Figure 5 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
An accurate estimation of a casualty rate is critical in response to
earthquake disasters, and could allow an increase in the survival rate.
Building damage is considered to be a major cause of earthquake casualties in
developing countries. High-resolution satellite imagery (HRSI) can be used to
detect the building damage in a period of a short tim...
Context in source publication
Context 1
... Guo et al., 2010). In this earthquake, 2968 people were killed and 12 135 peo- ple were injured. Jiegu, which is in the center of Yushu, was severely affected, and was selected as the study area. In the affected area of Jiegu, 1942 people were killed and 8283 people were injured. The HRSIs were collected by QuickBird with 0.7 m spatial resolution (Fig. 5). The im- age was downloaded from imagery courtesy of DigitalGlobe ...
Similar publications
This article introduces the concept of land suitability evaluation for possible application in residential settlement in Banda Aceh. On December 26 th , 2004 the earthquake and tsunami has struck the west coast of northern Sumatra Island, Indonesia. Banda Aceh is the largest residential area and most severely affected by this disaster impact. Ten y...
Citations
... A range of studies have explored the relationship between the Human HDI and disaster casualties. Feng et al. (2014) and Prasojo et al. (2021) both found that higher HDI is associated with lower casualties, with Prasojo specifically noting a negative correlation between HDI and human losses from disasters. This is further supported by Baradan et al. (2019), who found an inverse relationship between HDI and fatality rates in construction. ...
... Indian states that are highly populated, such as Bihar and UP, have experienced higher flood fatalities as a result of lower achievements in human development 15 . Our findings are similar to Feng et al. (2014) and Prasojo et al. (2021). Both found that higher HDI is associated with lower casualties, with Prasojo specifically noting a negative correlation between HDI and human losses from disasters. ...
Natural disasters present substantial dangers to both human life and physical infrastructure. Although the human development index (HDI) is recognized for its pivotal role in mitigating mortality resulting from natural disasters, the exact extent of its impact on fatalities remains unclear. In this study, we investigate the relationship between HDI and fatalities resulting from floods and cyclones using panel data for 19 states of India spanning from 1983 to 2011. Employing Fixed Effects Poisson and Negative Binomial estimates, we establish a causal-effect relationship between HDI and disaster-related fatalities. Additionally, we utilize the Instrumental Variable Poisson (IV) model to address the endogeneity between HDI and fatalities. Our empirical findings indicate that states with higher HDI levels experience lower fatalities due to natural disasters. Furthermore, our results underscore the importance of critical policy discussions regarding the role of inequality-adjusted HDI, government responsiveness, and human capital development in disaster risk reduction strategies.
... As an important technology for acquiring, processing and expanding spatial information, remote sensing and GIS are widely used in various fields Abdollahi et al. 2021;Rabiei et al. 2022). This method can quickly derive the extent and spatial distribution of building damage in earthquake-affected areas and thus estimate the loss of life (Feng et al. 2014;Zhang et al. 2019;Delavar and Sadrykia 2020). The most obvious drawback of this method is that it is difficult to apply to small-scale earthquakes with few fatalities. ...
Reliable earthquake fatality prediction is an important reference for post-earthquake emergency response efforts. Seismic data are the basis for constructing earthquake casualty prediction models, but the selection and evaluation of earthquake features are more critical due to the scarcity of destructive earthquake samples. In order to make full use of the high-dimensional survey data of destructive earthquake disasters in the Earthquake Reports in Yunnan Province since 1992, and effectively use it to improve the ability to predict the number of earthquake casualties, this paper proposes a hybrid feature importance evaluation method based on four conventional feature contribution methods (IG, PPMCC, SRCC and MDI), ranking the importance of 63 features that affect the number of earthquake casualties in Yunnan Province, and reducing the feature dimension accordingly. Then, cross-validation is used to compare the accuracy of the four machine models before and after dimensionality reduction. We found that (1) among the 10 features with the highest hybrid importance, there were 8 population distribution features, 1 geological hazard feature (number of landslides) and 1 damage degree feature (highest intensity of earthquakes); (2) the feature dimensionality reduction based on the importance of hybrid features can effectively improve the prediction accuracy of machine learning models; and (3) in the comparison of several methods, the Particle Swarm Optimized Support Vector Machine model had the highest prediction accuracy, with an R2 over 0.934. The research results showed that this method can significantly improve the prediction accuracy of the machine learning model and has some reference value for earthquake emergency rescue and post-disaster reconstruction work.
... Karimzadeh et al. [19] presented a GIS-oriented procedure in combination with geo-related parameters for identifying the destruction in earthquake-stricken areas and evaluated the seismic loss based on damage functions and relational analyses. Feng et al. [20] regarded building damage as a major cause of earthquake deaths, and used high-resolution satellite imagery to detect building damage in disaster areas. They developed a model for estimating the mortality rate due to an earthquake based on remote sensing and a geographical information system. ...
The evaluation of mortality in earthquake-stricken areas is vital for the emergency response during rescue operations. Hence, an effective and universal approach for accurately predicting the number of casualties due to an earthquake is needed. To obtain a precise casualty prediction method that can be applied to regions with different geographical environments, a spatial division method based on regional differences and a zoning casualty prediction method based on support vector regression (SVR) are proposed in this study. This study comprises three parts: (1) evaluating the importance of influential features on seismic fatality based on random forest to select indicators for the prediction model; (2) dividing the study area into different grades of risk zones with a strata fault line dataset and WorldPop population dataset; and (3) developing a zoning support vector regression model (Z-SVR) with optimal parameters that is suitable for different risk areas. We selected 30 historical earthquakes that occurred in China’s mainland from 1950 to 2017 to examine the prediction performance of Z-SVR and compared its performance with those of other widely used machine learning methods. The results show that Z-SVR outperformed the other machine learning methods and can further enhance the accuracy of casualty prediction.
... Les méthodes se basant sur les indicateurs de changement dans la morphologie des bâtiments analysent les attributs radiométriques et géométriques des objets (le bâtiment) utilisés pour caractériser un degré de dégât. Parmi ces méthodes, la photo-interprétation visuelle des images en mode multispectrale ou avec des images de fusion [11][12][13][14][15][16][17][18][19]. L'avantage de ces méthodes orientées-objets est de tenir compte de l'organisation spatiale des pixels mais elles ont l'avantage d'être moins sensibles aux changements non pertinents [10]. ...
Abstract - Building structures can undergo heavy damages after a strong earthquake. The estimation
of these damages is a fundamental task to any decision maker. Several methods do exist, among them
the use of very high spatial images which are very helpful in areas with difficult access.
They are three great family methods to assess damages using such images: a) Methods based on the
change of the building morphology, b) Methods based on the change of the building shadow and c)
Methods based on the change of building spectral response.
The present study aims to compare the three great family methods throw the use of a sample of six
buildings located in Zemmouri and damaged by Boumerdes earthquake (May 21st, 2003). The
comparison shows that the method based on the shadow gives better results.
Keywords: Remote Sensing; damage; earthquake; spectral responses; buildings
... In the early hours after an earthquake, collecting information and evaluating the extent of damage is essential for anticipating the healthcare needs of survivors, managing critical conditions [8], and allocating limited resources. Casualties and injuries estimation is one of the most crucial processes to measure the severity of damage [9]. The methods used to determine the loss of life caused by earthquakes can be divided into two categories. ...
... The settlement should be close to the disaster area, so the affected population should be easily transported to settlements; (2) Safety Principle. High MMI earthquakes can result in a large number of casualties and infrastructure damage when they occur in close proximity to the epicenter [9]. There is usually a long period of aftershocks and a lot of secondary hazards. ...
Background: Earthquakes causing significant damage have occurred frequently in China, producing enormous health losses, damage to the environment and public health issues. Timely public health response is crucial to reduce mortality and morbidity and promote overall effectiveness of rescue efforts after a major earthquake. Methods: A rapid assessment framework was established based on GIS technology and high-resolution remote sensing images. A two-step casualties and injures estimation method was developed to evaluate health loss with great rapidity. Historical data and health resources information was reviewed to evaluate the damage condition of medical resources and public health issues. Results: The casualties and injures are estimated within a few hours after an earthquake. For the Wenchuan earthquake, which killed about 96,000 people and injured about 288,000, the estimation accuracy is about 77%. 242/294 (82.3%) of the medical existing institutions were severely damaged. About 40,000 tons of safe drinking water was needed every day to ensure basic living needs. The risk of water-borne and foodborne disease, respiratory and close contact transmission disease is high. For natural foci diseases, the high-risk area of schistosomiasis was mapped in Lushan County as an example. Finally, temporary settlements for victims of earthquake were mapped. Conclusions: High resolution Earth observation technology can provide a scientific basis for public health emergency management in the major disasters field, which will be of great significance in helping policy makers effectively improve health service ability and public health emergency management in prevention and control of infectious diseases and risk assessment.
... There are only a handful of studies in other research domains (e.g., remote sensing) that assess the level of damage from aerial ( Turker & San, 2004;Fernandez Galarreta, Kerle, & Gerke, 2015;Attari, Ofli, Awad, Lucas, & Chawla, 2017) and satellite ( Pesaresi, Gerhardinger, & Haag, 2007;Feng et al., 2014) images collected from disaster-hit regions. Most recent studies based on social media data, and also the most relevant ones to our study, are presented by ( Lagerstrom et al., 2016) and ( Daly & Thom, 2016) where both studies analyze social media images in a binary classification setting for fire/not-fire detection scenario. ...
The extensive use of social media platforms, especially during disasters, creates unique op- portunities for humanitarian organizations to gain situational awareness as disaster unfolds. In addition to textual content, people post overwhelming amounts of imagery content on social networks within minutes of a disaster hit. Studies point to the importance of this online imagery content for emergency response. Despite recent advances in computer vision research, making sense of the imagery content in real-time during disasters remains a challenging task. One of the important challenges is that a large proportion of images shared on social media is redun- dant or irrelevant, which requires robust filtering mechanisms. Another important challenge is that images acquired after major disasters do not share the same characteristics as those in large-scale image collections with clean annotations of well-defined object categories such as house, car, airplane, cat, dog, etc., used traditionally in computer vision research. To tackle these challenges, we present a social media image processing pipeline that combines human and machine intelligence to perform two important tasks: (i) capturing and filtering of social media imagery content (i.e., real-time image streaming, de-duplication, and relevancy filtering), and (ii) actionable information extraction (i.e., damage severity assessment) as a core situational awareness task during an ongoing crisis event. Results obtained from extensive experiments on real-world crisis datasets demonstrate the significance of the proposed pipeline for optimal utilization of both human and machine computing resources.
... Studies of satellite image processing for crisis response also include [20]- [22] and [23]. Similar studies in remote sensing research area show the evidences of damage level assessment from aerial [5], [6] and satellite [24], [25] images collected from disaster-hit regions. ...
We present an end-to-end social media image processing system called Image4Act. The system aims at collecting, denoising, and classifying imagery content posted on social media platforms to help humanitarian organizations in gaining situational awareness and launching relief operations. It combines human computation and machine learning techniques to process high-volume social media imagery content in real time during natural and human-made disasters. To cope with the noisy nature of the social media imagery data, we use a deep neural network and perceptual hashing techniques to filter out irrelevant and duplicate images. Furthermore, we present a specific use case to assess the severity of infrastructure damage incurred by a disaster. The evaluations of the system on existing disaster datasets as well as a real-world deployment during a recent cyclone prove the effectiveness of the system.
... On the other hand, use of computer vision and image processing techniques for damage assessment from images has not been fully explored in literature, except for a handful of studies that has sporadically appeared mainly in the remote sensing domain which were mostly based on analyses of satellite [28], [29] and aerial [30]- [32] imagery. Most recent studies in this direction, and also the most relevant ones to the current study, are presented by Lagerstrom et al. [33] and by Daly and Thom [34] where both studies analyzed social media data but in a binary image classification setting for fire/not-fire detection scenario. ...
Rapid access to situation-sensitive data through social media networks creates new opportunities to address a number of real-world problems. Damage assessment during dis- asters is a core situational awareness task for many humanitarian organizations that traditionally takes weeks and months. In this work, we analyze images posted on social media platforms during natural disasters to determine the level of damage caused by the disasters. We employ state-of-the-art machine learning techniques to perform an extensive experimentation of damage assessment using images from four major natural disasters. We show that the domain-specific fine-tuning of deep Convolutional Neural Networks (CNN) outperforms other state-of-the-art techniques such as Bag-of-Visual-Words (BoVW). High classification ac- curacy under both event-specific and cross-event test settings demonstrate that the proposed approach can effectively adapt deep-CNN features to identify the severity of destruction from social media images taken after a disaster strikes.
... Change detection (CD), using satellite remote-sensing observations, has been an important technique for various applications such as land-cover/land-use change analyses (Nunes and Auge 1999;Shalaby and Tateishi 2007), assessment of deforestation (Hosonuma et al. 2012;Römer et al. 2012), damage assessment (Domenikiotis, Loukas, and Dalezios 2003;Feng et al. 2014;Kamthonkiat et al. 2011), disaster monitoring (Kaiser et al. 2013;Lahousse, Chang, and Lin 2011;Roemer et al. 2010), and other environmental changes. The general objectives of CD in remote sensing include identifying the geographical location and type of changes, as well as quantifying the changes (Singh 1989). ...
The Earth’s land covers are exposed to several types of environmental changes, issued by either human activities or natural disasters. On 11 March 2011, an earthquake occurred at about 130 km of the east coast of Sendai City in Japan. This earthquake has been followed by a huge tsunami, which caused devastating damages over the wide areas in the eastern coastlines of Japan. In order to manage such crises quickly and efficiently, change maps of affected areas are really crucial for damage estimation and proposing the essential services. Therefore, an automatic extraction of inundated and damaged areas from satellite images, with less user interaction, is essential and helpful. So far, the existing change detection (CD) approaches have a low degree of automation and are not optimal and applicable to high resolution optical and radar remote-sensing data. In order to resolve these problems, an integrated object-level CD method based on an object-based classifier and support vector data description method is proposed. In addition, parameter determination of the proposed method is addressed automatically by using an inter-cluster distance based approach. In order to evaluate the efficiency of the proposed method and extract the damaged areas, various optical and radar remote-sensing images from before and after of Sendai 2011’s tsunami, acquired by IKONOS, Radarsat-2, and TerraSAR-X, were used. The accuracy analysis of results showed a great flexibility for CD of by finding nonlinear object-level solutions to the problem. Furthermore, the comparative analysis of experimental results from IKONOS, Radarsat-2, and TerraSAR-X (kappa coefficient (κ): 0.85, 0.82, 0.76) and Support Vector Machine-based CD techniques (κ = 0.83, 0.73, 0.84), showed that the accuracy of the change maps is relatively improved. Finally, we came to the conclusion that the proposed method is considerably automated and less influenced by the errors in the classification process.
... Taking a step further, Chen et al. studied the association between tweets and images, and their use in classifying visually-relevant and irrelevant tweets (Chen et al. 2013). They designed classifiers by combining features from text, images and socially relevant contextual features (e.g., posting time, follower ratio, the number of comments, re-tweets), and reported an F1-score of 70.5% in a binary classification task, which is 5.7% higher than the text-only classification., France, May 2017 Tina Comes, Fr?d?rick B?naben, Chihab Hanachi, Matthieu Lauras, eds.There are similar studies in other research domains (e.g., remote sensing), not necessarily using social media data though, that try to assess level of damage from aerial (Turker and San 2004;Fernandez Galarreta et al. 2015) and satellite (Pesaresi et al. 2007;Feng et al. 2014) images collected from disaster-hit regions. Almost all of the aforementioned studies rely on the classical bag-of-visual-words-type features extracted from images to build the desired classifiers. ...
The extensive use of social media platforms, especially during disasters, creates unique opportunities for humanitarian organizations to gain situational awareness and launch relief operations accordingly. In addition to the textual content, people post overwhelming amounts of imagery data on social networks within minutes of a disaster hit. Studies point to the importance of this online imagery content for emergency response. Despite recent advances in the computer vision field, automatic processing of the crisis-related social media imagery data remains a challenging task. It is because a majority of which consists of redundant and irrelevant content. In this paper, we present an image processing pipeline that comprises de-duplication and relevancy filtering mechanisms to collect and filter social media image content in real-time during a crisis event. Results obtained from extensive experiments on real-world crisis datasets demonstrate the significance of the proposed pipeline for optimal utilization of both human and machine computing resources.
