Wildfire Prediction: Handling Uncertainties Using Integrated Bayesian Networks and Fuzzy Logic

Wildfire is one of the most frequent natural hazards across the globe, one which has cast a malevolent shroud over many communities in recent years, causing significant risk to human lives, infrastructure, and property. Wildfires are hydrogeological events which are bound to escalate, especially due to climate change. They are different from other natural hazards as they are mainly triggered by human interventions rather than natural triggers. The wildfire risk management is a complex process with many uncertainties in the assessment, fire behavior and spread modelling, and decision making. To predict wildfires, sophisticated temporal geospatial methods are required. This paper develops a wildfire probability prediction method considering the capabilities of Bayesian networks and fuzzy logic that can handle uncertainties and update probabilities in response to the availability of new data. The model takes into account the data from a geographic information system (GIS) for a specific area at micro level to estimate the wildfire probability and is able to update the probability due to any planned or unplanned changes in the area. Therefore, the proposed method can feed to future macro and micro risk-based decision-making situations in wildfire prone areas. The method is evaluated through a sensitivity analysis and its performance is investigated through a case study in New South Wales (NSW), Australia.