Tools
Tools
Sahoo, Amit (2020) Classification of Wildfire Spread Severity using Machine Learning Algorithm. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (864kB) | Preview |
Abstract
Wildfire is one of the natural disasters, that can burn millions of acres of land at a very fast speed, almost burning everything that comes in the way. However, only a few of the wildfire occurs on their own, while majority are human caused. In this research, the size of the fire spread has been predicted, with respect to the weather details of the last five days of the outbreak. This research will help the Fire Fighting Department and the local governing body to predict the fire spread in advance and make decisions accordingly. Alaska location has been chosen specifically, for this research as there is a huge difference in temperature in summer and winter. Data has been collected from various sources and have been merged. At every stage of pre-processing, a Logistic Regression has been used as a baseline model. The technique that produces the highest accuracy has been carried forward to the next stage. Several Machine Learning algorithms have been performed, and it is observed that Artificial Neural Network, outperforms the other tree-based algorithms, ensembled algorithms and LSTM with an accuracy of 68%.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Dan English |
| Date Deposited: | 25 Jan 2021 14:39 |
| Last Modified: | 25 Jan 2021 14:39 |
| URI: | https://norma.ncirl.ie/id/eprint/4467 |
Actions (login required)
 |
View Item |