The Outsiders| Spot That Fire V3.0

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.

Safe Forest

Summary

Our project is a mobile application which provides two separate services, the first is to identify the predicted fires by Satellites, and the app provides an alert service to residents near the expected location where the fire is expected to occur, to alert them several days before it. The second service is for sudden fires, where the one who notices the fire takes an instant picture and publishes it on the app so that all those living in the neighborhood can identify the fire and take the necessary precautions to avoid injury. While the app connects directly to a fire station near the fire, the app connects to NASA Firms while a fire occurs to alert NASA to take the necessary measures.

How We Addressed This Challenge

During the last years, wildfire frequency, intensity, and extent, as well as economic and human health impacts, have significantly increased worldwide. Thousands of acres of land have burned, homes and buildings have been destroyed, many animals have lost their lives by wildfires. But now, we believe that we can prevent this from happening by focusing on these two techniques: First, the time of prediction. A lot of losses were caused by the late fire prediction time or by incorrect prediction as NASA's Fire Information for Resource Management System (FIRMS) distributes Near Real-Time (NRT) active fire data within 3 hours of satellite observation from NASA's Moderate Resolution Imaging Spectroradiometer (MODIS) aboard the Terra and Aqua and then it will be too late to control the fire or take the necessary measures. So, we decided to use the data of the geostationary satellites from NOAA because it will be more useful as it will predict the fires faster than (MODIS) so that they can take the necessary measures. Second, making the data of the satellites clear and understandable for the decision makers and firefighters. So, we developed a machine learning model which will take the data from the satellites and show them on our application by a way that will be clear to anyone like the tracks of the fire on maps and graphs showing its impacts so it will be useful to the decision makers. So, by these two techniques, we will be able to save money, save trees, save lives, and make the world a better place. Also, we added some features to our application that make it special and different from the other solutions. Our application offers some services. First, the predicted fires, once we got the prediction based on natural factors from the satellite data for example that there will be a wildfire tomorrow, the app sends an alert to residents near the expected location where the fire is expected to occur to warn them and also sends the alert to the nearest fire station to take the necessary measures. And these will be SMS messages to ensure that everyone has got the message if anyone doesn’t have internet on their phone. Second, the unpredictable fires, where the one who notices the fire takes an instant picture and publishes it on the application so that all those living in the neighborhood can identify the fire and take the necessary precautions to avoid injury and to ensure that it’s a real fire, we will check the location on the satellite maps before sending the alert to people. Third, the part of volunteering. You can be a volunteer through our application by two ways. First, you can donate money to the people or families that have lost their homes because of fire or donate money to help the animals that got hurt because of the fire too. Second, you can be volunteer through helping firefighters to control the fire. And these features show that our application is special and different from other solutions. And here is a link for the simulation of our idea:

https://drive.google.com/drive/folders/177SdLgDxyIy08bIQhQqx4_JSO-ZyPrel?usp=sharing

How We Developed This Project

An uncontrolled wildfire can devastate everything in its path, spread for miles, crossing rivers and roads. Each year, between 60,000 and 80,000 wildfires occur, destroying between 3 and 10 million hectares. Recently, wildfires in California have also increased pollution and left devastation for animal wildlife. Unless the wildfires in California are somehow put into control, then the situation will continue to worsen and many more people will die or find themselves without home. And for these reasons we decided to work on this challenge. We started with the research as we searched about the past solutions then we started to search about the codes we need for ours then each member of the team had a task to do and finally we collected them together. Space agency data was very useful for us and literally we obtained our idea from the resources. First, the resources made us understand the challenge better. They have showed us that we can’t depend basically on the orbiting satellites like Terra and Aqua in the prediction of fires as they would take too long to observe a fire due to its orbiting around the earth so, we decided to depend on the geostationary satellites from NOAA as they will be very more useful as by using them, we can predict a fire a few days before it happens. So, Space agency data helped us a lot. To develop our project, we of curse used some tools, software, and coding languages. We used the help of some websites to make the needed video and a simulation for our application. Also, we used coding language to write the codes of our application which is python. Like any team we had a problem which was the we weren’t able to write the codes which allow us to take the data from the satellite and convert it to clear information so that it would be understandable for the firefighters and decision makers. But we were able to overcome this problem by the search. So, we searched a lot about how to write the codes and eventually we did it! We wrote the codes and overcame this problem and that was a great achievement to us. 

This presentation shows our Solution in more details: https://docs.google.com/presentation/d/1fToPsV8VprWU_e_WxxspOhUYvbsXFotr6sqhVtk__H0/edit?usp=sharing

This video as well:

https://drive.google.com/file/d/1bI_jRLUoW0d3umHIvUjCY-RlZadWw-lD/view?usp=drivesdk 

How We Used Space Agency Data in This Project

Space agency data did a great favor for us. First, we used the projects of the last two years as a reference as we took a look on the solutions of many teams, saw their ideas, determined their weaknesses and strengths so that we can come up with a new and effective solution so it was really really helpful. Second, The resources have showed us that we can’t depend basically on the orbiting satellites like Terra and Aqua in the prediction of fires as they would take too long to observe a fire due to its orbiting around the earth so, we decided to depend on the geostationary satellites from NOAA as they will be very more useful as by using them, we can predict a fire a few days before it happens. So, Space agency data helped us a lot.

Project Demo
Data & Resources
Tags
#Forests have the right to stay safe, #Machine Learning, #Wildfire Prediction, #Mobile Application, #NASA Firms, #Live-Action Prediction, #Satellites Prediction, #Alert, #Be a Volunteer
Judging
This project was submitted for consideration during the Space Apps Judging process.