Estimation of total tree height in plantations of different species through artificial neural networks
The objective of this study was to analyze the ability of an artificial neural network (ANN) to estimate the total height of two tree species in different growing conditions. For comparison purposes, it was also adjusted Campos hypsometric model, applied by stratum as genus, species, rotation, spacing and age classes. The evaluation of artificial neural networks and Campos model was based on the correlation coefficient between the observed and estimated heights, the square root of the mean square percentage error (RMSE) and graphical analysis. The results of this study showed that trees height of different species, in different growing conditions and locations can be estimated using a single neural network with the same efficiency and accuracy usually obtained with regression equations.
| Main Authors: | , , , , |
|---|---|
| Format: | Digital revista |
| Language: | por |
| Published: |
Embrapa Florestas
2016
|
| Online Access: | https://pfb.cnpf.embrapa.br/pfb/index.php/pfb/article/view/1166 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The objective of this study was to analyze the ability of an artificial neural network (ANN) to estimate the total height of two tree species in different growing conditions. For comparison purposes, it was also adjusted Campos hypsometric model, applied by stratum as genus, species, rotation, spacing and age classes. The evaluation of artificial neural networks and Campos model was based on the correlation coefficient between the observed and estimated heights, the square root of the mean square percentage error (RMSE) and graphical analysis. The results of this study showed that trees height of different species, in different growing conditions and locations can be estimated using a single neural network with the same efficiency and accuracy usually obtained with regression equations. |
|---|