Limassol, Cyprus. A satellite-based system using machine learning to detect wildfires across Cyprus 24 hours a day has been presented in Limassol, aiming to provide first responders with earlier and more reliable warnings of possible outbreaks.
The Geosfire project, funded by TechIsland, was presented on Thursday by Anna Zenonos, a researcher at the Cyprus Institute’s Climate and Atmosphere Research Centre, as part of the TechIsland Wildfire Initiative.
System tailored to Cyprus
Geosfire, which stands for Geospatial Earth Observation System for Fire Intelligence and Real-time Evaluation, is being developed specifically for Cyprus.
Zenonos said the project aims to create a satellite-based, machine-learning fire detection and alert system tailored to Cyprus’ geographic and climatic conditions and the operational needs of first responders.
Round-the-clock satellite monitoring
Unlike traditional monitoring methods that largely rely on people seeing smoke or flames, Geosfire uses satellite data to monitor locations across the island.
Zenonos said the system enables 24-hour fire detection across all locations and addresses the limitations of visual monitoring, which is restricted to daytime and populated areas.
The approach could be particularly relevant in remote or sparsely populated areas, where fires may develop without being immediately noticed by residents, drivers or patrols. Satellite monitoring can also continue at night, when visual observation is more difficult.
Detection and decision support
Geosfire uses data from recently launched satellite systems and applies machine-learning algorithms to identify possible fire outbreaks and generate alerts.
The project also includes a visualisation platform for real-time monitoring, situational awareness and decision support, presenting satellite information in a format intended to be more accessible to first responders.
