Accuracy of tree height estimation with model extracted from artificial neural network and new linear and nonlinear models

Palavras-chave: hypsometric relationship; forest inventory; eucalyptus.

Resumo

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

Downloads

Não há dados estatísticos.

Referências

Aertsen, W., Kint, V., Orshoven, J. V., Özkan, K., & Muys, B. (2010). Comparison and ranking of different modelling techniques for prediction of site index in Mediterranean mountain forests. Ecological Modelling, 221(8), 1119-1130. DOI: https://doi.org/10.1016/j.ecolmodel.2010.01.007

Ali, K. M., & Pazzani, M. J. (1997). Error reduction through learning multiple descriptions. Machine Learning, 24(3), 173-202. DOI: https://doi.org/10.1007/BF00058611

Bartoszeck, A. C. P. S., Machado, S. A., Figueiredo Filho, A., & Oliveira, E. B. (2004). Dinâmica da relação hipsométrica em função da idade, do sítio e da densidade inicial de povoamentos de bracatinga da Região Metropolitana de Curitiba, PR. Revista Árvore, 28(4), 517-533. DOI: http://doi.org/10.1590/S0100-67622004000400006

Binoti, D. H. B., Binoti, M. L. M. S., & Leite, H. G. (2014). Configuração de redes neurais artificiais para estimação do volume de árvores. Brazilian Journal of Wood Science, 5, 58-67. DOI: https://doi.org/10.12953/2177-6830.v05n01a06

Binoti, D. H. B., Duarte, P. J., Silva, M. L. M., Silva, G. F., Leite, H. G., Mendonça, A. R., ..., Vega, A. E. D. (2018). Estimation of height of eucalyptus trees with neuroevolution of augmenting topologies (NEAT). Revista Árvore, 41(3), 1-8. DOI: https://doi.org/10.1590/1806-90882017000300014

Burnham, K. P., & Anderson, D. R. (2002). Model selection and multimodel inference: a practical information-theoretic approach (2nd ed.). New York, NY: Springer.

Campos, J. C. C., & Leite, H. G. (2017). Mensuração florestal: perguntas e respostas (5. ed.). Viçosa, MG: UFV.

Castaño-Santamaría, J., Crecente-Campo, F., Fernández-Martínez, J. L., Barrio-Anta, M., & Obeso, J. R. (2013). Tree height prediction approaches for uneven-aged beech forests in northwestern Spain. Forest Ecology Management, 307, 63-73. DOI: https://doi.org/10.1016/j.foreco.2013.07.014

Cigizoglu, H. K., & Kisi, Ö. (2006). Methods to improve the neural network performance in suspended sediment estimation. Journal of Hydrology, 317(3-4), 221-238. DOI: https://doi.org/10.1016/j.jhydrol.2005.05.019

Coelho Junior, L. M., Rezende, J. L. P., & Oliveira, A. D. (2013). Concentração das exportações mundiais de produtos florestais. Ciência Florestal, 23(4), 691-701. DOI: https://doi.org/10.5902/1980509812353

Curtis, R. 1(967). Height-diameter and height-diameter-age equations for second-growth Douglas-fir. Forest Science, 13(4), 365-375. DOI: https://doi.org/10.1093/forestscience/13.4.365

Dantas, D., & Oliveira, M. L. R. (2018). Redes neurais artificiais na estimação da altura de árvores. São Paulo, SP: Novas Edições Acadêmicas.

Dantas, D., Calegario, N., Acerbi Junior, F. W., Carvalho, S. P. C., Isaac Junior, M. A., & Melo, E. A. (2020). Multilevel nonlinear mixed-effects model and machine learning for predicting the volume of Eucalyptus spp. trees. Cerne, 26(1), 48-57. DOI: https://doi.org/10.1590/01047760202026012668

Dantas, D., Terra, M. C. N. S., Schorr, L. P. B., & Calegario, N. (2021). Machine learning for carbon stock prediction in a tropical forest in Southeastern Brazil. Bosque, 42(1), 131-140. DOI: http://dx.doi.org/10.4067/S0717-92002021000100131

David, H. C., Arce, J. E., Oliveira, E. B., Netto, S. P., Miranda, R. O. V., & Ebling, A. A. (2017). Economic analysis and revenue optimization in management regimes of Pinus taeda. Revista Ceres, 64(3), 222-231. DOI: https://doi.org/10.1590/0034-737x201764030002

Furnival, G. M. (1961). An index for comparing equations used in constructing volume tables. Forest Science, 7(4), 337-341. DOI: https://doi.org/10.1093/forestscience/7.4.337

Gevrey, M., Dimopoulos, I., & Lek, S. (2003). Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecological Modelling, 160(3), 249-264. DOI: https://doi.org/10.1016/S0304-3800(02)00257-0

Graybill, F. A. (1976). Theory and application of the linear model. Belmont, US: Duxbury Press.

Günther, F., & Fritsch, S. (2010). Neuralnet: Training of neural networks. The R journal, 2(1), 30-38. DOI: https://doi.org/10.32614/RJ-2010-006

Lacerda, T. H. S., Cabacinha, C. D., Araújo Júnior, C. A., Maia, R. D., & Lacerda, K. W. S. (2017). Artificial neural networks for estimating tree volume in the brazilian savanna. Cerne, 23(4), 483-491. DOI: https://doi.org/10.1590/01047760201723042347

Lek, S., Delacoste, M., Baran, P., Dimopoulos, I., Lauga, J., & Aulagnier, S. (1996). Application of neural networks to modelling nonlinear relationships in ecology. Ecological Modelling, 90(1), 39-52. DOI: https://doi.org/10.1016/0304-3800(95)00142-5.

Martins, E. D. R., Binoto, M. L. M. S., Leite, H. G., Binoti, D. H. B., & Dutram G. C. (2016). Configuração de redes neurais artificiais para estimação da altura total de árvores de eucalipto. Revista Brasileira de Ciências Agrárias, 11(1), 117-123. DOI: https://doi.org/10.5039/agraria.v11i1a5354

Mehtätalo, L., Maltamo, M., & Kangas, A. (2006). The use of quantile trees in the prediction of the diameter distribution of a stand. Silva Fennica, 40(3), 501-516. DOI: https://doi.org/10.14214/sf.333

Mendonça, A. R., Carvalho, S. P. C., & Calegario, N. (2015). modelos hipsométricos generalizados mistos na predição da altura de Eucalyptus sp. Cerne, 21(1), 107-115. DOI: http://dx.doi.org/10.1590/01047760201521011191

Nandy, S., Singh, R., Ghosh, S., Watham, T., Kushwaha, S. P. S., Kumar, A. S., & Dadhwal, V. K. (2017). Neural network-based modelling for forest biomass assessment. Carbon Management, 8(4), 305-317. DOI: https://doi.org/10.1080/17583004.2017.1357402

Nogueira, G. S., Marshall, P. L., Leite, H. G., & Campos, J. C. C. (2015). Thinning intensity and pruning impacts on Eucalyptus plantations in Brazil. International Journal of Research, 2015, 1-10. DOI: http://dx.doi.org/10.1155/2015/168390

Özçelik, R., Diamantopoulou, M. J., Crecente-Campo, F., & Eler, U. (2013). Estimating Crimean juniper tree height using nonlinear regression and artificial neural network models. Forest Ecology Management, 306, 52-60. DOI: https://doi.org/10.1016/j.foreco.2013.06.009

Preacher, K. J., Curran, P. J., & Bauer, D. J. (2006). Computational tools for probing interactions in multiple linear regression, multilevel modeling, and latent curve analysis. Journal of Educational and Behavioral Statistics, 31(4), 437-448. DOI: https://doi.org/10.3102/10769986031004437

R Development Core Team. (2017). R: a language and environment for statistical computing. Vienna, AT: R Foundation for Statistical Computing.

Reis, L. P, Souza, A. L., Reis, P. C. M., Mazzei, L., Soares, C. P. B., Torres, C. M. M. E., … Leite, H. G. (2018). Estimation of mortality and survival of individual trees after harvesting wood using artificial neural networks in the amazon rain forest. Ecological Engineering, 112, 140-147. DOI: https://doi.org/10.1016/j.ecoleng.2017.12.014

Retslaff, F. A. S., Figueiredo Filho, A., Dias, A. N., Bernett, L. G., & Figura, M. A. (2015). Curvas de sítio e relações hipsométricas para Eucalyptus grandis na região dos Campos Gerais, Paraná. Cerne, 21(2), 219-225. DOI: http://dx.doi.org/10.1590/01047760201521021349

Sakamoto, Y., Ishiguro, M., & Kitagawa, G. (1986). Akaike information criterion statistics. Dordrecht, NT: D. Reidel.

Sena, A. L. M., Silva Neto, A. J., Oliveira, G. M. V., & Calegario, N. (2015). Linear and nonlinear models with use of covariates for hypsometric relationship of two tropical pine species. Ciência Florestal, 25(4), 969-980. DOI: http://dx.doi.org/10.5902/1980509820651

Siipilehto, J. (2000). A comparison of two parameter prediction methods for stand structure in Finland. Silva Fennica, 34(4), 331-349. DOI: https://doi.org/10.14214/sf.617

Silva, G. F., Xavier, A. C., Rodrigues, F. L., & Peternelli, L. A. (2007). Análise da influência de diferentes tamanhos e composições de amostras no ajuste de uma relação hipsométrica para Eucalyptus grandis. Revista Árvore, 31(4), 685-694. DOI: http://doi.org/10.1590/S0100-67622007000400013

Silva, J. P. M., Cabacinha, C. D., Assis, A. L., Monteiro, T. C., Araújo Júnior, C. A, & Maia, R. D. (2018). Redes neurais artificiais para estimar a densidade básica de madeiras do cerrado. Pesquisa Florestal Brasileira, 38, 1-10. DOI: https://doi.org/10.4336/2018.pfb.38e201801656

Silva Junior, E. M., Maia, R. D., & Cabacinha, C. D. (2018). Bee-inspired RBF network for volume estimation of individual trees. Computers and Electronics in Agriculture, 152, 401-408. DOI: https://doi.org/10.1016/j.compag.2018.07.036

Soares, F. A. A. M. N., Flôres, E. L., Cabacinha, C. D., Carrijo, G. A., & Veiga, A. C. P. (2011). Recursive diameter prediction and volume calculation of eucalyptus trees using Multilayer Perceptron Networks. Computers and Electronics in Agriculture, 78(1), 19-27. DOI: https://doi.org/10.1016/j.compag.2011.05.008

Téo, S. J., Machado, S. A., Figueiredo Filho, A., & Tomé, M., (2017). General height-diameter equation with biological attributes for Pinus taeda L. stands. Cerne, 23(4), 403-411. DOI: http://doi.org/10.1590/01047760201723042414

Valença, M. (2010). Fundamentos das redes neurais: exemplos em Java (2. ed.). Olinda, PE: Livro Rápido.

Vendruscolo, D. G. S., Drescher, R., Souza, H. S., Moura, J. P. V. M., Mamoré, F. M. D., & Siqueira, T. A. S. (2015). Estimativa da altura de eucalipto por meio de regressão não linear e redes neurais artificiais. Revista Brasileira de Biometria, 33(4), 556-569. DOI: http://doi.org/10.13140/RG.2.1.1742.5684

Vieira, G. C. V., Mendonça, A. R., Silva, G. F., Zanetti, S. S., Silva, M. M., & Santos, A. R. (2018). Prognoses of diameter and height of trees of eucalyptus using artificial intelligence. Science of the Total Environment, 619-620, 1473-1481. DOI: https://doi.org/10.1016/j.scitotenv.2017.11.138

Publicado
2023-12-11
Como Citar
Dantas, D., Pinto, L. O. R., Lacerda, T. H. S., Cordeiro, N. G., & Calegario, N. (2023). Accuracy of tree height estimation with model extracted from artificial neural network and new linear and nonlinear models. Acta Scientiarum. Agronomy, 46(1), e63286. https://doi.org/10.4025/actasciagron.v46i1.63286
Seção
Biometria, Modelagem e Estatística

 

2.0
2019CiteScore
 
 
60th percentile
Powered by  Scopus

 

2.0
2019CiteScore
 
 
60th percentile
Powered by  Scopus