Emergency Response Inference Mapping (ERIMap): A Bayesian network-based method for dynamic observation processing

TL;DR

Emergency response demands rapid synthesis of fragmented and uncertain information under time pressure. ERIMap leverages Bayesian networks integrated with GIS to process incomplete, uncertain, conflicting, dynamic, and spatial observations, producing evolving belief maps of key emergency variables. The method features a preparation phase for BN construction and area specification, and an operation phase for translating observations into evidence and updating beliefs across area-specific networks, including virtual evidence handling and a regret function to address conflicts. A gas-leak case study demonstrates dynamic, spatially resolved inferences that support decision-making, while highlighting limitations related to pre-existing knowledge and the need for empirical validation and user-centric tooling. Overall, ERIMap offers explainable, scalable situational awareness support for emergency responders in complex, real-time scenarios.

Abstract

In emergencies, high stake decisions often have to be made under time pressure and strain. In order to support such decisions, information from various sources needs to be collected and processed rapidly. The information available tends to be temporally and spatially variable, uncertain, and sometimes conflicting, leading to potential biases in decisions. Currently, there is a lack of systematic approaches for information processing and situation assessment which meet the particular demands of emergency situations. To address this gap, we present a Bayesian network-based method called ERIMap that is tailored to the complex information-scape during 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 thereby 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 that is updated each time a new observation becomes available. The method is illustrated in a case study in which an emergency response is triggered by an accident causing a gas leakage on a chemical plant site.

Figures (11)

• Figure 1: Example of a BN with two nodes, one edge, and respective marginal and conditional probability tables.
• Figure 2: Illustrative example of a BN with two initial nodes and one virtual node.
• Figure 3: Overview of the structure of the method and division of the following sections. The preparation phase includes the construction of the BN and specification of areas or locations. During the emergency operation phase, observations are collected and processed.
• Figure 4: Illustration of one initial BN (white filled nodes) duplicated for four different areas. For each area, different virtual nodes (orange filled) are added.
• Figure 5: Summary of the ERIMap method in the operation phase. Rectangles with rounded corners describe processes, grey rectangles describe the class of information. Decision nodes are diamond-shaped. Start and stop of the process are highlighted with green fill.