A SAFER mobile app for citizens, professionals and volunteers, will be designed and developed and will be implemented in the form of a chatbot to promote and integrated forest fire management. The chatbot application aims to both deliver and retrieve multimedia geolocated contents from smartphones. It can act as warning system in potentially affected areas and tasking/monitoring during emergencies. 

Using a conversational approach (i.e. a chat), this mobile application will allow professional responders to better coordinate their activities, enabling a better communication between field forces the control centers; crowdsource data collection activities involving citizens; and contextual communication on forest fire risks and self-protection behavior towards citizens for enhanced awareness.  The reasoning driving the selection of the “chatbot” instead of a traditional smartphone mobile application relies in the simplicity of access and effective usage. If on one hand, a smartphone application needs to be firstly downloaded from the App store (e.g. iOS or Google store), be installed on the user’s phone, needs continuous maintaining and upgrading and occupies space in the users’ smartphone; on the other hand, a chatbot can run on an existing messaging already present in the set of smartphone apps utilized by the user.

Wildfire management phase: prevention and preparedness; detection and response; adaptation and restoration.

This service will provide forecasted occurrence risk of relevant, high-impact weather variables and indices for wild/forest fires in time scales of days up to six weeks. In detail, the SAFERS intelligence service will deliver information and data related to:

• Short-range Weather observations and Fire Weather (FW) indices (up to 14 days): this service provides twice-a-day updated forecast up to two weeks ahead. This forecast is updated on a daily basis and allow its visualization over map, with different timeseries, zoom-ins, pan, overlays of different weather parameters with other data. These indices give information for awareness and early warning potential risk;

• Medium-range Weather forecast and Fire Weather indices (from 15 days up to 42 days): This service provides forecast up to 42 days and it is updated twice per week. It allows the visualization over map, timeseries, zoom, pan, overlays of different weather parameters with other data. These indices can be used in response-phase of forest fires;

• Probabilistic forecast (long term forecast), which will allow the visualization on map under user-defined thresholds;

• Weather alerts and early warnings, with user-defined thresholds and parameters.

The service involves statistical post-processing methods utilizing real-time and historical EO data, covering the whole sub-seasonal forecast scale that relevant to SAFERS for selected two pilot data sets provided by the European Centre for Medium-Range Weather Forecasts- ECMWF. In detail:

This service aims to augment the current operational wildfire early warning services with automated processes and local data fusion and model outputs. It is the integration of the EFFIS data, lightning forecasts, improving spatial resolution, and user provided local data. The service will allow automatic triggering of local services based on high resolution Earth Observation imagery.

Many emergency operators have access to certain levels of information, as already available. This SAFERS service aims to improve the existent information in order to make operations safer and better, by reducing the effects of forest fires.  In particular, this SAFERS intelligent service combines various sets of information from weather forecast; wildfire monitoring; wildfire risk models; automatic Earth Observation (EO) mapping - especially from Copernicus – integrating, as well, local user inputs.

This will allow to support local and regional wildfire stakeholders in reducing the impacts of wildfires based on up-to-date information; improve data and information access at a variety of scales to maximize decision support; and integrate state-of-the-art forecasting, modelling and user inputs into operational early warnings.

Wildfire management phase: prevention and preparedness; detection and response.

The SAFERS “Smoke and fire detection systems” intelligent service - i.e. the SmoCAM - is based on artificial intelligence that analyses images and detects the presence of smoke and fire. It provides a video analytics solution that works in the visible spectrum and exploits common surveillance cameras to early detect smoke plumes in outdoor, thus reinforcing prevention activities even when thermal cameras fail.

In detail, it will enable smoke and fire with non-dedicated situ imagery (thermal and video surveillance cameras), complementing the already existing proprietary WV solutions. As mentioned, SmoCAM includes artificial neural network-supported image processing for which the data model will be trained in four pilot installation sites. Data collection will be done real time and will create a weather condition database that will be used to inform local fire hazard scenarios.

This SAFERS intelligent service is intended to be used for early warnings. It is a tool aimed to improve safety in a variety of situations such as natural areas, parks, cultural heritage sites, archaeological sites and urban areas.

The SmoCAM can be used with Internet Protocol-IP surveillance camera with a full High Definition (HD) minimum resolution and performs server-side analytics and it is based on cutting edge computer vision techniques and machine learning technologies. This SAFERS service ensures detection accuracy in a variety of scenarios.

Wildfire management phase: detection and response; adaptation and restoration.

This SAFERS “On-demand nowcast and forecast” intelligent service aims to predict the spread and the potential impacts of an active fire, based on Earth Observation data, in order to support the decisions-making during forest fire emergencies.

In particular, this service aims to provide on-demand nowcast and forecast to be used to predict fire behavior, to define the strategy of fire attack, to anticipate emergency conditions, for adequate planning of evacuation and to simulate fire attack strategies.

Wildfire management phase: prevention and preparedness; detection and response.

The SAFERS “EO-based fire delineation and burnt area” intelligent service will establish an on-demand service able to delineate burned areas, fire fronts using Copernicus Sentinel-2 imagery, when available, and advanced artificial intelligence algorithms.

In detail, an AI module will be developed to delineate burned area boundaries and fire fronts based on Sentinel-2. Multiple machine and deep learning models will be used for comparison, and the best performing models will be operationalized to be triggered by other SAFERS detection services.

This service enables end-users to request a mapping activity by specifying the spatial-temporal references i.e. an area of interest and a time interval. Moreover, the service will produce maps according to the satellite data availability, including burned areas with a severity index and fire fronts.

Wildfire management phase: detection and response; adaptation and restoration.

This SAFERS intelligent service “Post wildfire habitat recovery monitoring” provides a monitoring service, that will use imagery obtained from Copernicus Sentinel satellites. In particular, Sentinel-1 for soil conditions; Sentinel-2 for vegetation, high resolution imagery; and Sentinel-3 for supporting imagery,  and temporal monitoring. This service aims to provide past and up-to-date land cover and vegetation maps to sustainably restore and monitor planned burned area restoration for automated reporting.

This service will offer continuous monitoring and reporting, enabling to support the reporting of Sustainable Development Goals (SDGs) and EU Green Deal targets; provide context to the development of post-wildfire recovery especially for Wildland-Urban Interface (WUI) planning; automate the monitoring of vegetation re-growth based on climate change resilience programs; and provides the quantification of forest fuel regeneration.

Wildfire management phase: adaptation and recovery.