To Predict the Fire Outbreak in Australia using Historical Database
Devendra K. Tayal, Nidhi Agarwal, Anjali Jha, Deepakshi, Vrinda Abrol
Abstract
Australian bush fires have caused huge damage, not only to the environment but also to the community. In southeastern Australia, 11.5 million hectares (28.4 million acres) of bushland and forest was affected during the “Black Summer” Bushfire of 2019–2020. The frequency of bushfires gives context for modelling different climate data to accurately anticipate future hot regions for bushfires. In this study, we have implemented a Machine Learning based Decision Tree Model to construct a Forest Fire Prediction Model using data from the last 20 years. This algorithm is derived from a collection of unrelated decision trees. Additionally, we converted observed fire spots into a continuous density of fire spots and made a choropleth map. The prediction model's structure makes it possible to produce predictions with a higher degree of accuracy. Additionally, it helps to increase assistance for fire crews at the front-line.