Table 5 Above-ground biomass (AGB, t∙ha−1) root mean square prediction error (RMSPE) using different predictor variable dataset combinations and models, ordered by mean RMSPE and mean RMSPE%
From: Model-based estimation of above-ground biomass in the miombo ecoregion of Zambia
Model | \( {\hat{CC}}_{\mathrm{VERT}} \) | \( {\hat{CC}}_{\mathrm{HEMI}} \) | Landsat | Env/Dist | Landsat + Env/Dist | \( {\hat{CC}}_{\mathrm{HEMI}} \) + Landsat | \( {\hat{CC}}_{\mathrm{HEMI}} \) + Env/Dist | \( {\hat{CC}}_{\mathrm{HEMI}} \) + Env/Dist + Landsat |
|---|---|---|---|---|---|---|---|---|
GAM (1) | 50.1 | 44.3 | 48.8 | 41.5 | 40.7 | 43.4 | 37.9 | 35.1 |
Sigmoidal (2) | 49.8 | 45.2 | 47.8 | 47.0 | 45.6 | 44.2 | 39.8 | 37.5 |
Exponential (3) | 72.1 | 46.3 | 45.9 | 46.6 | 44.3 | 42.8 | 40.5 | 39.4 |
Mean RMSPE | 57.3 | 45.3 | 47.5 | 45 | 43.5 | 43.5 | 39.4 | 37.3 |
Mean RMSPE% | 89Â % | 71Â % | 74Â % | 70Â % | 68Â % | 68Â % | 61Â % | 58Â % |