Table 1 Calculated importance of variables in Random Forest models for predicting post-fire recovery in three aridity areas (pooled and separately) in the western Mediterranean basin according to the model improvement ratio (MIR). Means and standard deviation (SD) of the percent root mean square error and R squared of each model are also indicated
All | Semi-arid | Sub-humid | Humid | |
|---|---|---|---|---|
Variable importance (MIR) | ||||
Drought duration (SPEI) | 1.00 | 1.00 | 1.00 | 1.00 |
Fire severity (RdNBR) | 0.54 | 0.64 | 0.78 | 0.54 |
Northness index | 0.25 | 0.31 | 0.46 | 0.41 |
Topographic wetness index | 0.18 | 0.26 | 0.31 | 0.23 |
% Root mean square error (SD) | 3.76 (± 0.34) | 3.33 (± 0.35) | 3.68 (± 0.35) | 3.09 (± 0.25) |
Mean R squared (SD) | 0.18 (± 0.05) | 0.24 (± 0.06) | 0.09 (± 0.04) | 0.49 (± 0.06) |