Valerio Lorini, Carlos Castillo, Steve Peterson, Paola Rufolo, Hemant Purohit, Diego Pajarito, et al. (2021). Social Media for Emergency Management: Opportunities and Challenges at the Intersection of Research and Practice. 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. 772–777). Blacksburg, VA (USA): Virginia Tech.
Abstract: This paper summarizes key opportunities and challenges identified during the workshop “Social Media for Disaster Risk Management: Researchers Meet Practitioners” which took place online in November 2020. It constitutes a work-in-progress towards identifying new directions for research and development of systems that can better serve the information needs of emergency managers. Practitioners widely recognize the potential of accessing timely information from social media. Nevertheless, the discussion outlined some critical challenges for improving its adoption during crises. In particular, validating such information and integrating it with authoritative information and into more traditional information systems for emergency managers requires further work, and the negative impacts of misinformation and disinformation need to be prevented.
|
Victor A. Bañuls, Andrzej M. Skulimowski, & José Antonio Román Begines. (2021). Disaster Resilience Modeling of Municipal Water Supply Infrastructures in the Context of Atmospheric Threats. 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. 198–207). Blacksburg, VA (USA): Virginia Tech.
Abstract: The resilience of water supply infrastructure (WSI) is of utmost importance as threats to predominantly, although not exclusively, urban WSI may accompany virtually all kinds of natural disasters. In this paper, we present some of the challenges posed by climate change in modeling emergencies in WSIs. Climate change is a global phenomenon that significantly impacts global lifestyle. It is expected that increase in global temperatures causes sea levels to rise, increases the number of extreme weather events such as floods, droughts, and storms while highly impacting WSI. In this respect, the challenge is to be prepared for the unexpended by modeling various complex scenarios. Only with a multidisciplinary approach at the global, regional, national, and local levels, can success be achieved. We discuss some of the specific challenges posed by climate change in modeling emergencies in WSIs with a case study modeled using EMERTIC. EMERTIC is a software based on AI and scenarios, that is aimed at supporting decision making at different stages of the Emergency Management cycle.
|
Xiaojing Guo, Xinzhi Wang, Luyao Kou, & Hui Zhang. (2021). A Question Answering System Applied to Disasters. 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. 2–16). Blacksburg, VA (USA): Virginia Tech.
Abstract: In emergency management, identifying disaster information accurately and promptly out of numerous documents like news articles, announcements, and reports is important for decision makers to accomplish their mission efficiently. This paper studies the application of the question answering system which can automatically locate answers in the documents by natural language processing to improve the efficiency and accuracy of disaster knowledge extraction. Firstly, an improved question answering model was constructed based on the advantages of the existing neural network models. Secondly, the English question answering dataset pertinent to disasters and the Chinese question answering dataset were constructed. Finally, the improved neural network model was trained on the datasets and tested by calculating the F1 and EM scores which indicated that a higher question answering accuracy was achieved. The improved system has a deeper understanding of the semantic information and can be used to construct the disaster knowledge graph.
|
Xiaoyong Ni, Hong Huang, Wenxuan Dong, Chao Chen, Boni Su, & Anying Chen. (2021). Scenario Prediction and Crisis Management for Rain-induced Waterlogging Based on High-precision Simulation. 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. 159–173). Blacksburg, VA (USA): Virginia Tech.
Abstract: Many cities, especially those in developing countries, are not well prepared for the devastating disaster of exceptional rain-induced waterlogging caused by extreme rainfall. This paper proposes a waterlogging scenario prediction and crisis management method for such kind of extreme rainfall conditions based on high-precision waterlogging simulation. A typical urban region in Beijing, China is selected as the study area in this paper. High-precision and full-scale data in the study area requested for the waterlogging simulation are introduced. The simulation results show that the study area is still vulnerable to extreme rainfall and the subsequent waterlogging. The waterlogging situation is much more severe with the increase of the return period of rainfall. This study offers a good reference for the relevant government departments to make effective policy and take pointed response to the waterlogging problem.
|
Yan Wang, Qi Wang, & John Taylor. (2021). Loss of Resilience in Human Mobility across Severe Tropical Cyclones of Different Magnitudes. 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. 755–765). Blacksburg, VA (USA): Virginia Tech.
Abstract: Severe tropical cyclones impose threats on highly populated coastal urban areas, thereby, understanding and predicting human movements plays a critical role in evaluating disaster resilience of human society. However, limited research has focused on tropical cyclones and their influence on human mobility resilience. This preliminary study examined the strength and duration of human mobility perturbation across five significant tropical storms and their affected eight urban areas using Twitter data. The results suggest that tropical cyclones can significantly perturb human movements by changing travel frequencies and displacement probability distributions. While the power-law still best described the pattern of human movements, the changes in the radii of gyration were significant and resulted in perturbation and loss of resilience in human mobility. The findings deepen the understanding about human-environment interactions under extreme events, improve our ability to predict human movements using social media data, and help policymakers improve disaster evacuation and response.
|
Yasas Senarath, Jennifer Chan, Hemant Purohit, & Ozlem Uzuner. (2021). Evaluating the Relevance of UMLS Knowledge Base for Public Health Informatics during Disasters. 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. 97–105). Blacksburg, VA (USA): Virginia Tech.
Abstract: During disasters public health organizations increasingly face challenges in acquiring and transforming real-time data into knowledge about the dynamic public health needs. Resources on the internet can provide valuable information for extracting knowledge that can help improve decisions which will ultimately result in targeted and efficient health services. Digital content such as online articles, blogs, and social media are some of such information sources that could be leveraged to improve the health care systems during disasters. To efficiently and accurately identify relevant disaster health information, extraction tools require a common vocabulary that is aligned to the health domain so that the knowledge from these unstructured digital sources can be accurately structured and organized. In this paper, we study the degree to which the Unified Medical Language System (UMLS) contains relevant disaster, public health, and medical concepts for which public health information in disaster domain could be extracted from digital sources.
|
Yitong Li, Duoduo Liao, Jundong Li, & Wenying Ji. (2021). Automated Generation of Disaster Response Networks through Information Extraction. 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. 431–438). Blacksburg, VA (USA): Virginia Tech.
Abstract: Following a disaster, maintaining and restoring community lifelines require collective efforts from various stakeholders. Aiming at reducing the efforts associated with generating stakeholder collaboration networks (SCNs), this research proposes a systematic approach for reliably extracting stakeholder collaboration information from texts and automatically generating SCNs. In the proposed approach, stakeholders and their interactions are automatically extracted from texts through a natural language processing technique--Named Entity Recognition. Once extracted, the collaboration information is stored into structured datasets to automate the generation of SCNs. A case study on stakeholder collaboration in response to Hurricane Harvey is used to demonstrate the feasibility and applicability of the proposed approach. Overall, the proposed approach achieves the reliable and automated generation of SCNs from texts, which largely reduces practitioners' interpretation loads and eases the data collection process.
|
Ylenia Casali, Nazli Yonca Aydin, & Tina Comes. (2021). Zooming into Socio-economic Inequalities: Using Urban Analytics to Track Vulnerabilities – A Case Study of Helsinki. 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. 1028–1041). Blacksburg, VA (USA): Virginia Tech.
Abstract: The Covid19 crisis has highlighted once more that socio-economic inequalities are a main driver of vulnerability. Especially in densely populated urban areas, however, these inequalities can drastically change even within neighbourhoods. To better prepare for urban crises, more granular techniques are needed to assess these vulnerabilities, and identify the main drivers that exacerbate inequality. Machine learning techniques enable us to extract this information from spatially geo-located datasets. In this paper, we present a prototypical study on how Principal Component Analysis (PCA) to analyse the distribution of labour and residential characteristics in the urban area of Helsinki, Finland. The main goals are twofold: 1) identify patterns of socio-economic activities, and 2) study spatial inequalities. Our analyses use a grid of 250x250 meters that covers the whole city of Helsinki, thereby providing a higher granularity than the neighbourhood-scale. The study yields four main findings. First, the descriptive statistical analysis detects inequalities in the labour and residential distributions. Second, relationships between the socio-economic variables exist in the geographic space. Third, the first two Principal Components (PCs) can extract most of the information about the socio-economic dataset. Fourth, the spatial analyses of the PCs identify differences between the Eastern and Western areas of Helsinki, which persist since the 1990s. Future studies will include further datasets related to the distribution of urban services and socio-technical indicators.
|
Yohann Chasseray, Anne-Marie Barthe-Delanoë, Stéphane Négny, & Jean-Marc Le Lann. (2021). Automated unsupervised ontology population system applied to crisis management domain. 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. 968–981). Blacksburg, VA (USA): Virginia Tech.
Abstract: As crisis are complex systems, providing an accurate response to an ongoing crisis is not possible without ensuring situational awareness. The ongoing works around knowledge management and ontologies provide relevant and machine readable structures towards situational awareness and context understanding. Many metamodels, that can be derived into ontologies, supporting the collect and organization of crucial information for Decision Support Systems have been designed and are now used on specific cases. The next challenge into crisis management is to provide tools that can process an automated population of these metamodels/ontologies. The aim of this paper is to present a strategy to extract concept-instance relations in order to feed crisis management ontologies. The presented system is based on a previously proposed generic metamodel for information extraction and is applied in this paper to three different case studies representing three different crisis namely Ebola sanitarian crisis, Fukushima nuclear crisis and Hurricane Katrina natural disaster.
|
Yudi Chen, Angel Umana, Chaowei Yang, & Wenying Ji. (2021). Condition Sensing for Electricity Infrastructures in Disasters by Mining Public Topics from Social Media. 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. 598–608). Blacksburg, VA (USA): Virginia Tech.
Abstract: Timely and reliable sensing of infrastructure conditions is critical in disaster management for planning effective infrastructure restorations. Social media, a near real-time information source, has been widely used in the disaster domain for building timely, general situational awareness, such as urgent public needs and donations. However, the employment of social media for sensing electricity infrastructure conditions has yet been explored. This study aims to address the research gap to sense electricity infrastructure conditions through mining public topics from social media. To achieve this purpose, we proposed a systematic and customized approach wherein (1) electricity-related social media data is extracted by the classifier developed based on Bidirectional Encoder Representations from Transformers (BERT); and (2) public topics are modeled with unigrams, bigrams, and trigrams to incorporate the formulaic expressions of infrastructure conditions in social media. Electricity infrastructures in Florida impacted by Hurricane Irma are studied for illustration and demonstration. Results show that the proposed approach is capable of sensing the temporal evolutions and geographic differences of electricity infrastructure conditions.
|
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.
|
Zeno Franco, Chris Davis, Adina Kalet, Michelle Horng, Johnathan Horng, Christian Hernandez, et al. (2021). Augmenting Google Sheets to Improvise Community COVID-19 Mask Distribution. 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. 359–375). Blacksburg, VA (USA): Virginia Tech.
Abstract: Face mask scarcity in the United States hindered early infection control efforts during the COVID-19 pandemic. Areas with a history of racial segregation and poverty experienced differential COVID-19 death and morbidity rates. Supplying masks equitably and rapidly became an urgent public health priority. A partnership between a local manufacturer with available polypropylene fabric and the Medical College of Wisconsin, which had the capability to assemble and distribute masks, was formed in April, 2020. An improvised logistics framework allowed for rapid distribution more than 250,000 masks, and later facilitated hand-off to other organizations to distribute over 3 million masks. Using an action research framework three phases of the effort are considered, 1) initial deliveries to community clinics, 2) equitable distribution to community agencies while under “safer at home” orders, and 3) depot deliveries and transfer of logistics management as larger agencies recovered. A multi-actor view was used to interrogate the information needs of faculty and staff remotely directing distribution, medical student volunteers delivering masks, and the manufacturer monitorng overall inventory. Logistics information was managed using Google Sheets augmented with a small SQLite component. A phenomenological view, toggling back and forth from the “socio” to the “technical” provides detailed insight into the strengths and limitations of digital solutions for humanitarian logistics, highlighting where paper-based processes remain more efficient. This case study suggests that rather than building bespoke logistics software, supporting relief efforts with non-traditional responders may benefit from extensible components that augment widely used digital tools.
|
Zijun Long, & Richard Mccreadie. (2021). Automated Crisis Content Categorization for COVID-19 Tweet Streams. 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. 667–678). Blacksburg, VA (USA): Virginia Tech.
Abstract: Social media platforms, like Twitter, are increasingly used by billions of people internationally to share information. As such, these platforms contain vast volumes of real-time multimedia content about the world, which could be invaluable for a range of tasks such as incident tracking, damage estimation during disasters, insurance risk estimation, and more. By mining this real-time data, there are substantial economic benefits, as well as opportunities to save lives. Currently, the COVID-19 pandemic is attacking societies at an unprecedented speed and scale, forming an important use-case for social media analysis. However, the amount of information during such crisis events is vast and information normally exists in unstructured and multiple formats, making manual analysis very time consuming. Hence, in this paper, we examine how to extract valuable information from tweets related to COVID-19 automatically. For 12 geographical locations, we experiment with supervised approaches for labelling tweets into 7 crisis categories, as well as investigated automatic priority estimation, using both classical and deep learned approaches. Through evaluation using the TREC-IS 2020 COVID-19 datasets, we demonstrated that effective automatic labelling for this task is possible with an average of 61% F1 performance across crisis categories, while also analysing key factors that affect model performance and model generalizability across locations.
|
Øyvind Hanssen. (2021). Improving Trails from GPS Trackers with Unreliable and Limited Communication Channels. 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. 489–502). Blacksburg, VA (USA): Virginia Tech.
Abstract: In this document we explore position tracking in the context of land based search and rescue operations, where we also may have a limited and unreliable communication channel. This is the case when using APRS (amateur radio tracking) in voluntary SAR services in Norway. We have looked more closely into trails of movements and how to plot these on the map to present informative real-time pictures to the incident commanders. A simple scheme is proposed to improve trails by piggybacking positions at the end of regular transmissions.Experiments show that a significant amount of positions are recovered. In some cases this can recover useful information, though it depends on the actual situation.
|
