Predicting Forest Fire Hazards Using Data Mining Techniques: Decision Tree and Neural Networks

Abstract

Lebanon is known as a tourist destination for its scenic green mountains but the fires have been threatening this green forestry all over the world. The consequences of forest fires are disastrous on the natural environment and ecological systems, not to mention the population, by worsening poverty and lowering the quality of life. Two data mining techniques are used for the purpose of prediction and decision-making: Decision trees and back propagation forward neural networks. Four meteorological attributes are utilized: temperature, relative humidity, wind speed and daily precipitation. The obtained tree drawn from applying the first algorithm could classify these attributes from the most significant to the least significant and better foretell fire incidences. Adopting neural networks with different training algorithms shows that networks with 2 inputs only (temperature and relative humidity) retrieve better results than 4-inputs networks with less mean squared error. Feed forward and Cascade forward networks are under scope, with the use of different training algorithms.