Firen't| Spot That Fire V3.0
Spot That Fire V3.0
Firen’t (Global forest fire detection system)
Summary
Public entities in all countries face the challenge of addressing and mitigating the effects caused by forest fires. However, the information on these is in an isolated way and this depends on the warnings given by the population close to the fire. We resort to satellite data provided by FIRMS and using unsupervised machine learning algorithms to find points of interest, in addition this information is related to data from cities and towns to be able to estimate the distance to people's homes and from this In order to have the capacity to notify the authorities of these places, in addition to estimating the economic impact that these fires entail.
How We Addressed This Challenge
Firen’t is an integrated information portal that aims to detect and measure the impact generated by forest fires around the world, in addition to presenting useful information to the populations of the area. All this is done in order for the tool to be used by authorities around the world in order to streamline mitigation and evacuation procedures for populations near forest fires, in addition to presenting information regarding the economic impact of forest fires .
How We Developed This Project
In the first instance, the data provided by all the satellites in the FIRMS database are used, and with these we proceed to make a cleaning of the information where the data is eliminated with a low confidentiality rate, after this is applied a clustering algorithm (mean shift clustering) which aims to find the sets of points that present a high density of hot spots per unit area, and with the groups found, we proceed to estimate the area of action of the detected fire, and With this estimate of the affected area, we proceed to estimate the costs associated with its mitigation in addition to the economic losses caused by this, finally we proceed to find the cities near the detected fire to notify the nearby communities.
How We Used Space Agency Data in This Project
In this project the information provided by the FIRMS database was used, these data are the backbone of this project since from these the machine learning algorithms are applied, in addition to the results being crossed with the data of the populations throughout the world to obtain relevant information regarding the danger that people are exposed to.
Project Demo
Web site:
https://dashboardnasa.herokuapp.com/main%20map.html
Youtube video:
https://www.youtube.com/watch?v=ccHLAB4y42U&feature=youtu.be
Project Code
Data & Resources
· Fire Information for Resource Management System. (2020). Retrieved 3 October 2020, from https://firms.modaps.eosdis.nasa.gov/active_fire/#firms-txt
· World Cities Database | Simplemaps.com. (2020). Retrieved 3 October 2020, from https://simplemaps.com/data/world-cities
· D. Alexandrov, E. Pertseva, I. Berman, I. Pantiukhin and A. Kapitonov, "Analysis of Machine Learning Methods for Wildfire Security Monitoring with an Unmanned Aerial Vehicles," 2019 24th Conference of Open Innovations Association (FRUCT), Moscow, Russia, 2019, pp. 3-9, doi: 10.23919/FRUCT.2019.8711917.
· D, Jonh. “Economic Impacts of Wildfire”, 2012, Southern Fire Exchange (SFE). Florida, United States, doi: SFE Fact Sheet 2012-7.
· Rodríguez y Silva, Francisco; Martínez, Juan Ramón Molina; Soto, Miguel Castillo. 2013. Methodological approach for assessing the economic impact of forest fires using MODIS remote sensing images. In: González-Cabán, Armando, tech. coord. Proceedings of the fourth international symposium on fire economics, planning, and policy: climate change and wildfires. Gen. Tech. Rep. PSW-GTR-245 (English). Albany, CA: U.S. Department of Agriculture, Forest Service, Pacific Southwest Research Station: 281-295.
· Di Fonzo M., P.M. Falcone, A.R. Germani, C. Imbriani, P. Morone, F. Reganati (2015). The Quantitative and Monetary Impacts of Forest Fire Crimes. Report compiled as part of the EFFACE project, University of Rome “La Sapienza”, www.efface.eu