Floresta e Ambiente
http://www.floram.periodikos.com.br/article/doi/10.1590/2179-8087-FLORAM-2025-0056
Floresta e Ambiente
Original Article Forest Management

Neural Networks for Eucalyptus Volume Prediction in a Sensitive Brazilian Tropical Biome Transition Zone

Valeria Cardoso Lopes, Thatiele Pereira Eufrazio, Michelle Pereira de Menezes, Luiz Felipe Tiussi de Mendonça, Brenda Raiane Lopes do Nascimento, Henrique da Silva Fernandes, Everton Alves Rodrigues Pinheiro, Maria Cristina Bueno Coelho

Downloads: 0
Views: 74

Abstract

Accurate stem volume prediction is essential for sustainable management of planted forests in ecologically sensitive regions. This study aimed to evaluate and compare Artificial Neural Networks (ANNs) and classical volume models for predicting stem volume of Eucalyptus spp. in an unmanaged stand within the Cerrado–Caatinga ecotone of the Jalapão region, Brazil. A dataset of 134 felled trees, with volumes obtained by the Smalian method, was used to train three ANN architectures (14–3–1) and fit eight classical models. Classical models produced the most accurate predictions, particularly Näslund (R² = 0.93) and Polynomial (R² = 0.93). Among ANNs, ANN 3 achieved the highest performance (R² = 0.90). Paired t-tests showed ANN 1 was statistically equivalent to Näslund and Polynomial, confirming a small practical performance gap. Both approaches are complementary; model selection should consider data availability, interpretability, and management objectives

Keywords

Forest Modeling; Machine Learning; Allometry; MATOPIBA

Referências

  • Abreu Neto RD, Abreu MC, Soares AAV, Monte MA, Araújo EJGD, Curto RDA et al. Describing the structure and relationship of height and diameter in an old unmanaged Eucalyptus spp. plantation. Floresta e Ambiente 2021; 28(3): e20200087. https://doi.org/10.1590/2179-8087-floram-2020-0087
    » https://doi.org/10.1590/2179-8087-floram-2020-0087
  • Andrade VCLD. Modelos volumétricos de dupla entrada para aplicar em povoamentos florestais brasileiros. Floresta e Ambiente 2017; 24(0). https://doi.org/10.1590/2179-8087.135415
    » https://doi.org/10.1590/2179-8087.135415
  • Antar GM, Sano PT. Angiosperms of dry grasslands and savannahs of Jalapão, the largest conserved Cerrado area in Brazil. Rodriguésia 2019; 70: e04002017. https://doi.org/10.1590/2175-7860201970070
    » https://doi.org/10.1590/2175-7860201970070
  • Azevedo GB, Tomiazzi HV, Azevedo GTDOS, Teodoro LPR, Teodoro PE, De Souza MTP, et al. Multi-volume modeling of Eucalyptus trees using regression and artificial neural networks. PLOS ONE 2020; 15(9): e0238703. https://doi.org/10.1371/journal.pone.0238703
    » https://doi.org/10.1371/journal.pone.0238703
  • Azevedo TL, Mello AA, Ferreira RA, Sanquetta CR, Nakajima NY. Equações hipsométricas e volumétricas para um povoamento de Eucalyptus sp. localizado na FLONA do Ibura, Sergipe. Revista Brasileira de Ciências Agrárias 2011; 6(1): 105-112. https://doi.org/10.5039/agraria.v6i1a861
    » https://doi.org/10.5039/agraria.v6i1a861
  • Bayat M, Ghorbanpour M, Zare R, Jaafari A, Thai Pham B. Application of artificial neural networks for predicting tree survival and mortality in the Hyrcanian forest of Iran. Computers and Electronics in Agriculture 2019; 164: 104929. https://doi.org/10.1016/j.compag.2019.104929
    » https://doi.org/10.1016/j.compag.2019.104929
  • Binoti MLMS, Binoti DHB, Leite HG. Aplicação de redes neurais artificiais para estimação da altura de povoamentos equiâneos de eucalipto. Revista Árvore 2013; 37(4): 639-645. https://doi.org/10.1590/S0100-67622013000400007
    » https://doi.org/10.1590/S0100-67622013000400007
  • Binoti MLMDS, Binoti DHB, Leite HG, Garcia SLR, Ferreira MZ, Rode R, Silva AALD. Redes neurais artificiais para estimação do volume de árvores. Revista Árvore 2014; 38(2): 283–288. https://doi.org/10.1590/S0100-67622014000200008
    » https://doi.org/10.1590/S0100-67622014000200008
  • Costa EA, Hess AF, Finger CAG, Schons CT, Klein DR, Barbosa LO, et al. Enhancing height predictions of Brazilian pine for mixed, uneven-aged forests using artificial neural networks. Forests 2022; 13(8): 1284. https://doi.org/10.3390/f13081284
    » https://doi.org/10.3390/f13081284
  • Czimber K, Szász B, Ács N, Heilig D, Illés G, Mészáros D, et al. Estimation of the Total Carbon Stock of Dudles Forest Based on Satellite Imagery, Airborne Laser Scanning, and Field Surveys. Forests 2025; 16(3): 512. https://doi.org/10.3390/f16030512
    » https://doi.org/10.3390/f16030512
  • Diamantopoulou MJ, Milios E. Modelling total volume of dominant pine trees in reforestations via multivariate analysis and artificial neural network models. Biosystems Engineering 2010; 105(3): 306–315. https://doi.org/10.1016/j.biosystemseng.2009.11.010
    » https://doi.org/10.1016/j.biosystemseng.2009.11.010
  • Dittmar H. Environmental crimes in the brazilian native charcoal production chain. RECIMA21 - Revista Científica Multidisciplinar 2024; 5(3): e535036. https://doi.org/10.47820/recima21.v5i3.5036
    » https://doi.org/10.47820/recima21.v5i3.5036
  • Ercanlı, İ. Deep learning algorithms for addressing overfitting and biological realism in tree taper and volume predictions. Canadian Journal of Forest Research 2024; 54(12): 1500–1518. https://doi.org/10.1139/cjfr-2024-0068
    » https://doi.org/10.1139/cjfr-2024-0068
  • Ferraz Filho AC, Mola-Yudego B, Ribeiro A, Scolforo JRS, Loos RA, Scolforo HF. Height-diameter models for Eucalyptus ssp. plantations in Brazil. CERNE 2018; 24(1): 9–17. https://doi.org/10.1590/01047760201824012466
    » https://doi.org/10.1590/01047760201824012466
  • Foster JR. Statistical power in forest monitoring. Forest Ecology and Management 2001; 151(1–3): 211–222. https://doi.org/10.1016/S0378-1127(01)00591-6
    » https://doi.org/10.1016/S0378-1127(01)00591-6
  • Goodfellow I, Bengio Y, Courville A. Deep learning. MIT Press, 2016.
  • Gorgens EB, Leite HG, Santos HDN, Gleriani JM. Estimação do volume de árvores utilizando redes neurais artificiais. Revista Árvore 2009; 33(6): 1141–1147. https://doi.org/10.1590/S0100-67622009000600016
    » https://doi.org/10.1590/S0100-67622009000600016
  • Harrell J. Regression modeling strategies: with applications to linear models, logistic and ordinal regression, and survival analysis. Springer, 2015. https://doi.org/10.1007/978-3-319-19425-7
    » https://doi.org/10.1007/978-3-319-19425-7
  • Haykin S. Redes neurais: princípios e prática. 2. ed. Porto Alegre: Bookman, 2001. 900p.
  • Hegde R, Clara Manasa PA, Salimath SK. Forest mensuration. In Mandal AK, Nicodemus A. (Eds.), Textbook of Forest Science. Springer Nature Singapore 2025: 361-388. https://doi.org/10.1007/978-981-97-8289-5_16
    » https://doi.org/10.1007/978-981-97-8289-5_16
  • Klink CA, Machado RB. Conservation of the Brazilian Cerrado. Conservation Biology 2005; 19(3): 707–713. https://doi.org/10.1111/j.1523-1739.2005.00702.x
    » https://doi.org/10.1111/j.1523-1739.2005.00702.x
  • Lemos-Junior JM, Silva-Neto CM, Souza KR, Guimarães LE, Oliveira FD, Gonçalves RA, et al. Volumetric models for Eucalyptus grandis × urophylla in a crop-livestock-forest integration (CLFI) system in the Brazilian Cerrado. African Journal of Agricultural Research 2016; 11(15): 1336-1343. https://doi.org/10.5897/AJAR2016.10806
    » https://doi.org/10.5897/AJAR2016.10806
  • Lima RBD, Ferreira RLC, Da Silva JAA, Alves Júnior FT, De Oliveira CP. Estimating tree volume of dry tropical forest in the Brazilian semi-arid region: a comparison between regression and artificial neural networks. Journal of Sustainable Forestry 2021; 40(3): 281–299. https://doi.org/10.1080/10549811.2020.1754241
    » https://doi.org/10.1080/10549811.2020.1754241
  • Messier C, Puettmann KJ. Forests As Complex Adaptive Systems: Implications for forest management and modelling. L’Italia Forestale e Montana 2011; 249–258. https://doi.org/10.4129/ifm.2011.3.11
    » https://doi.org/10.4129/ifm.2011.3.11
  • Miguel EP, Mota FCM, Téo SJ, Nascimento RGM, Leal FA, Pereira RS, et al. Artificial intelligence tools in predicting the volume of trees within a forest stand. African Journal of Agricultural Research 2016; 11(21): 1914-1923. https://doi.org/10.5897/AJAR2016.11015
    » https://doi.org/10.5897/AJAR2016.11015
  • Özçelik R, Diamantopoulou MJ, Brooks JR, Wiant HV. Estimating tree bole volume using artificial neural network models for four species in Turkey. Journal of Environmental Management 2010; 91(3): 742–753. https://doi.org/10.1016/j.jenvman.2009.10.002
    » https://doi.org/10.1016/j.jenvman.2009.10.002
  • Özçelık R, Diamantopoulou MJ, Eker M, Gürlevık N. Artificial Neural Network Models: An alternative approach for reliable aboveground pine tree biomass prediction. Forest Science 2017; 63(3): 291–302. https://doi.org/10.5849/FS-16-006
    » https://doi.org/10.5849/FS-16-006
  • Prechelt L. Early stopping - But when? In Orr GB, Müller KR. (Eds.), Neural networks: tricks of the trade. Springer Berlin Heidelberg 1998; 1524: 55-69. https://doi.org/10.1007/3-540-49430-8_3
    » https://doi.org/10.1007/3-540-49430-8_3
  • Ribeiro RBS, Gama JRV, Melo LO. Seccionamento para cubagem e escolha de equações de volume para a Floresta Nacional do Tapajós. Cerne 2014; 20(4): 605-612. https://doi.org/10.1590/01047760201420041400
    » https://doi.org/10.1590/01047760201420041400
  • Riedmiller M, Braun HA. Direct adaptive method for faster backpropagation learning: the RPROP algorithm. In: Proceedings of the IEEE International Conference on Neural Networks. New York: IEEE; 1993. p. 586-591.
  • Scolforo HF, Castro Neto, F, Scolforo JRS, Burkhart H, McTague JP, Raimundo MR, et al. Modeling dominant height growth of Eucalyptus plantations with parameters conditioned to climatic variations. Forest Ecology and Management 2016; 380: 182–195. https://doi.org/10.1016/j.foreco.2016.09.001
    » https://doi.org/10.1016/j.foreco.2016.09.001
  • Sedlar T, Šefc B, Stojnić S, Jarc A, Perić I, Sinković T. Tvrdoća toplinski modificirane bukovine i grabovine. Šumarski List 2019; 143(9–10): 433–433. https://doi.org/10.31298/sl.143.9-10.4
    » https://doi.org/10.31298/sl.143.9-10.4
  • Siipilehto J, Sarkkola S, Nuutinen Y, Mehtätalo L. Predicting height-diameter relationship in uneven-aged stands in Finland. Forest Ecology and Management 2023; 549: 121486. https://doi.org/10.1016/j.foreco.2023.121486
    » https://doi.org/10.1016/j.foreco.2023.121486
  • Silva MLMD, Binoti DHB, Gleriani JM, Leite HG. Ajuste do modelo de Schumacher e Hall e aplicação de redes neurais artificiais para estimar volume de árvores de eucalipto. Revista Árvore 2009; 33(6): 1133–1139. https://doi.org/10.1590/s0100-67622009000600015
    » https://doi.org/10.1590/s0100-67622009000600015
  • Spera ST, Reatto A, Martins ES, Correia JR, Cunha TJF. Solos areno-quartzosos no Cerrado: problemas, características e limitações ao uso. Planaltina: Embrapa Cerrados; 1999. 48 p.
  • Téo SJ, Machado SDA, Figueiredo Filho A, Tomé M. Equação de volume de aplicabilidade extensiva a diversas classes de idade para Pinus taeda L. na região meio oeste do estado de Santa Catarina. Brazilian Journal of Biometrics 2018, 36(3): 668–685. https://doi.org/10.28951/rbb.v36i3.278
    » https://doi.org/10.28951/rbb.v36i3.278
  • Trigueiro WR, Nabout JC, Tessarolo G. Uncovering the spatial variability of recent deforestation drivers in the Brazilian Cerrado. Journal of Environmental Management 2020; 275: 111243. https://doi.org/10.1016/j.jenvman.2020.111243
    » https://doi.org/10.1016/j.jenvman.2020.111243
  • Thornthwaite CW. An approach toward a rational classification of climate. Geographical Review 1948; 38(1): 55-94.
  • Urbano E, Simplicio VHDS, Cacau FVDP. Comparação de métodos para estimativas volumétricas em diferentes espécies de pinus plantadas no Mato Grosso do Sul. Brazilian Journal of Biological Sciences 2021; 8(19): 33–51. https://doi.org/10.21472/bjbs.v08n19-004
    » https://doi.org/10.21472/bjbs.v08n19-004
  • Valverde JC, Rubilar R, Medina A, Mardones O, Emhart V, Bozo D et al. Taper and individual tree volume equations of Eucalyptus varieties under contrasting irrigation regimes. New Zealand Journal of Forestry Science 2022; 52. https://doi.org/10.33494/nzjfs522022x181x
    » https://doi.org/10.33494/nzjfs522022x181x
  • Vauhkonen J, MehtÄtalo L, Packalén P. Combining tree height samples produced by airborne laser scanning and stand management records to estimate plot volume in Eucalyptus plantations. Canadian Journal of Forest Research 2011; 41(8): 1649–1658. https://doi.org/10.1139/x11-083
    » https://doi.org/10.1139/x11-083
  • Vendruscolo DGS, Drescher R, Souza HS, Siqueira TA. Estimativa da altura de eucalipto por meio de regressão não linear e redes neurais artificiais. Revista Brasileira de Biometria 2015; 33(4): 556-569.
  • Viana RHO, Schaefer CEGR, Campos PV, Neri AV, Corrêa GR, Lolis SDF et al. Soil-vegetation relationship in savanic formations of the Jalapão, Brazil. Anais Da Academia Brasileira de Ciências 2023; 95(3): e20220097. https://doi.org/10.1590/0001-3765202320220097
    » https://doi.org/10.1590/0001-3765202320220097
  • Vieira GC, De Mendonça AR, Da Silva GF, Zanetti SS, Da Silva MM, Dos Santos AR. Prognoses of diameter and height of trees of Eucalyptus using artificial intelligence. Science of The Total Environment 2018; 619–620: 1473–1481. https://doi.org/10.1016/j.scitotenv.2017.11.138
    » https://doi.org/10.1016/j.scitotenv.2017.11.138
  • Vieira RMDSP, Tomasella J, Barbosa AA, Polizel SP, Ometto JPHB, Santos FC et al. Land degradation mapping in the MATOPIBA region (Brazil) using remote sensing data and decision-tree analysis. Science of The Total Environment 2021; 782: 146900. https://doi.org/10.1016/j.scitotenv.2021.146900
    » https://doi.org/10.1016/j.scitotenv.2021.146900
  • Woo H, Acuna M, Cho S, Park J. Assessment techniques in forest biomass along the timber supply chain. Forests 2019; 10(11): 1018. https://doi.org/10.3390/f10111018
    » https://doi.org/10.3390/f10111018
  • Zeller L, Caicoya AT, Pretzsch H. Analyzing the effect of silvicultural management on the trade-off between stand structural heterogeneity and productivity over time. European Journal of Forest Research 2021, 140(3): 615–634. https://doi.org/10.1007/s10342-020-01350-z
    » https://doi.org/10.1007/s10342-020-01350-z
  • Zhao Q, Yu S, Zhao F, Tian L, Zhao Z. Comparison of machine learning algorithms for forest parameter estimations and application for forest quality assessments. Forest Ecology and Management 2019; 434: 224–234. https://doi.org/10.1016/j.foreco.2018.12.019
    » https://doi.org/10.1016/j.foreco.2018.12.019

Submetido em:
15/12/2025

Aceito em:
29/07/2026

6afb403da953951ee3441d3c floram Articles

FLORAM

Share this page
Page Sections