A Web-GIS wildfire prevention and management information system (AEGIS) was developed as a cost effective and easy-to-use forest fire platform (http://aegis.aegean.gr), aiming at reducing potential socioeconomic and environmental losses. The AEGIS platform assists with early fire warning, fire planning, fire control and coordination of firefighting forces by providing access to wildfire prediction data (fire danger and fire behavior), as well as to additional information such as socioeconomic activities, roads, land uses, water tanks, patrol routes, satellite images, detection cameras, vegetation types, terrain and weather data.
The system was developed and applied in seven different study areas from north to south of Greece with high-hazard, high-value and high-use forests and other multi-purpose sites. Detailed land use/ land cover maps were produced by combining field inventory data with high resolution multispectral satellite images (RapidEye) and other remote sensing techniques. Databases were created with spatial and non-spatial data to support key system functionalities. The system also incorporates weather measurements from remote automatic weather stations (http://meteo.aegean.gr) and weather forecast maps.
Artificial neural networks (ANN) and innovative geo-spatial tools were utilized for wildfire ignition risk assessment based on various parameters (i.e. latitude, longitude, altitude, month, day of week, distance from urban areas, distance from power lines, distance from main and secondary roads, distance from landfills, distance from agricultural areas, wind, rain, relative humidity and temperature), training methods, activation functions, pre-processing methods and network structures. The combination of ANNs and expected burned area maps produced an integrated output map for fire danger prediction.
Utilization of the Minimum Travel Time (MTT) algorithm acts as a powerful fire behavior prediction system; end users provide a minimum amount of inputs such as fire duration, ignition point and weather information to conduct a fire simulation. AEGIS offers three types of simulations; i.e. single-fire propagations, conditional burn probabilities and at the landscape level, similar to the FlamMap fire behavior modeling software. The implementation of the fire behavior research was achieved with the collaboration of one of the top research teams worldwide in the field of fire behavior algorithms; i.e. Dr. Mark Finney and associates (from the world renowned USDA Missoula Fire Sciences Laboratory in Montana, USA).
The structure of the algorithms relies on parallel processing techniques (i.e. High Performance Computing and Cloud Computing) that ensure computational power and speed. All AEGIS functionalities are accessible for free to authorized end users through a web-based graphical user interface. An innovative mobile application, AEGIS App, acts as a complementary means to the web-based version of the system. This research project is co-financed by the European Union (European Social Fund) and the Greek State within the framework of the Action ARISTEIA, with action’s beneficiary the General Secretariat for Research and Technology.