Individual Tree Basal Area Increment Models for Brazilian Pine (<i>Araucaria angustifolia</i>) Using Artificial Neural Networks
This research aimed to develop statistical models to predict basal area increment (BAI) for <i>Araucaria angustifolia</i> using Artificial Neural Networks (ANNs). Tree species were measured for their biometric variables and identified at the species level. The data were subdivided into t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/13/7/1108 |
| _version_ | 1797433594956742656 |
|---|---|
| author | Lorena Oliveira Barbosa Emanuel Arnoni Costa Cristine Tagliapietra Schons César Augusto Guimarães Finger Veraldo Liesenberg Polyanna da Conceição Bispo |
| author_facet | Lorena Oliveira Barbosa Emanuel Arnoni Costa Cristine Tagliapietra Schons César Augusto Guimarães Finger Veraldo Liesenberg Polyanna da Conceição Bispo |
| author_sort | Lorena Oliveira Barbosa |
| collection | DOAJ |
| description | This research aimed to develop statistical models to predict basal area increment (BAI) for <i>Araucaria angustifolia</i> using Artificial Neural Networks (ANNs). Tree species were measured for their biometric variables and identified at the species level. The data were subdivided into three groups: (1) intraspecific competition with <i>A. angustifolia</i>; (2) the first group of species that causes interspecific competition with <i>A. angustifolia</i>; and (3) the second group of species that causes interspecific competition with <i>A. angustifolia</i>. We calculated both the dependent and independent distance and the described competition indices, considering the impact of group stratification. Multi-layer Perceptron (MLP) ANN was structured for modeling. The main results were that: (i) the input variables size and competition were the most significant, allowing us to explain up to 77% of the <i>A. angustifolia</i> BAI variations; (ii) the spatialization of the competing trees contributed significantly to the representation of the competitive status; (iii) the separate variables for each competition group improved the performance of the models; and (iv) besides the intraspecific competition, the interspecific competition also proved to be important to consider. The ANN developed showed precision and generalization, suggesting it could describe the increment of a species common in native forests in Southern Brazil and with potential for upcoming forest management initiatives. |
| first_indexed | 2024-03-09T10:19:14Z |
| format | Article |
| id | doaj.art-603f7edcbad74973b46ea2a40457bd26 |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-09T10:19:14Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-603f7edcbad74973b46ea2a40457bd262023-12-01T22:09:49ZengMDPI AGForests1999-49072022-07-01137110810.3390/f13071108Individual Tree Basal Area Increment Models for Brazilian Pine (<i>Araucaria angustifolia</i>) Using Artificial Neural NetworksLorena Oliveira Barbosa0Emanuel Arnoni Costa1Cristine Tagliapietra Schons2César Augusto Guimarães Finger3Veraldo Liesenberg4Polyanna da Conceição Bispo5Graduate Program in Forest Engineering, Federal University of Lavras (UFLA), Lavras 37200-900, MG, BrazilGraduate Program in Forest Engineering, Federal University of Santa Maria (UFSM), Santa Maria 97105-900, RS, BrazilGraduate Program in Forest Engineering, Federal University of Santa Maria (UFSM), Santa Maria 97105-900, RS, BrazilGraduate Program in Forest Engineering, Federal University of Santa Maria (UFSM), Santa Maria 97105-900, RS, BrazilGraduate Program in Forest Engineering, Santa Catarina State University (UDESC), Lages 88520-000, SC, BrazilDepartment of Geography, School of Environment, Education and Development, University of Manchester, Oxford Road, Manchester M13 9PL, UKThis research aimed to develop statistical models to predict basal area increment (BAI) for <i>Araucaria angustifolia</i> using Artificial Neural Networks (ANNs). Tree species were measured for their biometric variables and identified at the species level. The data were subdivided into three groups: (1) intraspecific competition with <i>A. angustifolia</i>; (2) the first group of species that causes interspecific competition with <i>A. angustifolia</i>; and (3) the second group of species that causes interspecific competition with <i>A. angustifolia</i>. We calculated both the dependent and independent distance and the described competition indices, considering the impact of group stratification. Multi-layer Perceptron (MLP) ANN was structured for modeling. The main results were that: (i) the input variables size and competition were the most significant, allowing us to explain up to 77% of the <i>A. angustifolia</i> BAI variations; (ii) the spatialization of the competing trees contributed significantly to the representation of the competitive status; (iii) the separate variables for each competition group improved the performance of the models; and (iv) besides the intraspecific competition, the interspecific competition also proved to be important to consider. The ANN developed showed precision and generalization, suggesting it could describe the increment of a species common in native forests in Southern Brazil and with potential for upcoming forest management initiatives.https://www.mdpi.com/1999-4907/13/7/1108incrementindividual tree modelingdendrometric and morphometric variablescompetition indicesmixed forest |
| spellingShingle | Lorena Oliveira Barbosa Emanuel Arnoni Costa Cristine Tagliapietra Schons César Augusto Guimarães Finger Veraldo Liesenberg Polyanna da Conceição Bispo Individual Tree Basal Area Increment Models for Brazilian Pine (<i>Araucaria angustifolia</i>) Using Artificial Neural Networks Forests increment individual tree modeling dendrometric and morphometric variables competition indices mixed forest |
| title | Individual Tree Basal Area Increment Models for Brazilian Pine (<i>Araucaria angustifolia</i>) Using Artificial Neural Networks |
| title_full | Individual Tree Basal Area Increment Models for Brazilian Pine (<i>Araucaria angustifolia</i>) Using Artificial Neural Networks |
| title_fullStr | Individual Tree Basal Area Increment Models for Brazilian Pine (<i>Araucaria angustifolia</i>) Using Artificial Neural Networks |
| title_full_unstemmed | Individual Tree Basal Area Increment Models for Brazilian Pine (<i>Araucaria angustifolia</i>) Using Artificial Neural Networks |
| title_short | Individual Tree Basal Area Increment Models for Brazilian Pine (<i>Araucaria angustifolia</i>) Using Artificial Neural Networks |
| title_sort | individual tree basal area increment models for brazilian pine i araucaria angustifolia i using artificial neural networks |
| topic | increment individual tree modeling dendrometric and morphometric variables competition indices mixed forest |
| url | https://www.mdpi.com/1999-4907/13/7/1108 |
| work_keys_str_mv | AT lorenaoliveirabarbosa individualtreebasalareaincrementmodelsforbrazilianpineiaraucariaangustifoliaiusingartificialneuralnetworks AT emanuelarnonicosta individualtreebasalareaincrementmodelsforbrazilianpineiaraucariaangustifoliaiusingartificialneuralnetworks AT cristinetagliapietraschons individualtreebasalareaincrementmodelsforbrazilianpineiaraucariaangustifoliaiusingartificialneuralnetworks AT cesaraugustoguimaraesfinger individualtreebasalareaincrementmodelsforbrazilianpineiaraucariaangustifoliaiusingartificialneuralnetworks AT veraldoliesenberg individualtreebasalareaincrementmodelsforbrazilianpineiaraucariaangustifoliaiusingartificialneuralnetworks AT polyannadaconceicaobispo individualtreebasalareaincrementmodelsforbrazilianpineiaraucariaangustifoliaiusingartificialneuralnetworks |