Indian Bushfire Detection Using Machine Learning and Neural Networks

Authors

  • Syed Ilyas Ayan Razvi, Abbu Talib, Syed Suffian Hussain, Syed Omer Farooq

DOI:

https://doi.org/10.17762/msea.v72i1.2363

Abstract

Forest fires are increasingly one of the most predominant and alarming disasters in the planet right now and preventing it is very important in order to protect the environment and thousands of animals and plants species that depend on it. The 2019–20 indian bushfire caused serious uncontrolled fires throughout the summer which burnt millions of hectares of land, destroyed thousands of buildings and killed many people. It has also been estimated to have killed about a billion animals and has bought endangered species on the brink of extinction. Such catastrophic events cannot be allowed to be repeated again. The primary goal of this paper is to improve the efficiency of forest fire detection system of australia. Data mining and machine learning techniques can help to anticipate and quickly detect fires and take immediate action to minimise the damage. In this paper we try to focus on the implementation of a set of well-known classification algorithms (k-nn and artificial neural networks), which can reduce the existing disadvantages of the fire detection systems. Results from the kaggle dataset infer that our ann-mlp algorithm (multilayer perceptron) yields better performance by calculating confusion matrix that in turn helps us to calculate performance measure as detection rate accuracy. All predictions and calculations are done with the help of data collected by lance firms operated by nasa’s earth science data and information system (esdis). The training and testing of the model was done using university of maryland dataset and was implemented using python.

Downloads

Published

2023-01-12

How to Cite

Syed Ilyas Ayan Razvi, Abbu Talib, Syed Suffian Hussain, Syed Omer Farooq. (2023). Indian Bushfire Detection Using Machine Learning and Neural Networks. Mathematical Statistician and Engineering Applications, 72(1), 1415–1420. https://doi.org/10.17762/msea.v72i1.2363

Issue

Section

Articles