Automated Detection of Hazards

Countless phenomena such as floods, fires, and algae blooms routinely impact ecosystems, economies, and human safety. Your challenge is to use satellite data to create a machine learning model that detects a specific phenomenon and build an interface that not only displays the detected phenomenon, but also layers it alongside ancillary data to help researchers and decision-makers better understand its impacts and scope.

Chase The Fires

Summary

Using satellites, we measure the thermal radiation of living organisms in the specified area, from which we determine the type, density and condition of living organisms by making a classification using artificial intelligence. By using humidity sensors, we can determine the wind speed and by the direction of the wind and the path of the fire and we can, using artificial intelligence, make a heat map, and thus predict the location of fires and the specifications, and thus the fires can be controlled and faced. We aren’t only target humans and rare plants found in some fire-prone areas, but also rare animal breeds found in forests such as in the Amazon as we've made an evacuation plan for it.

How We Addressed This Challenge

What did We develop?

We developed an application to chase the fire to make classification and predict the areas where the fire will spread using artificial intelligence.



Why is it important?

Controlled burns have become more important as fire suppression efforts have grown over the last century. Historically, smaller fires occurred in forests at regular intervals. When these fires are suppressed, flammable materials accumulate, insect infestations increase, forests become more crowded with trees and underbrush, and invasive plant species move in.



What does it do?

  1. Classification of plant status.
  2. Determining the path of the fire.
  3. predict the location of fires
  4. Targeting humans ,rare plants found in some fire-prone areas, and rare animal breeds found in forests.

How does it work?

  1. Using satellites, we measure the thermal radiation of living organisms in the specified area, from which we determine the type, density and condition of living organisms.
  2. By making a classification using artificial intelligence, and based on the classification we determine if the plant is alive.
  3. By using humidity sensors, we can determine the wind speed, and by the direction of the wind, we determine the path of the fire.
  4. We made an Desktop and Hardware Application to Make a heat map based on the Satellites, Classification and Sensors results to predict the location of fires and the specifications, and thus the fires can be controlled and faced.
  5. Sending Waves at certain frequencies that will attract animals to safe areas outside the expected fire path.

What you hope to achieve?

We hope to reduce the risks of fires and predict their occurrence and save people from these areas, and also animals that are found in forests such as the Amazon forests that are exposed to huge fires throughout the year.

How We Developed This Project

1-What inspired your team to choose this challenge?

We have inspired to choose this challenge because the world is exposed to many fires every year, as an example of the Amazon forests Since January 2019 until now around 80,000 fires in the Amazon.



2-What was your approach to developing this project?

We are developing this project to accomplish the benefits that regular fires historically provided to an environment while also preventing the forests from burning out of control and threatening life and property.



3-What tools, coding languages, hardware, software did you use to develop your project?

  1. Tools : MATLAB Machine Learning - MATLAB App Designer-Arduino IDE - Proteus
  2. Coding Languages :MATLAB - Embedded C - Arduino C - C++
  3. Hardware: we design two circuit:
  4. Sensor Circuit: Atmega 328P - Smoke Sensor - MPU 6050 - DHT22
  5. High Frequency Circuit :555 IC-Capacitors - Resistors -Potential Resistors - Piezo
  6. Software: MATLAB Libraries - Classification And Regression Trees for Machine Learning "CART" - Atmega 328 SDK
How We Used Space Agency Data in This Project

We used NASA dataset to build a machine learning model. The functionality of this model is to predict forest fires, its types, and which direction it will go.

Data & Resources
  1. Fire_archive_M6_157333 data set.
  2. P. Cortez and A. Morais. A Data Mining Approach to Predict Forest     Fires using Meteorological Data. In J. Neves, M. F. Santos and J. Machado Eds, New Trends in Artificial Intelligence, December, 2007.
  3. D. Stojanova, P. Panov, A. Kobler, S. Dzeroski, and K. Taskova. Learning to Predict Forest.
  4. Fires with Different Datamining Techniques. In D. Mladenic and M. Grobelnik, editors.
  5. International multiconference Information Society (IS 2006), Ljubljana, Slovenia, 2006.
Tags
#embedded_systems,#artificial_intelligence,#forest_fires, #AI
Judging
This project was submitted for consideration during the Space Apps Judging process.