Table 8 Comparison of accuracy metrics for various biomass estimation models in shrubland and broadleaf forest. The Stacking model consistently demonstrates superior performance in terms of \({R}^2\), RMSE, and MAE, highlighting its effectiveness in biomass estimation compared with individual models (best results are highlighted in bold, and the second-best results are italics).
Vegetation type | Model | \(R^2\) | RMSE (Mg/ha) | MAE (Mg/ha) |
|---|---|---|---|---|
| Â | GBR | 0.23 | 30.42 | 22.25 |
| Â | RF | 0.29 | 29.22 | 21.74 |
| Â | AGBoost | 0.20 | 31.02 | 25.26 |
Shrubland | SVR | 0.22 | 30.57 | 21.80 |
| Â | MLP | 0.26 | 29.78 | 22.23 |
| Â | KNN | 0.02 | 34.30 | 25.23 |
| Â | Stacking model | 0.30 | 29.14 | 23.34 |
| Â | GBR | 0.38 | 88.54 | 67.62 |
| Â | RF | 0.41 | 86.23 | 65.18 |
| Â | AGBoost | 0.27 | 96.03 | 77.02 |
Broadleaf forest | SVR | 0.15 | 104.05 | 78.93 |
| Â | MLP | 0.15 | 104.08 | 83.47 |
| Â | KNN | 0.08 | 107.54 | 82.14 |
| Â | Stacking model | 0.43 | 85.22 | 65.27 |
