Tools
Tools
Arunkumar, Madhumitha (2024) Enhancing Forest Fire Predictions using Machine Learning and Deep Learning. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (2MB) | Preview |
Abstract
Global climate change is causing more frequent and severe wildfires, posing major risks to both ecosystems and human populations. Traditional prediction techniques find it challenging to accurately predict wildfire dangers due to the dynamic nature of environmental elements. This problem is addressed in this study by utilizing advanced machine learning and deep learning techniques such as ResNet50, LSTM, and RBF Kernel SVR to enhance wildfire forecasting and identification. The research reveals that these models outperform older methods, with ResNet50 achieving 80.16% accuracy in analysing aerial images and LSTM models reaching 99.19% accuracy in detecting smoke in real-time. These results indicate that integrating these advanced techniques leads to more precise forecasts and improved wildfire management strategies, resulting in enhanced prevention and response measures in practice. This study advances current wildfire prediction methods by demonstrating how deep learning models can effectively capture intricate environmental patterns.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Mulwa, Catherine UNSPECIFIED |
| Subjects: | G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 07 Aug 2025 08:56 |
| Last Modified: | 07 Aug 2025 08:56 |
| URI: | https://norma.ncirl.ie/id/eprint/8457 |
Actions (login required)
 |
View Item |