Abstract: This article shows the research process carried out by Regional Government of southern Europe, with more than 8 million citizens, to create an Information System to serve as a diagnostic and certification model for the resilience level of the municipalities of that region. This Information System will allow the local authorities of the regional governments to know in what situation they are and what they should do to improve their resilience level. The research framework is based on the best practices in urban resilience. One of the relevant characteristics of the work is the integration of the knowledge of a very heterogeneous group of experts for the identification of the special needs of the target region that has been articulated through a Delphi process.

Abstract: Flooding is a natural hazard that causes a lot of deaths every year and the number of flood events is increasing worldwide because of climate change effects. Detecting and monitoring floods is of paramount importance in order to reduce their impacts both in terms of affected people and economic losses. Automated image analysis techniques capable to extract the amount of water from a picture can be used to create novel services aimed to detect floods from fixed surveillance cameras, drones, crowdsourced in-field observations, as well as to extract meaningful data from social media streams. In this work we compare the accuracy and the prediction performances of recent Deep Learning algorithms for the pixel-wise water segmentation task. Moreover, we release a new dataset that enhances well-know benchmark datasets used for multi-class segmentation with specific flood-related images taken from drones, in-field observations and social media.

Abstract: Abstractive summarization is intended to capture key information from the full text of documents. In the application domain of disaster and crisis event reporting, key information includes disaster effects, cause, and severity. While some researches regarding information extraction in the disaster domain have focused on keyphrase extraction from short disaster-related texts like tweets, there is hardly any work that attempts abstractive summarization of long disaster-related documents. Following the recent success of Reinforcement Learning (RL) in other domains, we leverage an RL-based state-of-the-art approach in abstractive summarization to summarize disaster-related documents. RL enables an agent to find an optimal policy by maximizing some reward. We design a novel hybrid reward metric for the disaster domain by combining \underline{Vec}tor Similarity and \underline{Lex}icon Matching (\textit{VecLex}) to maximize the relevance of the abstract to the source document while focusing on disaster-related keywords. We evaluate the model on a disaster-related subset of a CNN/Daily Mail dataset consisting of 104,913 documents. The results show that our approach produces more informative summaries and achieves higher \textit{VecLex} scores compared to the baseline.

Abstract: Many governments, organizations, practitioners and researchers involved in collaboration on resilience in emergency management are agreed that this is a key aspect. The QuEP+R framework aims to improve resilience in an organization's emergency plan management, in which the stakeholders must be adequately prepared and trained for their responsibilities in the emergency plan, providing techniques that propose the improvement of the emergency plan besides resilience. However, for these techniques to be effective, organizations need the theoretical resilience proposed in QuE+R to be implemented. The CiET framework was designed for this purpose and has learning objectives and training contents related to QuEP+R techniques to train stakeholders. The CiET capability plan contents have been classified by resilience dimensions towards the optimization of resilience in emergency plan management. The integration is supported by I+R-Tool, which generates the capability plans automatically from the results of the QuEP+R assessment, which outcomes in a stakeholder's effective training, contributing to the optimization and improvement of the resilience, therefore, in improving the quality of emergency plans. Hence, the aim remains to search for the continuous improvement of the emergency plan management within organizations.

Abstract: Risk analysis of snowmelt flood is an urgent demand in cold highland areas. This paper focuses on the method for the rapid and reliable forecast of daily snowmelt, snow water runoff, and snowmelt flood risk. A neural network algorithm is used to calculate snow density distribution, snow depth and snow-water equivalent with the brightness temperature data. Then, daily snowmelt is predicted using the degree-day factor method with the temperature distribution. On this basis, we use the steepest descent method and Manning formula with hydrographic information to simulate snow water runoff. We also propose a method to predict the snowmelt flood risk with the geographic feature and historical flood data. The evaluated risk is compared with monitored data in the Xinjiang Autonomous Region of China, which shows good consistency. At last, we develop a risk analysis system to generate the snowmelt flood risk map and provide risk analysis service.

Abstract: Digital technologies have become an integral enabler of communication during various phases of emergency management (EM). A crucial prerequisite of effective communication between authorities and the public during EM is the establishment of adequate mutual trust. Trust, however, is an elusive concept which is not easily translatable into technical settings. In this paper we propose an integrative model of trust in digital communication and show how such model can be advantageous in assessing and improving trust relations in context of EM. Our interdisciplinary model, which is based on findings from psychology, sociology and computer sciences provides an abstraction which not only seizes both subjective and objective as well as personal and non-personal, \eg institutional or cultural, aspects of trust but at the same time is concrete enough to be applicable to real-life scenarios.

Abstract: The ubiquity of mobile internet-enabled devices combined with wide-spread social media use during emergencies is posing new challenges for response personnel. In particular, service operators are now expected to monitor these online channels to extract actionable insights and answer questions from the public. A lack of adequate tools makes this monitoring impractical at the scale of many emergencies. The TREC Incident Streams (TREC-IS) track drives research into solving this technology gap by bringing together academia and industry to develop techniques for extracting actionable insights from social media streams during emergencies. This paper covers the second year of TREC-IS, hosted in 2019 with two editions, 2019-A and 2019-B, contributing 12 new events and approximately 20,000 new tweets across 25 information categories, with 15 research groups participating across the world. This paper provides an overview of these new editions, actionable insights from data labelling, and the automated techniques employed by participant systems that appear most effective.

Abstract: Robots such as unmanned aerial vehicles (UAVs) deployed for search and rescue (SAR) can explore areas where human searchers cannot easily go and gather information on scales that can transform SAR strategy. Multi-UAV teams therefore have the potential to transform SAR by augmenting the capabilities of human teams and providing information that would otherwise be inaccessible. Our research aims to develop new theory and technologies for field deploying autonomous UAVs and managing multi-UAV teams working in concert with multi-human teams for SAR. Specifically, in this paper we summarize our work in progress towards these goals, including: (1) a multi-UAV search path planner that adapts to human behavior; (2) an in-field distributed computing prototype that supports multi-UAV computation and communication; (3) behavioral modeling that yields spatially localized predictions of lost person location; and (4) an interface between human searchers and UAVs that facilitates human-UAV interaction over a wide range of autonomy.

Abstract: This paper aims at studying the role of Wikipedia in social resilience processes during terrorist attacks. It discusses how Wikipedia users' specific skills are mobilized in order to make sense of the event as it unfolds. We have conducted an ethnographic analysis of several Wikipedia's terrorist attacks pages as well as interviews with regular Wikipedia's contributors. We document how Wikipedia is used during crisis by readers and contributors. Doing so, we identify a specific pace of contributions which provides reliable information to readers. By discussing the conditions of their trustworthiness, we highlight how historical sources (i.e. traditional media and authorities) support this pace. Our analyses demonstrate that citizens are engaging very quickly in processes of resilience and should be, therefore, considered as relevant partners by authorities when engaging a response to the crisis.

Abstract: In this article, we want to present the concept for a risk management approach to assess the condition of critical infrastructure networks within metropolitan areas, their interdependencies among each other and the potential cascading effects. In contrast to existing solutions, this concept aims at providing a holistic view on the variety of interconnected networks within a city and the complex dependencies among them. Therefore, stochastic models and simulations are integrated into risk management to improve the assessment of cascading effects and support decision makers in crisis situations. This holistic view will allow risk managers at the city administration as well as emergency organizations to understand the full consequences of an incident and plan mitigation actions accordingly. Additionally, the approach will help to further strengthen the resilience of the entire city as well as the individual critical infrastructures in crisis situations.

Abstract: This paper takes on the challenge of designing situational awareness information systems that take into account not only the prevalence of so-called demons of situational awareness, but also situational disabilities that will typically occur in a disaster situation, both in the control room and in the field among the general public as well as first responders. It further outlines how a situational awareness information system process model can be adapted and used as a basis for designing situational awareness information support systems that address these issues with the help of Universal Design principles.

Abstract: This study aims to design a route planner functionality that includes real-time context information from physical sensors and citizen observations to support pedestrian navigation in urban areas exposed to extreme heat and floods. Urban population is growing and people living in urban areas are especially exposed to heat and urban flooding, which are two of the anticipated effects of climate change. Route planning functionality can be of value to individual citizens, especially those with limited mobility, as well as for healthcare professionals and authorities who are responsible for crisis response and management. Although the route planner functionality is to be experimentally implemented in a specific tool with the use of broadly available web technologies and real time data, a major generic outcome is the framework that can be used to develop the functionality as part of a decision support tool of any kind.

Abstract: Securing the accessibility of emergency vehicles using specific emergency transportation road (SETR) is crucial for the rapid activities of emergency vehicles after a large earthquake. In this paper, we construct a simulation model that describes collapse of roadside buildings and following street blockages, and evaluate the accessibility of emergency vehicles. Performing the simulations, we demonstrate the effects of quake-resistant-conversion of roadside buildings as follows: (1) the accessibility of emergency vehicles using SETR is not good enough under the current situation, but (2) can be significantly improved by performing seismic retrofit of buildings according to seismic index of building structure.