Title: Cloud and IoT-based Implementation and Validation of a Predictive Fire Risk Indication Model
Speaker: Lars M. Kristensen, IDER, HVL
The high representation of wooden houses in Norwegian cities combined with periods of dry and cold climate during the winter time often results in a high risk of severe fires. This makes it important for public authorities and fire departments to have an accurate estimate of the current fire risk in order to take proper precautions. We have implemented a predictive model which exploits measurements from weather stations and weather forecasts from the Norwegian Meteorological Institute. This data is in turn used to predict the current and future fire risk at a given geographical location. We have experimentally validated the model during the winter period at selected geographical locations, and by considering weather data from the time of several historical fires. Our results show that our cloud and IoT-based implementation is both time and storage efficient, and capable of being able to accurately predict the fire risk measured in terms of the estimated time to flashover.
Joint work with Torgrim Log and Sindre Stokkenes, and part of the NFR Funded DYNAMIC project at HVL.