Prediction Model for Forests Fire Spread in M’sila
| dc.contributor.author | Bechere, M’hamed Ayoub | |
| dc.contributor.author | Zamit, Zohir | |
| dc.contributor.author | Mehenni, Tahar: Supervisor | |
| dc.date.accessioned | 2024-07-14T08:45:35Z | |
| dc.date.available | 2024-07-14T08:45:35Z | |
| dc.date.issued | 2023-06 | |
| dc.description.abstract | In this study, three machine-learning algorithms (Linear regression, Polynomial Regression, and Random Forest Regression) were explored for predicting forest fires spread. A comprehensive dataset consisting of environmental and weather factors influencing forest fires was collected and used to train and test the models. Performance metrics such as accuracy, precision and recall score were used to evaluate the models. The results showed that all three algorithms performed well, but the Polynomial Regression Model achieved the highest accuracy. This study emphasizes the effectiveness of machine learning in forest fire spread prediction, particularly the superiority of the Polynomial Regression Model, and highlights the importance of leveraging advanced techniques for mitigating the impact of forest fires and protecting ecosystems | |
| dc.identifier.uri | https://dspace.univ-msila.dz/handle/123456789/43650 | |
| dc.language.iso | en | |
| dc.publisher | UNIVERSITY OF MOHAMED BOUDIAF - MSILA | |
| dc.subject | Linear regression | |
| dc.subject | Polynomial Regression | |
| dc.subject | Random Forest Regression | |
| dc.title | Prediction Model for Forests Fire Spread in M’sila | |
| dc.type | Thesis |