A new emergency decision support system: the automatic interpretation and contextualisation of events to model a crisis situation in real-time

This paper studies, designs and implements a new type of emergency decision support system that aims to improve the decision-making of emergency managers in crisis situations by connecting them to new, multiple data sources. The system combines event-driven and model-driven architectures and is dedicated to crisis cells. After its implementation, the system is evaluated using a realistic crisis scenario, in terms of its user interfaces, its ability to interpret data in real time and its ability to manage the 4Vs of Big Data. The input events correspond to traffic measurements, water levels, water flows, water predictions and flow predictions made available by French official services. The main contributions of this study are: (i) the connection between a complex event processing engine and a graph database containing the model of the crisis situation and (ii) the continuous updating of a common operational picture for the benefit of emergency managers. This study could be used as a framework for future research works on decision support systems facing complex, evolving situations