Spatial inferences for enhanced situation awareness

Abstract

In emergencies, high-stakes decisions often have to be made under time pressure and stress. To support such decisions, information from multiple sources needs to be gathered and processed quickly. The available information tends to be temporally and spatially variable, uncertain and sometimes conflicting, leading to potential biases in decisions. To address this issue, we propose a Bayesian network-based method, called ERIMap, that is tailored to the complex information landscape in emergencies. The method enables the systematic and rapid processing of heterogeneous and potentially uncertain observations and draws inferences about key variables of an emergency. It reduces complexity and cognitive load for decision makers. The output of the ERIMap method is a dynamically evolving and spatially resolved map of beliefs about key variables of an emergency, which is updated each time a new observation becomes available. The ERIMap method has the advantage that it follows a very general principle that can be easily transferred to other applications. Therefore, in addition to a case study illustrating the method of emergency response triggered by a gas leak accident at a chemical plant, an outlook on possible applications in the field of security will be given.