Amro Al-Akkad, & Zimmermann, A. (2011). User study: Involving civilians by smart phones during emergency situations. In E. Portela L. S. M.A. Santos (Ed.), 8th International Conference on Information Systems for Crisis Response and Management: From Early-Warning Systems to Preparedness and Training, ISCRAM 2011. Lisbon: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: This paper concerns a preliminary user study to determine the acceptance of a mobile application that is supposed to involve civilians during emergencies. In particular, the focus is on bystanders. Their intervention during emergencies constitutes a delicate issue, since they were traditionally considered as a rather annoying party being merely observers of incidents. However, with the ubiquity and ever-increasing capabilities of cell phones there might emerge a great potential to flip the coin and to benefit from bystanders playing from now on a contributive role. To examine this hypothesis, we conducted semi-structured interviews with 24 persons. The result of our study shows that people are willing to use such mobile assisting system, and thus we take it as a positive starting signal to continue our research into this direction considering the elicited user constraints.
|
Amro Al-Akkad, & Zimmermann, A. (2012). Survey: ICT-supported public participation in disasters. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: In an increasingly networked society citizens at disaster sites utilize information and communication technology (ICT) to communicate needs or to share information. In order to understand better emergent possibilities and implications of applying ICT for supporting public participation in disasters, we surveyed 57 respondents regarding several key user aspects as perceived usefulness, socially related issues, or deployment. Surprisingly, our results show a clear tendency to use a disaster specific application instead of using everyday services as facebook or Twitter. However, such application poses the risk to loose its focus fading slowly away after once downloading it. Further study is needed to understand if these results are representative regarding public society. © 2012 ISCRAM.
|
Alexander Almer, Thomas Schnabel, Johann Raggam, Armin Köfler, Roland Wack, & Richard Feischl. (2015). Airborne multi-sensor management support system for emergency teams in natural disasters. In L. Palen, M. Buscher, T. Comes, & A. Hughes (Eds.), ISCRAM 2015 Conference Proceedings ? 12th International Conference on Information Systems for Crisis Response and Management. Kristiansand, Norway: University of Agder (UiA).
Abstract: This paper describes the development of a multi-functional airborne management support system within the frame of the Austrian national safety and security research programme. The objective was to assist crisis management tasks of emergency teams and armed forces in disaster management by providing multi spectral, near real-time airborne image data products. As time, flexibility and reliability as well as objective information are crucial aspects in emergency management, the used components are tailored to meet these requirements. This article includes the individual system components as well as their performance using examples from lab tests and real-life deployments. Based on this, the impact of existing command and control processes as well as the benefits for time critical decision making processes are described based on expertise of the involved end users. In addition, it gives an outlook on future perspectives.
|
Artur Ricardo Bizon, Luciana P. de Araújo Kohler, Adilson Luiz Nicoletti, Fernanda Dal Bosco, Murilo Schramm da Silva, & Thales Bohn Pessatti. (2020). Integration statistical systems for land cover mapping in Southern Brazil. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 498–505). Blacksburg, VA (USA): Virginia Tech.
Abstract: The remote sensing is a way to optimize the process of land cover classification allowing that this process will be by high definition images of satellite. For the research it was used the Google Earth Engine with JavaScript programming language to classify the images, identifying the areas with forest or reforest. It was identified that classifiers Random Forest and Logistic Regression have a high performance in classify the images. From them it was developed functions to process automatically of new images with purpose of classify them in relation to land cover.
|
Einar Bjørgo. (2004). Satellite imagery and GIS for disaster response & management in the United Nations: The UNOSAT approach. In B. C. B. Van de Walle (Ed.), Proceedings of ISCRAM 2004 – 1st International Workshop on Information Systems for Crisis Response and Management (pp. 105–110). Brussels: Royal Flemish Academy of Belgium.
Abstract: Remote sensing and Geographic Information Systems (GIS) have the potential to provide United Nations (UN) humanitarian agencies and their partners with much needed disaster related information and improved management of resources. However, the technical nature of these tools requires considerable expertise to fully benefit from satellite images and related geographic information. The UN Office for Project Services (UNOPS) is implementing the UNOSAT service on behalf of the UN Institute on Training and Research (UNITAR) together with several private actors. UNOSAT provides the UN and its partners with the expertise in Earth Observation (EO) and GIS applications. As a crisis is part of a spectrum of disaster related events, UNOSAT provides services in all phases of humanitarian assistance, including planning, crisis response, relief and development. UNOSAT's objectives are to facilitate the territory planning and monitoring processes of local authorities, local technicians, development project managers and humanitarian field operators working in coordination with or within the framework of UN activities, on issues such as disaster management, risk prevention, peace keeping operations, post conflict reconstruction, environmental rehabilitation and social and economic development. A key part of this work is to accelerate and expand the use of accurate geographic information derived from EO-satellite imagery. UNOSAT is also involved in several international initiatives aimed at improved crisis response and management, such as the International Charter “Space and Major Disasters”, an important asset in providing timely information to relief personnel on the ground. By working closely with its UN sister agencies, UNOPS/UNOSAT offers a one-stop-shop for satellite imagery and GIS services related to disaster response & management within the United Nations. © Proceedings ISCRAM 2004.
|
Carolin Klonner, Sabrina Marx, Tomás Usón, & Bernhard Höfle. (2016). Risk Awareness Maps of Urban Flooding via OSM Field Papers- Case Study Santiago de Chile. In A. Tapia, P. Antunes, V.A. Bañuls, K. Moore, & J. Porto (Eds.), ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management. Rio de Janeiro, Brasil: Federal University of Rio de Janeiro.
Abstract: Urban flooding has been increasing in recent years and therefore new specified methods need to be developed and applied. The rise of Web 2.0 technologies and collaborative projects based on volunteered geographic information like OpenStreetMap (OSM) lead to new dimensions of participatory practices. Thus, citizens can provide local knowledge for natural hazard analysis in a convenient way. In the following, a case study of the Quilicura community in Santiago de Chile -regularly affected by urban floods- is presented. A combination of OSM Field Papers and the risk perception of local people is applied in the concept of risk awareness maps including a questionnaire for participants? information. This explorative study is a promising approach for a complementing data source because insight into local knowledge is acquired in a fast way. Results reveal two main streets, which are identified by the participants as prone to urban floods.
|
Marline Claessens, Nicolas Lewyckyj, Jane Biesemans, & Jurgen Everaerts. (2005). Pegasus, a UAV project for disaster management. In B. C. B. Van de Walle (Ed.), Proceedings of ISCRAM 2005 – 2nd International Conference on Information Systems for Crisis Response and Management (pp. 233–236). Brussels: Royal Flemish Academy of Belgium.
Abstract: The Flemish Institute for Technological Research (Vito) in Belgium has initiated in 2000 the PEGASUS (Policy support for European Governments by Acquisition of information from Satellite and UAV-borne Sensors) project which envisages the development of a solar powered UAV (Unmanned Aerial Vehicle) containing several types of instruments for remote sensing and flying at an altitude of about 20 km. The aircraft can be deployed rapidly in crisis situations and provide disaster managers with ~1 m resolution images (or better if required) of the affected area. High quality data shall be received in less than half an hour from a mobile ground station that is in direct contact with the UAV, which can operate as long as requested by the user. The PEGASUS HALE-UAV is a flexible and cost-effective tool that will allow officials and local authorities to dispose quickly over relevant geographical information in an emergency situation. The first demonstration flight of the PEGASUS HALE-UAV shall take place in the summer of 2005 over Flanders.
|
Tom De Groeve, & Patrick Riva. (2009). Early flood detection and mapping for humanitarian response. In S. J. J. Landgren (Ed.), ISCRAM 2009 – 6th International Conference on Information Systems for Crisis Response and Management: Boundary Spanning Initiatives and New Perspectives. Gothenburg: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Space-based river monitoring can provide a systematic, timely and impartial way to detect floods of humanitarian concern. This paper presents a new processing method for such data, resulting in daily flood magnitude time series for any arbitrary observation point on Earth, with lag times as short as 4h. Compared with previous work, this method uses image processing techniques and reduces the time to obtain a 6 year time series for an observation site from months to minutes, with more accurate results and global coverage. This results in a daily update of major floods in the world, with an objective measure for their magnitude, useful for early humanitarian response. Because of its full coverage, the grid-based technique also allows the automatic creation of low-resolution flood maps only hours after the satellite passes, independent of cloud coverage.
|
Tom De Groeve, Zsofia Kugler, & G. Robert Brakenridge. (2007). Near real time flood alerting for the global disaster alert and coordination system. In K. Nieuwenhuis P. B. B. Van de Walle (Ed.), Intelligent Human Computer Systems for Crisis Response and Management, ISCRAM 2007 Academic Proceedings Papers (pp. 33–39). Delft: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: A new flood monitoring module is in development for the Global Disaster Alert and Coordination System (GDACS). GDACS is an information system designed to assist humanitarian responders with their decisions in the early onset after a disaster. It provides near-real time flood alerts with an initial estimate of the consequences based on computer models. Subsequently, the system gathers information in an automated way from relevant information sources such as international media, mapping and scientific organizations. The novel flood detection methodology is based on daily AMSR-E passive microwave measurement of 2500 flood prone sites on 1435 rivers in 132 countries. Alert thresholds are determined from the time series of the remote observations and these are validated using available flood archives (from 2002 to present). Preliminary results indicate a match of 47% between detected floods and flood archives. Individual tuning of thresholds per site should improve this result.
|
Sébastien Delhay, Mahamadou Idrissa, & Vinciane Lacroix. (2005). PARADIS: GIS tools for humanitarian demining. In B. C. B. Van de Walle (Ed.), Proceedings of ISCRAM 2005 – 2nd International Conference on Information Systems for Crisis Response and Management (pp. 213–219). Brussels: Royal Flemish Academy of Belgium.
Abstract: Landmines and UXO (UneXploded Ordnance1) represent a constant and long-lasting threat to the life of millions of individuals. Moreover, these weapons have a strong socio-economic impact on contaminated countries as they involve serious effects as the loss of agricultural fields or access to water. Demining is a critical issue since contaminated areas are large and their clearance often requires investing much time and money into it. It is then fundamental to manage demining activities in an efficient manner. PARADIS 2 is a tool dedicated to Mine Action and helps demining campaigns planners take rational decisions. It fits the needs of all campaign actors, as it is based on the tasks assigned to both the campaign planner and the field operator. The tool is built upon GIS technology and uses satellite imagery as a substitute for background maps, in order to represent all data involved in demining in their most explicit form: a map.
|
Fatehkia, M., Imran, M., & Weber, I. (2023). Towards Real-time Remote Social Sensing via Targeted Advertising. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 396–406). Omaha, USA: University of Nebraska at Omaha.
Abstract: Social media serves as an important communication channel for people affected by crises, creating a data source for emergency responders wanting to improve situational awareness. In particular, social listening on Twitter has been widely used for real-time analysis of crisis-related messages. This approach, however, is often hindered by the small fraction of (hyper-)localized content and by the inability to explicitly ask affected populations about aspects with the most operational value. Here, we explore a new form of social media data collected through targeted poll ads on Facebook. Using geo-targeted ads during flood events in six countries, we show that it is possible to collect thousands of poll responses within hours of launching the ad campaign, and at a cost of a few (US dollar) cents per response. We believe that this flexible, fast, and affordable data collection can serve as a valuable complement to existing approaches.
|
Flavio Horita, Ricardo Vilela, Renata Martins, Danielle Bressiani, Gilca Palma, & João Porto de Albuquerque. (2018). Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 1040–1050). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Crowd sensing data (also known as crowdsourcing) are of great significance to support flood risk management. With the growing volume of available data in the past few years, researchers have used in situ sensor data to filter and prioritize volunteers' information. Nevertheless, stationary, in situ sensors are only capable of monitoring a limited region, and this could hamper proper decision-making. This study investigates the use of weather radar precipitation to support the processing of crowd sensing data with the goal of improving situation awareness in a disaster and early warnings (e.g., floods). Results from a case study carried out in the city of São Paulo, Brazil, demonstrate that weather radar data are able to validate flooded areas identified from clusters of crowd sensing data. In this manner, crowd sensing and weather radar data together can not only help engage citizens, but also generate high-quality data at finer spatial and temporal resolutions to improve the decision-making related to weather-related disaster events.
|
Jose J. Gonzalez, Ole-Christoffer Granmo, Bjørn Erik Munkvold, Frank Y Li, & Julie Dugdale. (2012). Multidisciplinary challenges in an integrated emergency management approach. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: The University of Agder, Norway, has recently founded a Centre for Integrated Emergency Management (CIEM). The centre brings together a highly multi-disciplinary group of local and international researchers in technology and the social sciences. This paper presents an interdisciplinary vision for large-scale integrated emergency management that has been inspired by the transition from platform centric to Integrated Operations in the oil and gas fields, which uses remote emergency control centers collaborating virtually with local responders. The paper discusses some of the most salient research challenges for Integrated Emergency Management. © 2012 ISCRAM.
|
Klaus Granica, Thomas Nagler, Markus M. Eisl, Mathias Schardt, & Helmut Rott. (2005). Satellite remote sensing data for an alpine related disaster management GIS. In B. C. B. Van de Walle (Ed.), Proceedings of ISCRAM 2005 – 2nd International Conference on Information Systems for Crisis Response and Management (pp. 221–232). Brussels: Royal Flemish Academy of Belgium.
Abstract: Natural disasters are an age-old problem that occur regularly in alpine regions, posing a major threat to the safety of settlements and transport routes. Within the project “Safety of Alpine Routes – Application of Earth Observation Combined with GIS (Hannibal)”, financed by the Ministry of Transport and Innovation, information relevant for disaster management has been extracted from satellite remote sensing and integrated into a newly developed GIS based Decision Support System (DSS). Some of the required map information were inferred from ERS- or from SPOT5- and QUICKBIRD satellites, others were taken from conventional data sources such as maps or Digital Terrain Models.
|
Miao Jiang, & William L. McGill. (2010). Human-centered sensing for crisis response and management analysis campaigns. In C. Zobel B. T. S. French (Ed.), ISCRAM 2010 – 7th International Conference on Information Systems for Crisis Response and Management: Defining Crisis Management 3.0, Proceedings. Seattle, WA: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Human-centered sensing (HCS) is an emerging research field that leverages mobile devices carried by people to collect useful information in support of myriad analytic activities. In this paper, we explore ways in which HCS can be applied to support a variety of analytic campaigns in the context of crisis response and management (CRM). We first summarize the concept of HCS and then investigate the potential advantages of complementing traditional sensing platforms and analytic tasks with an HCS system. By recognizing the potentials of HCS, we offer a scheme for classifying HCS systems and envision three application scenarios of HCS in CRM as well as a general architecture of HCS systems.
|
Mitchell L. Moss, & Anthony M. Townsend. (2006). Disaster forensics: Leveraging crisis information systems for social science. In M. T. B. Van de Walle (Ed.), Proceedings of ISCRAM 2006 – 3rd International Conference on Information Systems for Crisis Response and Management (pp. 305–312). Newark, NJ: Royal Flemish Academy of Belgium.
Abstract: This paper contributes to the literature on information systems in crisis management by providing an overview of emerging technologies for sensing and recording sociological data about disasters. These technologies are transforming our capacity to gather data about what happens during disasters, and our ability to reconstruct the social dynamics of affected communities. Our approach takes a broad review of disaster research literature, current research efforts and new reports from recent disasters, especially Hurricane Katrina and the Indian Ocean Tsunami. We forecast that sensor networks will revolutionize conceptual and empiricial approaches to research in the social sciences, by providing unprecedented volumes of high-quality data on movements, communication and response activities by both formal and informal actors. We conclude with a set of recommendations to designers of crisis management information systems to design systems that can support social science research, and argue for the inclusion of post-disaster social research as a design consideration in such systems.
|
Jaziar Radianti, Julie Dugdale, Jose J. Gonzalez, & Ole-Christoffer Granmo. (2014). Smartphone sensing platform for emergency management. In and P.C. Shih. L. Plotnick M. S. P. S.R. Hiltz (Ed.), ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management (pp. 379–383). University Park, PA: The Pennsylvania State University.
Abstract: The increasingly sophisticated sensors supported by modern smartphones open up novel research opportunities, such as mobile phone sensing. One of the most challenging of these research areas is context-aware and activity recognition. The Smart Rescue project takes advantage of smartphone sensing, processing and communication capabilities to monitor hazards and track people in a disaster. The goal is to help crisis managers and members of the public in early hazard detection, prediction, and in devising risk-minimizing evacuation plans when disaster strikes. In this paper we suggest a novel smartphone-based communication framework. It uses specific machine learning techniques that intelligently process sensor readings into useful information for the crisis responders. Core to the framework is a content-based publish-subscribe mechanism that allows flexible sharing of sensor data and computation results. We also evaluate a preliminary implementation of the platform, involving a smartphone app that reads and shares mobile phone sensor data for activity recognition.
|
Muhammad Tauhidur Rahman, & Tarek Rashed. (2007). Towards a geospatial approach to post-disaster environmental impact assessment. In K. Nieuwenhuis P. B. B. Van de Walle (Ed.), Intelligent Human Computer Systems for Crisis Response and Management, ISCRAM 2007 Academic Proceedings Papers (pp. 219–226). Delft: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Natural disasters often leave profound impacts on the environment. Existing disaster impact assessment methods fall short in facilitating the relief work and in conducting cross-sectional comparison of various facets of such impacts. The development of a standardized index for measuring/monitoring the environmental impacts of disasters is necessary to address this gap. This paper proposes a conceptual framework to study the environmental impacts via remote sensing/GIS based geospatial analytical approach by developing a post-disaster environmental severity index. It considers physical, social and built-in components of the environment and identifies several key indicators of disaster impacts. Through statistical decomposition of a large number of environmental impact indicators, the study proposes a composite post-disaster environmental severity index (PDESI). Mapping of the proposed index would help identification of areas and component of the environment that are severely affected by a disaster, and formulation of disaster mitigation and damage recovery plans accordingly.
|
Rob Grace, & Michelle Potts. (2022). Opportunities for Multisensor Integration in Public-Safety Answering Points. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 895–904). Tarbes, France.
Abstract: Public-Safety Answering Points (PSAPs) coordinate emergency response by gathering critical information from 911 callers for dispatch to first responders. However, PSAPs fail to gather this information if 911 callers are unable, unwilling, or unavailable to report key details about an emergency. To address this problem, early-adopter PSAPs employ communication specialists to gather multimedia information from multiple sensing tools, including automated alarms, cameras, government databases, location systems, open-source websites, social media, and alternative communication channels such as text-to-911. Using preliminary usage data from an early- adopter PSAP, this study identifies 11 breakdowns in 911 call taking that create opportunities for multisensor integration. This study then characterizes use cases for multisensor tools based on usage patterns observed across five incident types. These findings highlight multisensor integration as a critical area for crisis informatics research.
|
Mohamad Rukieh. (2007). The effects of lineaments and epicentres on risk reduction in arabian rift zone. In K. Nieuwenhuis P. B. B. Van de Walle (Ed.), Intelligent Human Computer Systems for Crisis Response and Management, ISCRAM 2007 Academic Proceedings Papers (pp. 227–234). Delft: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: This paper describes the relationship between lineaments, which determined on space images, and the epicenters and their effects on spatial planning for risk reduction. Several studies have shown that most of the epicenters occur along these lineaments or their zones, or in the block regions which are bordered by these lineaments, or where these lineaments and different tectonic deformation are intersected. This paper presents a case study on the Arabian Rift Zone which is based on the linkages among lineaments, faults, and earthquakes that occurred in the region during 1910-93. Also, this study will show that most of these earthquakes were occurred along the main and secondary rift faults or in their zone, including the faults found in sea that helped in determining the courses of these earthquakes in the sea bottom. This confirms the importance of remote sensing techniques for providing space images of different scales in seismic studies.
|
Axel Schulz, Heiko Paulheim, & Florian Probst. (2012). Crisis information management in the Web 3.0 age. In Z.Franco J. R. L. Rothkrantz (Ed.), ISCRAM 2012 Conference Proceedings – 9th International Conference on Information Systems for Crisis Response and Management. Vancouver, BC: Simon Fraser University.
Abstract: The effectiveness of emergency response largely depends on having a precise, up-to-date situational picture. With the World Wide Web having evolved from a small read-only text collection to a large-scale collection of socially created data accessible both to machines and humans alike, with the advent of social media and ubiquitous mobile applications, new sources of information are available. Currently, that potentially valuable information remains mostly unused by the command staff, mainly because the sheer amount of information cannot be handled efficiently. In this paper, we show an approach for turning massive amounts of unstructured citizen-generated content into relevant information supporting the command staff in making better informed decisions. We leverage Linked Open Data and crowdsourcing for processing data from social media, and we show how the combination of human intelligence in the crowd and automatic approaches for enhancing the situational picture with Linked Open Data will lead to a Web 3.0 approach for more efficient information handling in crisis management. © 2012 ISCRAM.
|
Massimiliano Tarquini, & Maurizio Morgano. (2013). Ethical challenges of participatory sensing for crisis information management. In J. Geldermann and T. Müller S. Fortier F. F. T. Comes (Ed.), ISCRAM 2013 Conference Proceedings – 10th International Conference on Information Systems for Crisis Response and Management (pp. 421–425). KIT; Baden-Baden: Karlsruher Institut fur Technologie.
Abstract: “Participatory Sensing is an approach to data collection and interpretation in which individuals, acting alone or in groups, use their personal mobile devices and web services to systematically explore interesting aspects of their worlds ranging from health to culture.”[ http://www.mobilizingcs.org/about/participatory-sensing] Data from the physical world of sensors and the virtual world of social networks and Linked Data can be combined into interesting high-level information. Sensor data can assist in localized information retrieval by giving the search engine direct access to events happening locally in the real world. Participatory sensing enables individuals and communities to collect and share granular, accurate data about a particular area. This paper describes work in progress within the FP7 EU-funded project SMART project to develop a multimedia search engine over content and information streaming from both the physical world and the Internet. We will identify some ethical problems regarding the use and storage of such data.
|
Yan Wang, Hong Huang, Lida Huang, Minyan Han, Yiwu Qian, & Boni Su. (2017). An Agile Framework for Detecting and Quantifying Hazardous Gas Releases. In eds Aurélie Montarnal Matthieu Lauras Chihab Hanachi F. B. Tina Comes (Ed.), Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (pp. 42–49). Albi, France: Iscram.
Abstract: In response to the threat of hazardous gas releases to public safety and health, we propose an agile framework for detecting and quantifying gas emission sources. Emerging techniques like high-precision gas sensors, source term estimation algorithms and Unmanned Aerial Vehicles are incorporated. The framework takes advantage of both stationary sensor network method and mobile sensing approach for the detection and quantification of hazardous gases from fugitive, accidental or deliberate releases. Preliminary results on street-level detection of urban natural gas leakage is presented. Source term estimation is demonstrated through a synthetic test case, and is verified using Cramér-Rao bound analysis.
|
Zainab Akhtar, Ferda Ofli, & Muhammad Imran. (2021). Towards Using Remote Sensing and Social Media Data for Flood Mapping. In Anouck Adrot, Rob Grace, Kathleen Moore, & Christopher W. Zobel (Eds.), ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management (pp. 536–551). Blacksburg, VA (USA): Virginia Tech.
Abstract: Ghana's capital, the Greater Accra Metropolitan Area (GAMA) is most vulnerable to flooding due to its high population density. This paper proposes the fusion of satellite imagery, social media, and geospatial data to derive near real-time (NRT) flood maps to understand human activity during a disaster and the extent of infrastructure damage. To that end, the paper presents an automatic thresholding technique for NRT flood mapping using Sentinel-1 images where four different speckle filters are compared using the VV, VH and VV/VH polarization to determine the best polarization(s) for delineating flood extents. The VV and VH bands together on Perona-Malik filtered images achieved the highest accuracy with an F1-score of 81.6%. Moreover, all tweet text and images were found to be located in flooded regions or in very close proximity to a flooded region, thus allowing crisis responders to better understand vulnerable communities and what humanitarian action is required.
|