Spot That Fire V3.0

Recent wildfires worldwide have demonstrated the importance of rapid wildfire detection, mitigation, and community impact assessment analysis. Your challenge is to develop and/or augment an existing application to detect, predict, and assess the economic impacts from actual or potential wildfires by leveraging high-frequency data from a new generation of geostationary satellites, data from polar-orbiting environmental satellites, and other open-source datasets.

FireSense

Summary

Around the world, wildfires are becoming more frequent & deadly. Our cloud-based real-time responder application "FireSense" can help to prevent it before they get out of control.

How We Addressed This Challenge

Before begin, why don’t we take a look at some statistics of wildfire in the US?


As of 2020, approximately 3,754,729 acres of area has burnt in the wildfires of California.


In 2019, between January to October there are more than 40,000 wildfires reported in the Amazon rainforest, cost more than 957 billion dollars & about 906,000 hectares (9060 square km) have burnt. It also causes significant damages to the biodiversity & indigenous tribes.



That’s not all of it. NASA noted, “Africa is truly the fire continent. ”On an average day, satellites typically detect 10,000 actively burning fires around the world — 70 percent of which are in Africa.


According to, WHO between 1998-2017 about 6.2 million people affected by wildfires & volcanic activities & nearly 2400 deaths worldwide …. beyond fatalities, wildfires, and the resulting smoke and ashes, can cause:



  • Burns and injuries.
  • Eye, nose, throat, and lung irritation.
  • Decreased lung function, including coughing and wheezing.
  • Pulmonary inflammation, bronchitis, exacerbations of asthma, and other lung diseases.
  • Exacerbation of cardiovascular diseases, such as heart failure.

Our solution can help to reduce detection time and give enough time to the reaction!


Our Solution:

In this case, we’d like to share with you a mobile application based on the data provided by NASA. We created a GLOBAL FIRE DETECTION APPLICATION that can be used for detecting & visualizing all active fire-related incidents (like Wildfire, Volcanic Eruption) that allow the user to pinpoint the information.



Report Fire: Anyone can share a photo of a fire-related incident to social media or fire service via our app.

Verifying Data: By using data provided by NASA & Artificial Intelligence, will also cross-check if the data (sent by users) is true or false. Users need to register with their mobile number & government-provided national card/passport, so we can take legal actions if anyone posted false news.




Prediction & Detection: Our application will monitor information like suspicious temperature rising, latitude-longitude, air humidity, weather analysis, wind speed, rate of carbon dioxide, and applying machine learning it can predict and spot the wildfire instantly, it will also predict where the possible area of destruction is. Furthermore, we used GIS Machine Learning technology for image processing, object identification, anomaly detection, and surface mapping.

Our application will monitor this information, 




  • Latitude-longitude 
  • Suspicious Temperature Rising
  • Air humidity
  • Weather analysis 
  • Wind speed
  • Rate of carbon dioxide



Real Time Notification: Any app user within a 5 km radius will be notified if there are any fire-related incidents.



Emergency Evacuation: By using this application, notified people can evacuate themselves to find a safe spot.





Emergency Social Work & Rescue: It will also connect the fire service, medical units, relief workers & volunteers. It will reduce a significant amount of damages and provide aid to victims instantly.

How We Developed This Project

Our application based on 




  • Data provided by NASA
  • Artificial Intelligence 
  • GIS Machine Learning 
  • VISD (Video Image Smoke Detection) Technology



Tools we used to develop this project



  • Unity
  • C#
  • Python
  • Shader Lab
  • MapBox
  • QGIS (Geographic Information System Application)
  • Rastar Vision Plugin



What's Next?

We are working to enhance our prediction accuracy. So, we need more satellite data. That’s why we need to collect data from regional satellites. We will use IoT, drones & sensors to gather more data from the potential wildfire hotspots.

How We Used Space Agency Data in This Project

We processed data from three different satellites of NASA & visualized it through our app. We can observe it for 24 hours, 48 hours, or 7 days simultaneously, which can predict the vulnerable spot, for that case authority can assure serious measures to prevent it before any serious incidents can happen






We used the QGIS with Rastar Vision Plugin to analyze geological data provided by NASA(Fire Information for Resource Management System (FIRMS) ). Then we merged this data with Mapbox, an advanced map system to visualize it via Unity.

Data & Resources

Data We Used:

We collected data from,





We used those kind of data,



  • VIIRS 375m (The Visible Infrared Imaging), 
  • NOAA 20 satellite, 
  • Soumi NPP (The Soumi National Polar-Orbiting Partnership) Satellite, 
  • Modis (Moderate Resolution Imaging Spectroradiometer), 
  • EOSAM-1 Satellite data from NASA. 
Tags
#spot_the_fire_v3, #team_spectre #Wildfire
Judging
This project was submitted for consideration during the Space Apps Judging process.