Building Damage Assessment Research Articles

An Efficient and Uncertainty-Aware Decision Support System for Disaster Response Using Aerial Imagery

Efficient and robust search and rescue actions are always required when natural or technical disasters occur. Empowered by remote sensing techniques, building damage assessment can be achieved by fusing aerial images of pre- and post-disaster environments through computational models. Existing methods pay over-attention to assessment accuracy without considering model efficiency and uncertainty quantification in such a life-critical application. Thus, this article proposes an efficient and uncertain-aware decision support system (EUDSS) that evolves the recent computational models into an efficient decision support system, realizing the uncertainty during building damage assessment (BDA). Specifically, a new efficient and uncertain-aware BDA integrates the recent advances in computational models such as Fourier attention and Monte Carlo Dropout for uncertainty quantification efficiently. Meanwhile, a robust operation (RO) procedure is designed to invite experts for manual reviews if the uncertainty is high due to external factors such as cloud clutter and poor illumination. This procedure can prevent rescue teams from missing damaged houses during operations. The effectiveness of the proposed system is demonstrated on a public dataset from both quantitative and qualitative perspectives. The solution won the first place award in International Overhead Imagery Hackathon.

Structural and nonstructural damage assessment of steel buildings equipped with self-centering energy-absorbing rocking core systems: A comparative study

Self-centering energy-absorbing rocking core (SCENARIO) systems are emerging aseismic structural systems developed for obtaining excellent self-centering and collapse-resistant performance with negligible residual inter-story drifts in steel buildings under strong earthquakes. Despite its demonstrated superior structural performance, the nonstructural performance of SCENARIO systems, which is another essential consideration in seismic resilience evaluation of building structures, has not been well studied. For filling this research gap, this paper aims to make the original contributions by systematically assessing the structural and nonstructural damage of steel building structures equipped with SCENARIO systems under earthquakes and finding the efficient solution for enhancing the structural and nonstructural damage-control performance of SCENARIO systems. Two types of SCENARIO systems, including the SCENARIO system with friction spring dampers (denoted as SCENARIO-F system) and the SCENARIO system with hybrid dampers (denoted as SCENARIO-H system), were considered in this research. Three prototype steel buildings with SCENARIO systems were designed to achieve the same target displacement under design basis earthquakes (DBE). Incremental dynamic analyses (IDAs) were performed to study the seismic responses of the designed buildings subjected to far-field and near-fault ground motions with different intensities. The collapse-resistant performance, structural damage, post-earthquake repairability, and nonstructural damage of the designed buildings were investigated via seismic fragility analyses based on IDA results. Seismic fragility analysis results indicate that the SCENARIO-H systems show better performance than the SCENARIO-F systems in controlling structural and nonstructural damage under both far-field and near-fault earthquakes with high intensities. Benefiting from excellent self-centering capacity, the buildings equipped with SCENARIO-F and SCENARIO-H systems can show excellent post-earthquake repairability under strong earthquakes.

A cost-benefit analysis of sensor quality and spatial density for rapid regional post-event seismic damage assessment: Application to Istanbul

A quantitative evaluation of the influence of sensor quality and spatial density on the results of rapid regional seismic damage evaluations of buildings can provide an important reference for the deployment of a strong-motion network. However, the influence of sensor quality and spatial density on seismic damage assessment is still unclear. Therefore, a cost-benefit analysis framework of sensor quality and spatial density for rapid regional post-event seismic damage assessment is proposed. In this framework, a simulation method for sensor-recorded ground motions and an interpolation-based ground motion field refinement method are used to consider the influence of the quality and density of the sensor network. The accuracies of seismic damage assessments with different sensor layout schemes were compared using the time-history analysis-based regional seismic damage assessment method, through which the influence of sensor quality and spatial density on the seismic damage assessment can be quantitatively evaluated. Finally, the Zeytinburnu district of Istanbul was selected as an example for illustrating the proposed framework. The main conclusions are as follows: (1) the spatial density of the sensors used is more significant for improving the accuracy of a seismic damage assessment than the quality of the sensors used; (2) the influence of population density can be considered using the proposed framework; and (3) the proposed framework can quantitatively consider the influence of sensor quality and spatial density on the rapid regional seismic damage assessment of buildings, which provides an important reference for the deployment of a strong-motion network for a given budget.

Evaluation of geopolymer concrete at high temperatures: An experimental study using machine learning

Studying the mechanical performance of concrete after being exposed to high temperatures is an important step in the damage assessment of buildings and fire safety applications. However, predicting the compressive strength of GPC accurately after exposure to high temperatures is a challenging task. In this paper, artificial neural network (ANN) and support vector regression (SVR) models were developed to predict the compressive strength of geopolymer concrete (GPC) at high temperatures ranging from 100 °C to 1000 °C. A series of experiments consisting of different mix designs were conducted at elevated temperatures to prepare a dataset. Besides experiments' results, the data of previously published studies were also collected and used. Monte Carlo simulations were performed to study the effect of inputs' uncertainties on models’ outputs and generate probability curves. Feature importance analysis was performed to investigate the significance of inputs on the residual compressive strength of GPC. Results indicate that SVR outperformed ANN. Sodium silicate and curing time were observed as the most influential controlling factors affecting the residual compressive strength of GPC at high temperatures. In contrast, fly ash exhibited the slightest effect on the residual compressive strength of GPC, followed by sodium hydroxide. The overall results demonstrate that the machine learning (ML) approaches can effectively improve the monitoring of GPC after exposure to high temperatures.

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.

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.

Seismic Damage Assessment and Shaking-Table Test Validation of Midrise Cold-Formed Steel Composite Shear Wall Buildings

This paper proposes damage index–based limit-state criteria for seismic design of midrise cold-formed steel (CFS) buildings instead of the drift-based ones, and the Park-Ang damage model was used to calculate the damage indexes. Two 5-story CFS buildings with different wall configurations were tested, and a test-validated numerical model was developed. An incremental dynamic analysis was conducted on a typical midrise CFS building to obtain the degradation parameter β of different CFS walls. The damage indexes computed from numerical analyses were compared with the damage indexes estimated from test observations and the proposed damage index–based limit-state criteria. The results showed that the calculated degradation parameter as well as the proposed damage index–based limit-state criteria are effective for seismic damage assessment and damage level classification of midrise CFS buildings according to the validations by shaking-table tests on two CFS buildings. The Park-Ang damage index used in this paper and the proposed limit-state criteria could be used for performance-based seismic design of midrise CFS buildings.

A New Approach to Automatically Calibrate and Detect Building Cracks

Timely crack detection plays an important role in building damage assessment. In this study, an automatic crack detection method based on image registration and pixel-level segmentation (improved DeepLab_v3+) is proposed. Firstly, the moving images are calibrated by image registration, and the similarity method is adopted to evaluate the calibrated results. Secondly, the DeepLab_v3+ is improved and used to segment the fixed images and the calibrated images. Finally, the difference of crack pixels between the fixed and calibrated images is estimated, and the key parameter is investigated to find the optimal optimizer and learning rate. The results illustrate that: (1) the image registration technology shows excellent calibration achievement and the average error is only 4%; (2) with the resnet50 being selected as the backbone network of improved Deeplab_v3+, the automatic detection method proposed in this study is more efficient in comparison with other common pixel-level segmentation algorithms; (3) the best network optimizer of improved Deeplab_v3+ and learning rate of crack segmentation task are sgdm and 0.001, respectively. The crack detection method proposed in this study can significantly improves the technical level of crack detection in practical projects.

Seismic Damage Assessment of Steel Buildings considering Viscoelastic Dampers in Near-Field Earthquake

In this study, three flexural steel frames of 4, 8, and 12 floors were investigated. The frames were designed based on the standard guidelines and then subjected to nonlinear dynamic analysis. Damage to structures with the concept of inelastic behavior and, consequently, hysteresis energy is very close. Therefore, it can be said that hysteresis energy at these levels can be a significant criterion for designing or controlling the structure. The high dependence of hysteresis energy on structural damage has caused this concept and new structural design methods to be considered by researchers and engineers. In this research, the first three steel frames of 4, 8, and 12-story with medium bending frame system with statically equivalent method. Then, all frames under the effect of seven near-field accelerometers and seven far-field accelerometers were analyzed nonlinearly and dynamically. The purpose of this study is to investigate the distribution of damage, energy, relative displacement, roof displacement, and base shear in the studied frames. In the following, the necessity of using the reinforcement method to reduce the relative displacement is described based on the regulations, then viscoelastic dampers are used to strengthen and reduce the damage in the frames under study. The results show that despite the uniform distribution of resistance at the height of the floors, the hysteresis and damage distribution diagrams do not follow this distribution and the concentration of energy and damage is observed in one or more floors. Therefore, in order to make the best use of the maximum system capacity, the design of structures based on strength alone does not seem logical and other parameters such as hysteresis energy, which play a major role in structural member damage, should be considered in the design process. Viscoelastic dampers have been used for retrofitting. The results show that this type of damper has a great role in absorbing energy and reducing damage to buildings. By calculating the damage of floors and the damage of the whole structure, it was seen that the level of damage under near-field earthquakes was greater than that in distant earthquakes and also in structures with a higher number of floors. The results show that as the height of the structure increases, the base shear values increase. As dampers are added to the structural layers, the base shear values are highly reduced so that, for 4, 8, and 12 floor frames under distant field earthquakes, 54%, 45%, and 48% decrease, respectively, and near-field earthquakes decrease, by 55%, 68%, and 64%, respectively. Also, the effect of using viscoelastic dampers on reducing the damage of high-altitude frames has been more and shows good performance in reducing the damage under earthquakes in the near area.

A procedure for 3D simulation of seismic wave propagation considering source‐path‐site effects: Theory, verification and application

AbstractThis paper aims at obtaining a semi‐analytical and semi‐numerical 3D model of source‐to‐site seismic wave propagation due to kinematic finite‐fault sources. To this end, a two‐step procedure integrating the frequency‐wavenumber (FK) approach with the spectral element method (SEM) is proposed based on the concept of domain reduction. First, the broadband responses of a stratified crust are accurately calculated by using a novel FK approach and are converted into effective seismic inputs around the region of interest. After that, the seismic wavefields at local and regional scales arising from complex geological and topographical conditions are finely simulated using the SEM, and a perfectly matched layer absorbing boundary condition is simultaneously applied to realize the absorption of outgoing waves. In this procedure, a hybrid source modelling scheme that combines the low‐wavenumber deterministic and high‐wavenumber stochastic components on the fault plane is introduced, effectively addressing the high‐frequency motion radiated from the source rupture process. Subsequently, the proposed FK‐SEM procedure is verified step‐by‐step using the point source and finite‐fault source models. To illustrate the feasibility of the procedure, 3D physics‐based numerical simulations (PBSs) of two seismic events, including a historical Sanhe‐Pinggu earthquake and a well‐recorded Yangbi earthquake, are performed. The case studies validate that the proposed FK‐SEM procedure allows a significant reduction in computational effort and a substantial improvement in modelling resolution and can be applied to the source‐to‐site broadband synthetics of earthquake scenarios with limited resources. In addition, this coupled geophysics‐engineering simulation meets the requirements of time‐history analysis for engineering structures, which facilitates the study of soil‐structure interactions and regional‐scale building damage assessment.

Hybrid Reconnaissance Mission to the 30 October 2020 Aegean Sea Earthquake and Tsunami (Izmir, Turkey & Samos, Greece): Description of Data Collection Methods and Damage

On 30 October 2020, an earthquake of Mw 6.9 hit the Aegean coasts of Turkey and Greece. The epicentre was some 14 km northeast of Avlakia on Samos Island, and 25 km southwest of Seferihisar, Turkey, triggering also a tsunami. The event has been followed by >4,000 aftershocks up to Mw 5.2 The Earthquake Engineering Field Investigation Team (EEFIT) has immediately gathered a team to conduct a hybrid reconnaissance study, bringing together remote and field investigation techniques. The mission took place between 16 November and 17 December, inclusive of three sets of field study carried out by the field crews for building damage assessment in the affected areas in Turkey and Greece under the coordination of the remote team. The mission also aimed to assess the viability of alternative data sources for an appraisal of the future viability of hybrid missions. This paper summarises the mission setup and findings, and discusses the benefits of and difficulties encountered during this hybrid reconnaissance activity.

Using InSAR and PolSAR to Assess Ground Displacement and Building Damage after a Seismic Event: Case Study of the 2021 Baicheng Earthquake

During unexpected earthquake catastrophes, timely identification of damaged areas is critical for disaster management. On the 24 March 2021, Baicheng county was afflicted by a Mw 5.3 earthquake. The disaster resulted in three deaths and many human injuries. As an active remote sensing technology independent of light and weather, the increasingly accessible Synthetic Aperture Radar (SAR) is an attractive data for assessing building damage. This paper aims to use Sentinel-1A radar images to rapidly assess seismic damage in the early phases after the disaster. A simple and robust method is used to complete the task of surface displacement analysis and building disaster monitoring. In order to obtain the coseismic deformation field, differential interferometry, filtering and phase unwrapping are performed on images before and after the earthquake. In order to detect the damage area of buildings, the Interferometric Synthetic Aperture Radar (InSAR) and Polarimetric Synthetic Aperture Radar (PolSAR) techniques are used. A simple and fast method combining coherent change detection and polarimetric decomposition is proposed, and the complete workflow is introduced in detail. In our experiment, we compare the detection results with the ground survey data using an unmanned aerial vehicle (UAV) after the earthquake to verify the performance of the proposed method. The results indicate that the experiment can accurately obtain the coseismic deformation field and identify the damaged and undamaged areas of the buildings. The correct identification accuracy of collapsed and severely damaged areas is 86%, and that of slightly damaged and undamaged areas is 84%. Therefore, the proposed method is extremely effective in monitoring seismic-affected areas and immediately assessing post-earthquake building damage. It provides a considerable prospect for the application of SAR technology.

Real-Time Ground-Level Building Damage Detection Based on Lightweight and Accurate YOLOv5 Using Terrestrial Images

Real-time building damage detection effectively improves the timeliness of post-earthquake assessments. In recent years, terrestrial images from smartphones or cameras have become a rich source of disaster information that may be useful in assessing building damage at a lower cost. In this study, we present an efficient method of building damage detection based on terrestrial images in combination with an improved YOLOv5. We compiled a Ground-level Detection in Building Damage Assessment (GDBDA) dataset consisting of terrestrial images with annotations of damage types, including debris, collapse, spalling, and cracks. A lightweight and accurate YOLOv5 (LA-YOLOv5) model was used to optimize the detection efficiency and accuracy. In particular, a lightweight Ghost bottleneck was added to the backbone and neck modules of the YOLOv5 model, with the aim to reduce the model size. A Convolutional Block Attention Module (CBAM) was added to the backbone module to enhance the damage recognition effect. In addition, regarding the scale difference of building damage, the Bi-Directional Feature Pyramid Network (Bi-FPN) for multi-scale feature fusion was used in the neck module to aggregate features with different damage types. Moreover, depthwise separable convolution (DSCONV) was used in the neck module to further compress the parameters. Based on our GDBDA dataset, the proposed method not only achieved detection accuracy above 90% for different damage targets, but also had the smallest weight size and fastest detection speed, which improved by about 64% and 24%, respectively. The model performed well on datasets from different regions. The overall results indicate that the proposed model realizes rapid and accurate damage detection, and meets the requirement of lightweight embedding in the future.

Building Damage Assessment Based on Siamese Hierarchical Transformer Framework

The rapid and accurate damage assessment of buildings plays a critical role in disaster response. Based on pairs of pre- and post-disaster remote sensing images, effective building damage level assessment can be conducted. However, most existing methods are based on Convolutional Neural Network, which has limited ability to learn the global context. An attention mechanism helps ameliorate this problem. Hierarchical Transformer has powerful potential in the remote sensing field with strong global modeling capability. In this paper, we propose a novel two-stage damage assessment framework called SDAFormer, which embeds a symmetric hierarchical Transformer into a siamese U-Net-like network. In the first stage, the pre-disaster image is fed into a segmentation network for building localization. In the second stage, a two-branch damage classification network is established based on weights shared from the first stage. Then, pre- and post-disaster images are delivered to the network separately for damage assessment. Moreover, a spatial fusion module is designed to improve feature representation capability by building pixel-level correlation, which establishes spatial information in Swin Transformer blocks. The proposed framework achieves significant improvement on the large-scale building damage assessment dataset—xBD.

On Transfer Learning for Building Damage Assessment from Satellite Imagery in Emergency Contexts

When a natural disaster occurs, humanitarian organizations need to be prompt, effective, and efficient to support people whose security is threatened. Satellite imagery offers rich and reliable information to support expert decision-making, yet its annotation remains labour-intensive and tedious. In this work, we evaluate the applicability of convolutional neural networks (CNN) in supporting building damage assessment in an emergency context. Despite data scarcity, we develop a deep learning workflow to support humanitarians in time-constrained emergency situations. To expedite decision-making and take advantage of the inevitable delay to receive post-disaster satellite images, we decouple building localization and damage classification tasks into two isolated models. Our contribution is to show the complexity of the damage classification task and use established transfer learning techniques to fine-tune the model learning and estimate the minimal number of annotated samples required for the model to be functional in operational situations.

Effective Plans during Earthquake Emergencies for Medical Treatment

The collapse of buildings caused by earthquakes can lead to a large loss of life and property. Rapid assessment of building damage with remote sensing image data can support emergency rescues. However, current studies indicate that only a limited sample set can usually be obtained from remote sensing images immediately following an earthquake. Consequently, the difficulty in preparing sufficient training samples constrains the generalization of the model in the identification of earthquake-damaged buildings. To produce a deep learning network model with strong generalization, this study adjusted Convolution Neural Network (CNN) models for extracting earthquake detection, damaged building information and compared their performance. A sample dataset of damaged buildings, earthquake detection, was constructed by using multiple disaster images retrieved from our dataset. These results provide a solution to the rapid extraction of earthquake-damaged building information based on a deep learning network model.

Early-stage assessment of structural damage caused by braced excavations: Uncertainty quantification and a probabilistic analysis approach

Current early stage assessment methods for deep excavation induced structural damage have large uncertainty due to modeling idealizations (simplification in analyses) and ignorance (incompleteness of information). This paper implements an elastoplastic two-stage solution of soil-structure-interaction to predict building response to adjacent deep excavations with braced supports. This soil-structure-interaction solution is then used to study the uncertainty in two case studies. A global sensitivity analysis is conducted, which indicates that the prediction of ground movement profiles is the major source of uncertainty in early stage building damage assessment. The uncertainty due to ignorance and idealizations related to structural analysis models also contribute significantly when target buildings are modeled as equivalent beams. However, the use of a 2-dimensional elastic frame structural model, in lieu of an equivalent beam, considerably reduces the assessment uncertainty. Considering the existence of uncertainty, a probabilistic analysis approach is proposed to quantify the uncertainty when predicting potential building damage due to excavation-induced subsidence. A computer program called Uncertainty Quantification in Excavation-Structure Interaction (UQESI) is developed to implement this probabilistic analysis approach.

Vibration-Based and Near Real-Time Seismic Damage Assessment Adaptive to Building Knowledge Level

This paper presents a multi-level methodology for near real-time seismic damage assessment of multi-story buildings, tailored to the available level of knowledge and information from sensors. The proposed methodology relates changes in the vibratory characteristics of a building—evaluated via alternative dynamic identification techniques—to the European Macroseismic Scale (EMS-98) damage grades. Three distinct levels of knowledge are considered for the building, with damage classification made through (i) empirical formulation based on quantitative ranges reported in the literature, (ii) analytical formulation exploiting the effective stiffness concept, and (iii) numerical modelling including a simplified equivalent single-degree-of-freedom model or a detailed finite element model of the building. The scope of the study is twofold: to construct a framework for integrating structural health monitoring into seismic damage assessment and to evaluate consistencies/discrepancies among different identification techniques and model-based and model-free approaches. The experimental data from a multi-story building subject to sequential shaking are used to demonstrate the proposed methodology and compare the effectiveness of the different approaches to damage assessment. The results show that accurate damage estimates can be achieved not only using model-driven approaches with enhanced information but also model-free alternatives with scarce information.

Sentinel-1 and Sentinel-2 data fusion to distinguish building damage level of the 2018 Lombok Earthquake

Following an earthquake, Building Damage Assessment (BDA) is crucial in detecting areas that need immediate rescue actions and planning for the best evacuation strategy. Remote sensing has been widely used for BDA. The availability of Sentinel-1 and Sentinel-2 images that are freely accessible could enhance remote sensing applications for building damage classification caused by natural disasters. The accuracy of using the two satellite images for BDA mapping in tropical regions is still uncertain. This research aims to assess Sentinel-1 and Sentinel-2 data fusion performance for BDA mapping following the catastrophic 2018 Lombok Earthquake. Pre- and post-earthquake images of Sentinel-1 and Sentinel-2 were selected, preprocessed, and integrated using the random forest classifier. Three data scenarios were used in this study, i.e., Sentinel-1, Sentinel-2, and the fusion of both datasets. The results demonstrated that all models showed excellent performance in classifying destroyed buildings compared to severely and moderately damaged buildings. This is due to the medium spatial resolution of the images could not identify the damage level in detail. Sentinel-1 and Sentinel-2 data fusion provided the highest overall accuracy value (62.4%) compared to other single dataset models. According to the feature importance analysis result, GLCM Mean, GLCM Variance, and NIR Band played crucial roles in the damage classification. In conclusion, the fusion of Sentinel-1 and Sentinel-2 can provide the best model for destroyed building mapping. However, severely and moderately building damaged mapping can only be accurately mapped using higher spatial resolution images.

Rapid Assessment of Building Damage Using Multi-Source Data: A Case Study of April 2015 Nepal Earthquake

It is of great significance for emergency rescue to rapidly assess damage of buildings after an earthquake. Some previous methods are time-consuming, data are difficult to obtain, or there is lack of regional damage assessment. We proposed a novel way to rapidly assess building damage by comprehensively utilizing earth observation-derived data and field investigation to alleviate the above problems. These data are related to hazard-causing factors, hazard-formative environment, and hazard-affected body. Specifically, predicted ground motion parameters are used to reflect hazard-causing factors, e.g., peak ground velocity (PGV), peak ground acceleration (PGA), and pseudo-spectral acceleration (PSA). The hazard-formative environment is denoted by the underground 30 m shear wave velocity. Vulnerability of buildings is reflected by their structure type, age, and height. We take the April 2015 Nepal earthquake as a case study, and building damage data interpreted from satellite images are used to validate the effectiveness of the proposed method. Based on the gradient boosting machine, this paper rapidly assesses building damage from two different spatial levels, i.e., pixel and microzone, and obtains the potentially affected position and regional damage rate. Compared with the method of fragility function, the machine learning method provide a better estimation of the building damage rate. Compared with the assessment method based on remote sensing image, the method in this paper is very efficient since spatial distribution of hazard-causing factors, e.g., PGA, can be quickly predicted shortly after an earthquake. The comparison of experiment with and without vulnerability data of buildings shows that data on the vulnerability of buildings are very important to improve the assessment accuracy of building damage.