WaldFeuerwehr| 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.

Spot that Fire v3.0 - Team: WaldFeuerwehr (Mumbai, IN)

Summary

Utilizing datasets provided by NASA/CSA, EDA/Cleaning/Clustering of data, then with map polyline tool to derive a vector polygon(affected area is highlighted) ; next iteration marks some more points which generates second polygon which in turn highlights the spread of fire. Accuracy can be achieved using dynamic wind models and patterns across globe; which then triggers the economic losses mathematical model; generating estimated losses and sending this data through a domain server on a APP which will be used by end-user. Thus, solving the challenge 'Spot that fire 3.0' in simplest way.

How We Addressed This Challenge

Solution for the Challenge (Spot that fire 3.0):

 

 





  1. Collect/ clean/ cluster datasets
  2. Join and integrate data with Fire data from (FIRMS/NASA)
  3. Find the affected area by plotting the coordinates and based on the wind parameters and soil parameters we estimate the direction of spread and speed of spread based on the frequency of data updated from satellite.
  4. After considering the vegetation index(NDVI) we can estimate the area covered by tress and the loss incurred in form of resources.
  5. Applying Python mathematical model for indirect economic losses caused due firespread.
  • Collecting the costs of flora (vegetation or biomass)
  • Probability times the infrastructure costs.
  • Flagging the red / green / yellow.
  1. Impact on nearby Infrastructures or Government and Non Government investments (here e.g. Airports)
  2. datasets .json to APP
  3. APP for Emergencies (.apk)
How We Developed This Project


Softwares used:

 

 





  1. Python
  2. Android Studio
  3. kotlin
  4. TSQL
  5. QGIS
  6. Private Domain Server


Achievements:

 

 





  1. Collecting data from NASA Api OR CSV, Exploratory data analysis (EDA) for that data, Cleaning the data for particular subset of world (here we used Australia).
  2. Modelling whole system to model economic impact and predict depending on the data collected from the NASA FIRMS database.
  3. Mathematical forest economic model developed in python to generate economic losses.
  4. Observing the fire scenarios in Australia, this hotspot were well assessed for economic impacts. Although being a first world country they can minimize the damage and also observe spread and damage control through our app.
How We Used Space Agency Data in This Project

Datasets used (NASA + partner space agencies):

 

 





  1. NASA MODIS (TERRA/AQUA) only used for Fire Radiative Power (FRP) and DATE, TIME with CONFIDENCE LEVELS.
  2. CSA MOPITT data was used for Carbon emmisions data. ftp://data.asc-csa.gc.ca/
  3. MODIS PRODUCTS (NASA) for Vegetation index. (available until 2016)
Project Demo

https://github.com/rons4197/NASA_space_apps_PPT.git


https://github.com/rons4197/WaldFeuerwehr_Spotthatfire3.0.git

Data & Resources

Miscellanous datasets:

 

 





  1. NASA MODIS (TERRA/AQUA) only used for Fire Radiative Power (FRP) and DATE, TIME with CONFIDENCE LEVELS. https://firms.modaps.eosdis.nasa.gov/
  2. CSA MOPITT data was used for Carbon emmisions data. ftp://data.asc-csa.gc.ca/
  3. MODIS PRODUCTS (NASA) for Vegetation index. (available until 2016) https://modis.gsfc.nasa.gov/data/
  4. Airports open datasets (economic zones) https://openflights.org/data.html
Tags
#fastalerts #saveforests #nowildfires #economywildfires #wildfires #fires #wild #NASAwildfires #JAXAwildfires #Austrailianwildfires #CSAforestdata
Judging
This project was submitted for consideration during the Space Apps Judging process.