Accuracy of tree height estimation with model extracted from artificial neural network and new linear and nonlinear models
Variable height is commonly used as an input attribute to estimate other variables. Thus, to ensure less susceptibility to errors, it is necessary to obtain the variable height correctly. In addition to DBH, hypsometric relationships are influenced by several factors, such as site, age, genetic var...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Eduem (Editora da Universidade Estadual de Maringá)
2023-12-01
|
| Series: | Acta Scientiarum: Agronomy |
| Subjects: | |
| Online Access: | https://periodicos.uem.br/ojs/index.php/ActaSciAgron/article/view/63286 |
| _version_ | 1797393300584398848 |
|---|---|
| author | Daniel Dantas Luiz Otávio Rodrigues Pinto Talles Hudson Souza Lacerda Natielle Gomes Cordeiro Natalino Calegario |
| author_facet | Daniel Dantas Luiz Otávio Rodrigues Pinto Talles Hudson Souza Lacerda Natielle Gomes Cordeiro Natalino Calegario |
| author_sort | Daniel Dantas |
| collection | DOAJ |
| description |
Variable height is commonly used as an input attribute to estimate other variables. Thus, to ensure less susceptibility to errors, it is necessary to obtain the variable height correctly. In addition to DBH, hypsometric relationships are influenced by several factors, such as site, age, genetic variation, and silvicultural practices. The inclusion of these factors in hypsometric models can lead to a gain in the quality of the estimates and in the biological realism. The objective of this study was to propose and evaluate the performance of a model extracted from artificial neural network training and of new models to estimate the total height of eucalyptus trees. The data used in this study originated from temporary forest inventories conducted in eucalyptus stands in Minas Gerais, Brazil. A multilayer perceptron artificial neural network was trained, and a nonlinear equation was extracted from the best-performing network to predict the total heights of trees. New linear and nonlinear hypsometric models were constructed and fit considering variables related to individual trees (DBH) and stands (plot basal area, age and site index). The new hypsometric models proposed in this study showed satisfactory performance and are effective for estimating the total heights of eucalyptus trees, particularly the model extracted from the artificial neural network and the nonlinear model
|
| first_indexed | 2024-03-09T00:01:27Z |
| format | Article |
| id | doaj.art-f237b9e4c6194a6089173f52acf5126f |
| institution | Directory Open Access Journal |
| issn | 1679-9275 1807-8621 |
| language | English |
| last_indexed | 2024-03-09T00:01:27Z |
| publishDate | 2023-12-01 |
| publisher | Eduem (Editora da Universidade Estadual de Maringá) |
| record_format | Article |
| series | Acta Scientiarum: Agronomy |
| spelling | doaj.art-f237b9e4c6194a6089173f52acf5126f2023-12-12T17:55:24ZengEduem (Editora da Universidade Estadual de Maringá)Acta Scientiarum: Agronomy1679-92751807-86212023-12-0146110.4025/actasciagron.v46i1.63286Accuracy of tree height estimation with model extracted from artificial neural network and new linear and nonlinear modelsDaniel Dantas0Luiz Otávio Rodrigues Pinto1Talles Hudson Souza Lacerda2Natielle Gomes Cordeiro3Natalino Calegario4Universidade Federal de LavrasUniversidade Federal de LavrasUniversidade Federal de LavrasUniversidade Federal de LavrasUniversidade Federal de Lavras Variable height is commonly used as an input attribute to estimate other variables. Thus, to ensure less susceptibility to errors, it is necessary to obtain the variable height correctly. In addition to DBH, hypsometric relationships are influenced by several factors, such as site, age, genetic variation, and silvicultural practices. The inclusion of these factors in hypsometric models can lead to a gain in the quality of the estimates and in the biological realism. The objective of this study was to propose and evaluate the performance of a model extracted from artificial neural network training and of new models to estimate the total height of eucalyptus trees. The data used in this study originated from temporary forest inventories conducted in eucalyptus stands in Minas Gerais, Brazil. A multilayer perceptron artificial neural network was trained, and a nonlinear equation was extracted from the best-performing network to predict the total heights of trees. New linear and nonlinear hypsometric models were constructed and fit considering variables related to individual trees (DBH) and stands (plot basal area, age and site index). The new hypsometric models proposed in this study showed satisfactory performance and are effective for estimating the total heights of eucalyptus trees, particularly the model extracted from the artificial neural network and the nonlinear model https://periodicos.uem.br/ojs/index.php/ActaSciAgron/article/view/63286hypsometric relationship; forest inventory; eucalyptus. |
| spellingShingle | Daniel Dantas Luiz Otávio Rodrigues Pinto Talles Hudson Souza Lacerda Natielle Gomes Cordeiro Natalino Calegario Accuracy of tree height estimation with model extracted from artificial neural network and new linear and nonlinear models Acta Scientiarum: Agronomy hypsometric relationship; forest inventory; eucalyptus. |
| title | Accuracy of tree height estimation with model extracted from artificial neural network and new linear and nonlinear models |
| title_full | Accuracy of tree height estimation with model extracted from artificial neural network and new linear and nonlinear models |
| title_fullStr | Accuracy of tree height estimation with model extracted from artificial neural network and new linear and nonlinear models |
| title_full_unstemmed | Accuracy of tree height estimation with model extracted from artificial neural network and new linear and nonlinear models |
| title_short | Accuracy of tree height estimation with model extracted from artificial neural network and new linear and nonlinear models |
| title_sort | accuracy of tree height estimation with model extracted from artificial neural network and new linear and nonlinear models |
| topic | hypsometric relationship; forest inventory; eucalyptus. |
| url | https://periodicos.uem.br/ojs/index.php/ActaSciAgron/article/view/63286 |
| work_keys_str_mv | AT danieldantas accuracyoftreeheightestimationwithmodelextractedfromartificialneuralnetworkandnewlinearandnonlinearmodels AT luizotaviorodriguespinto accuracyoftreeheightestimationwithmodelextractedfromartificialneuralnetworkandnewlinearandnonlinearmodels AT talleshudsonsouzalacerda accuracyoftreeheightestimationwithmodelextractedfromartificialneuralnetworkandnewlinearandnonlinearmodels AT natiellegomescordeiro accuracyoftreeheightestimationwithmodelextractedfromartificialneuralnetworkandnewlinearandnonlinearmodels AT natalinocalegario accuracyoftreeheightestimationwithmodelextractedfromartificialneuralnetworkandnewlinearandnonlinearmodels |