Motivation :

Climate change is a global challenge that has no borders and it is a reality that no one can deny. This serious threat is hitting the ecological system of the planet. Fires destroying forests is a form of this threat. for this, we chose to target the challenge ' Spot the fire V2.0 ' where we created a solution, with a main goal: to be applied everywhere in the world by giving developers an open source API to build the most suitable systems for their region, taking in considiration the network availability and other varients. we materialize the use of the API by developing diverse type of application that exploit the maximum of its potentiel. A walk through the app and system logic :

1.Fire predection : Our major challenge is to mitigate fires and why not eliminate them . And the best way to reach that is to exploit NASA's data using artificial intelligence methods to analyze different natural factors and then predict possible wildfires in our mother Earth . These predictions can serve many , starting with citizens,firemen , reseachers and future developers . Sources : The Global Fire Weather Database (GFWED) Earth Data DONKI ( weather solar flare ) EONET (natural event) OpenNex( climate , temperature) Features : Fire forecasting models like weather forecasting models or climate models, use mathematical equations to represent real-world processes such as : winds, cloud formation and growth and spread of fires and smoke.

These models require real-world data on fuels, terrain, weather conditions, and other factors that affect a fire behavior. These informations come from NASA satellite data. Algorithms : Firefighters use computer models to predict where and how a wildfire will spread over the next few hours .NASA researchers recently created a model that analyzes various weather factors that lead to the formation and spread of fires. The Global Fire Weather Database (GFWED) accounts for local winds, temperatures, and humidity, while also being the first fire prediction model to include satellite–based precipitation measurements. Predicting the intensity of fires is important because smoke can affect air quality and increase the amount of greenhouse gases in the atmosphere. One of the most used algorithms is WRF-SFIRE which is a "coupled" fire-atmosphere model. That means it simulates not only the fire and the weather but the evolving interactions between the two. For example,the rising heat from a fire can create a powerful updraft that makes winds stronger, causing the fire to spread more quickly.

2.notification: Both predecting & detecting fires have to be shared to inform the concerned population . From our analysis results , the app send notifications ; to citizens having smartphones ; firemen by alerts and by return , they inform and guide citizens espcially the ones who don't have smartphones . At the same time the fire men add an option to inform a citizens by Radio, TV and social media.

3.Detecting Fire & reporting: Reporting detected fire can be devided in two categories ; Smart automatic category : It provides two solutions : the first one is based on a research published on a recent paper at texas Tech and George Washington University titled “Coordinating Disaster Emergency Response with Heuristic Reinforcement Learning” documented a machine learning system that can analyze tweets and identify volunteers and victims, along with their locations. The second solution is the use of two NASA satellites : "AQUA and TERRA" currently orbiting the Earth scan nearly the entire planet once a day and can spot the thermal signature of a fire. The process takes at least three hours, beam down the data, and run the images through a supercomputer. The other category is based on reportes coming from users of the mobile app by providing images or videos of the fire with the location. following this user report a verification process is lunched by requesting images from nasa satellite for thermal signature and notifing the fire department if it's verified. After detecting fires, we thought about some solutions that can help concerned people :

-Mapping system : Which provides a map showing affected areas with some details : wind direction , diameter , flame length and variation ,temperature..In addition,we suggest the best way to escape a fire to reach rescue regions .

-Voice assistant : In time of panic , we innovate a solution which allows a transmission of safety tips and escape paths to a troubled citizen. In case of being offline: Let’s pretend that you’re camping, worst case scenario is that our services won’t reach you, so when you open the app, we’ll invite you to download some additional files and modules that may help you in case of fire .

4-Ways to engage citizens besides the technological solutions we aim to create a community that motivates people to invest themselves in using our system by announcing a periodic list of most contributing users in terms of fire reporting in every local region where the API is used and a global list covering all regions.

To have a better overview on the use of our API we made a small demo explaining main functionalities within our Mobile App FlaminGo.

Thank you.