StarTroopers| 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.

Spreading Wildfire awareness through an App which anyone can download and use around the world.

Summary

The project focuses majorly to increase awareness on increasing wildfires around the globe. It does not only convey the catastrophic aspects of a wildfire but also the economic aspects of it and how does it impact an economy of a country. A prototype of an app is created so that the public could report a nearby dangerous fire with just a click of a button and inform the nearby authorities to take immediate action. It also has a button redirecting the user to a website which contains vast information about different wildfires that took place in the US in the last two decades and also conveys the economical aspect of the California Fires 2020 to spread awareness about Wildfires in the user.

How We Addressed This Challenge

We developed an Android application which has the basic feature to let a user take a picture and report a nearby hazardous fire and inform the nearby authorities to take immediate action. It also has a button to guide the user to a website which contains a lot of information regarding wildfires built through a Tableau interactive dashboard and a story. The dashboard has an interactive and user-friendly visualization about wildfires happened in the US in the past two decades and also shows the trend how they have surprisingly increased twofold in the previous decade. It has another dashboard showing the economical aspects of the latest California wildfires in 2020.


We have built an ML model using TFLearn to detect fire in images or videos. FireNet architectures determine whether an image frame contains fire globally. This approach works in real time as well.


![](https://github.com/thakur22429s/nasa-space-apps-challenge/tree/main/fire-detection-cnn/output/188.jpg)

How We Developed This Project

We chose this challenge as it is the most pressing matter for the world. Wildfires are one event where we can try to control them and take several measures to even prevent them. After seeing a series of wildfires that took place this year and the Amazon bush fires last year, we were dedicated to do something about this. We thought of the locals who get seriously affected by such fires and to help them, we came up with our solution.

Tools used: Android Studio, Tableau, XLMiner

Coding languages used: Javascript, Python, Java

Hardware: None

Software: TFLearn

How We Used Space Agency Data in This Project

We used the MODIS_C6_Global_7d.csv dataset from the NASA Fire Information for Resource Management System (FIRMS) and used that to show the wildfires in different states in the USA incorporated on a Tableau dashboard and embedded it on the website.

To show the trend of past two decades, we used the US wildfires dataset from Kaggle as well.

Project Demo

https://drive.google.com/file/d/1DEmboVGnZmbZYBTzdVo_nHEY0jFssfSO/view?usp=sharing

Project Code
Data & Resources
  1. https://firms.modaps.eosdis.nasa.gov/data/active_fire/c6/csv/MODIS_C6_Global_7d.csv
  2. https://www.motherjones.com/environment/2020/09/these-5-stats-show-just-how-devastating-californias-wildfires-have-been-so-far/
  3. https://www.kaggle.com/rtatman/188-million-us-wildfires
Tags
#economical aspects, #ML, #AndroidApp
Judging
This project was submitted for consideration during the Space Apps Judging process.