After the launch of the high resolution sensors such as IKONOS and QuickBird, it becomes realistic to identify damages on the scale of individual building. However the low accuracy of the results has often led to the use of visual interpretation techniques. Moreover, it is very difficult to estimate the degree of building damage (e.g. slight damage, moderate damage, or severe damage) in detail using the existing methods. Therefore, a novel approach integrating LiDAR data and high resolution optical imagery is proposed for evaluating building damage degree quantitatively. The approach consists of two steps: 3D building model reconstruction and rooftop patch-oriented 3D change detection. Firstly, a method is proposed for automatically reconstructing 3D building models with precise geometric position and fine details, using pre-earthquake LiDAR data and high resolution imagery. Secondly, focusing on each rooftop patch of the 3D building models, the pre- and post-earthquake LiDAR points belonging to the patch are collected and compared to detect whether it was destroyed or not, and then the degree of building damage can be identified based on the ratio of the destroyed rooftop patches to all rooftop patches. The novelty of the proposed approach is to detect damages on the scale of building’s rooftop patch and realize quantitative estimation of building damage degree.