Research Article
Wildfire Susceptibility Mapping Using Five Boosting Machine Learning Algorithms: The Case Study of the Mediterranean Region of Turkey
Table 4
Area and percentage distribution of the susceptibility classes of all the models.
| Models | Distribution | Susceptibility classes | Very low | Low | Medium | High | Very high |
| XGBoost | Area (km2) | 26349 | 27655 | 23716 | 17175 | 9258 | Percentage (%) | 25 | 27 | 23 | 16 | 9 |
| CatBoost | Area (km2) | 67201 | 17663 | 8170 | 5138 | 5981 | Percentage (%) | 65 | 17 | 8 | 5 | 6 |
| GBM | Area (km2) | 41579 | 20842 | 18171 | 13533 | 10029 | Percentage (%) | 40 | 20 | 17 | 13 | 10 |
| AdaBoost | Area (km2) | 4369 | 2633 | 16425 | 41285 | 39441 | Percentage (%) | 4 | 3 | 16 | 40 | 38 |
| LightGBM | Area (km2) | 73658 | 13388 | 6759 | 4321 | 6028 | Percentage (%) | 71 | 13 | 6 | 4 | 6 |
|
|