Abstract: Emergency response scenarios are characterized by the participation of multiple agencies, which cooperate to control the situation and restore normality. These agencies can come from diverse areas of expertise which entails that they represent knowledge dierently, using their own vocabularies and terminologies. This fact complicates the automation of the information-sharing process, creating problems such as ambiguity or specialisation. In this paper we present an approach to tackle these problems by domain-aware semantic matching. This method requires the formalisation of domain-specific terminologies which will be added to an existing system oriented to emergency response. Concretely, we have formalised terms from the UK Civil and Protection Terminology lexicon, which gathers some of the most common terms that UK agencies use in these scenarios.

Abstract: The prevalence and severity of mental health disorders are high among first responders. Routine exposure to trauma, unique work patterns and the social stigma of seeking care exacerbate their challenges. While there are many mHealth applications for effective interventions, they primarily focus on support, education, and symptom identification and management. Our research uses empirical data to inform the customization of the BattlePeer application, previously tested among US veterans. Through focus groups with first responders, we identify specific barriers to help in this population. Our work highlights the potential benefits of adapting an app to create effective peer support strategies. We suggest the modification of BattlePeer to help first responders meet their mental health needs through peer support with tailored feedback and notifications. This will help negotiate the pervasive social isolation and hesitance in articulating emotions described in focus groups that lend to negative mental health outcomes.

Abstract: This paper is a position paper, presenting an original but very anticipative and mainly imaginative vision of the evolution of the crisis management domain. After analyzing the options to make the past evolutions of that domain somehow explainable (mainly by analyzing the data of all the articles of the last fifteen editions of the ISCRAM conference), the paper aims at providing a framework to assess and evaluate the maturity of the domain of crisis management. Moreover, this framework is also used to tentatively infer some future evolutions and some directions that could be relevant, dangerous, tricky or of great benefit for the crisis management domain. These future trends are mainly based on the current maturity of crisis management (according to the proposed framework) and current or future influential practices, technologies or threats. It will be necessary to wait for fifteen years to see if these bets should be considered as accurate.

Abstract: Offshore wind farms (OWFs) have become an increasingly relevant form of renewable energy in recent years, with the German North Sea being one of the most active regions in the world. However, the safety and security of OWF have become increasingly important due to the potential threats and risks associated with their growing share in the security of energy supply. This paper aims to present a comprehensive and systematic indicator-based approach to assess the safety and security status of OWFs in the German North Sea. The approach is based on the results of a survey of people working in the offshore industry and draws on the work published by Gabriel et al. (2022). The results of the study suggest that the indicator-based approach is a useful tool for end users to assess the security status of offshore wind farms and can be used for further research and development.

Abstract: During natural disasters, automatic information extraction from Twitter posts is a valuable way to get a better overview of the field situation. This information has to be geolocated to support effective actions, but for the vast majority of tweets, spatial information has to be extracted from texts content. Despite the remarkable advances of the Natural Language Processing field, this task is still challenging for current state-of-the-art models because they are not necessarily trained on Twitter data and because high quality annotated data are still lacking for low resources languages. This research in progress address this gap describing an analytic pipeline able to automatically extract geolocatable entities from texts and to annotate them by aligning them with the entities present in Wikipedia/Wikidata resources. We present a new dataset for Entity Linking on French texts as preliminary results, and discuss research perspectives for enhancements over current state-of-the-art modeling for this task.

Abstract: Flood evacuation planning models are an important tool used in preparation for flooding events. Authorities use the plans generated by flood evacuation models to evacuate the population as quickly as possible. Contemporary models consider the whole solution space and use a stochastic search to explore and produce solutions. The one issue with stochastic approaches is that they cannot guarantee the optimality of the solution and it is important that the plans be of a high quality. We present a heuristically driven flood evacuation planning model; the proposed heuristic is deterministic, which allows the model to avoid this problem. The determinism of the model means that the optimality of solutions found can be readily verified.

Abstract: Shock forest fires have short and long-terms devastating impact on the sustainable management and viability of natural, cultural and residential environments, the local and regional economies and societies. Thus, the utilisation of risk-based decision support systems which encapsulate the technological achievements in Geographical Information Systems (GIS) and fire growth simulation models have rapidly increased in the last decades. On the other hand, the rise of image and video capturing technology, the usage mobile and wearable devices, and the availability of large amounts of multimedia in social media or other online repositories has increased the interest in the image understanding domain. Recent computer vision techniques endeavour to solve several societal problems with security and safety domains to be one of the most serious amongst others. Out of the millions of images that exist online in social media or news articles a great deal of them might include the existence of a crisis or emergency event. In this work, we propose a Multi-Layer Fusion framework, for Real-Time Fire Severity Assessment, based on knowledge extracted from the analysis of Fire Multimedia Incidents. Our approach consists of two levels: (a) an Early Fusion level, in which state-of-the-art image understanding techniques are deployed so as to discover fire incidents and objects from images, and (b) the Decision Fusion level which combines multiple fire incident reports aiming to assess the severity of the ongoing fire event. We evaluate our image understanding techniques in a collection of public fire image databases, and generate simulated incidents and feed them to our Decision Fusion level so as to showcase our method's applicability.

Abstract: Floods are one of the major natural hazards in terms of affected people and economic damages. The increasing and often uncontrolled urban sprawl together with climate change effects will make future floods more frequent and impacting. An accurate flood mapping is of paramount importance in order to update hazard and risk maps and to plan prevention measures. In this paper, we propose the use of a supervised machine learning approach for flood delineation from satellite data. We train and evaluate the proposed algorithm using Sentinel-1 acquisition and certified flood delineation maps produced by the Copernicus Emergency Management Service across different geographical regions in Europe, achieving increased performances against previously proposed supervised machine learning approaches for flood mapping.

Abstract: Understanding and managing systemic risk has huge importance for disaster risk reduction in our globally connected world. The COVID-19 pandemic is a prominent case for the global impact of systemic risk. Did so the added urgency of the pandemic systemic risk trigger such paradigm shift? The use of qualitative modelling of systemic risk has progressed the field, particularly when policy makers need support urgently and want to utilize a range of interdisciplinary expertise. We have extended to disaster risk reduction a method for causal mapping for problem solving and strategy development targeting complex project management. Our approach delivers useful, useable, and used mitigation to systemic risk in a pandemic using participatory modelling with practitioners, domain experts and power-brokers.

Abstract: Social media posts tend to provide valuable reports during crises. However, this information can be hidden in large amounts of unrelated documents. Providing tools that automatically identify relevant posts, event types (e.g., hurricane, floods, etc.) and information categories (e.g., reports on affected individuals, donations and volunteering, etc.) in social media posts is vital for their efficient handling and consumption. We introduce the Crisis Event Extraction Service (CREES), an open-source web API that automatically classifies posts during crisis situations. The API provides annotations for crisis-related documents, event types and information categories through an easily deployable and accessible web API that can be integrated into multiple platform and tools. The annotation service is backed by Convolutional Neural Networks (CNNs) and validated against traditional machine learning models. Results show that the CNN-based API results can be relied upon when dealing with specific crises with the benefits associated with the usage word embeddings.

Abstract: The paper describes the need for, and work in progress to provide the French population with
a modern emergency communication infrastructure that uses open source components to
deliver real time communications from smart phones as well as traditional routes.
The article puts forward the vision of the NexSIS 18-112 project aimed at designing and
implementing the next generation AI enhanced emergency services response platform for
France. The vision and ambition of the NexSIS 18-112 system is to rewrite the command and
control system from scratch at a national level, providing it with state of the art functionalities.
Anticipating the future deployment of 5G networks, the work described in the article explains
how to ensure the transition of the legacy emergency operation systems to an operational IPbased
model, capable of offering voice, video, Instant Messaging, and Real Time Text (RTT)
services to emergency services? operators.

Abstract: During a natural disaster or emergency event, individual social media posts or hot spots may not necessarily correlate
to the most devastated areas. To better understand the correlation between social media and physical damage, we
compare Tweets, data about the physical environment, and socio-economic factors with insurance claim information
(as a proxy for physical damage) from 2017 Hurricane Irma in the state of Florida. We use machine learning
to identify relevant Tweets, sensitivity analyses to identify socio-economic factors, and statistical regression to
determine the predictive capability of insurance claims as a proxy for damage. We find that Tweets alone result in a
poorly fitted regression model of insurance claims, but the inclusion of physical features (e.g., power outages, wind
level) and socio-economic factors (e.g., population density, education, Internet access) improves the model?s fit.
Such models contribute to the knowledge base that may allow social media to predict damage in real-time.