Fig 1.
Location of the three study sites in Southeastern Brazil, which are included in two Brazilian biomes (Cerrado and Atlantic Forest).
Table 1.
Field data summary.
Fig 2.
Diameter versus total height scatterplot.
Diameter at breast height and total height relationships of trees used as data set in Cerrado, semi-deciduous and rainforest.
Table 2.
Taper equations.
Table 3.
Taper models performance.
Table 4.
Modelling techniques performance.
Fig 3.
The root mean squared error (RMSE) distribution of diameter (d) and accumulated volume (Vac) for both training (black line) and validation (grey line) data sets, considering five hundred iterations for Artificial Neural Network (NN), Random Forest (RF) and taper model (TM).
Fig 4.
The bias distribution of diameter (d) and accumulated volume (Vac) for both training (black line) and validation (grey line) data sets, considering five hundred iterations for Artificial Neural Network (NN), Random Forest (RF) and taper model (TM).
Fig 5.
Diameter predictions residuals.
Residuals of diameter predictions (cm) versus tree stem diameters (cm) in the upper plots, as well as residuals of accumulated volume predictions (m³) versus tree stem diameters (cm) in the lower plots. Residuals were calculated using the model with the lowest RMSE along 500 iterations using Artificial Neural Network (NN), Random Forest (RF) and taper model (TM) techniques.
Fig 6.
Measured diameters (black dots) of trees with regular (Xylopia aromatica) and irregular (Bathysa australis) stem taper with the respective predictions fitted by Neural Network (NN), Random Forest (RF) and taper model (TM).