Abstract
This study aimed to model the height of trees and volumetric production of eucalypts trees on the agrosilvopastoral systems (AGP) of Zona da Mata Mineira region, Brazil, using artificial neural network (ANN) and regression models to determine the best alternative. The data was obtained from five systems with different spatial arrangements (8 × 3 m, 10 × 3 m, 11 × 3 m, 12 × 3 m, 12 × 2 m, and 12 × 4 m), ages (5.5, 6.5 and 8 years) and genotypes, of which 122 sample trees were scaled. Hypsometric and volumetric models were adjusted considering no stratification or stratification by the AGP, spatial arrangement, and genotype. A multilayer perceptron ANN was trained using resilient propagation and skip layer training algorithms. The stratification variables used in the regression were used in the ANN as categorical variables. To estimate height of trees were used as continuous variables: diameter at breast height (dbh), dominant height (Dh), and age. To estimate volume were used as continuous variables: dbh, total height, and age. The AGPs’s mean annual increment at 5.5, 6.5 and 8 years of age ranged from 21 to 62 m3 ha−1 year−1. ANN was proven to be an efficient methodology for hypsometric and volumetric estimates of eucalypt in AGP in the study region.
Similar content being viewed by others
References
Alcorn PJ, Pyttel P, Bauhus J et al (2007) Effects of initial planting density on branch development in 4-year-old plantation grown Eucalypt pilularis and Eucalyptus cloeziana trees. For Ecol Manag 252:41–51
Araújo ACSC, Binoti MLMS, Leite HG, Binoti DHB et al (2016) Artificial Neural Networks with Skip Layer Connections to estimate the volume of forest formations in the state of Minas Gerais. Aust J Basic Appl Sci 10:71–79
Assmann E (1970) The principles of forest yield study. Pergamon Press, Oxford p, p 506
Avery TE, Burkhart HE (2002) Forest measurements, 5th edn. Waveland Press Inc, Long Grove, IL
Barbosa RA, dos Reis GG, Reis MGF et al (2019) Growth, yield and economic analysis of an eucalypt-soybean consortium: effect of the distance between trees within the row. Revista Árvore. https://doi.org/10.1590/1806-90882019000200002
Bell S, Zitnick CL, Bala K, Girshick R (2016) Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, Las Vegas, NV, USA, pp 2874–2883
Binoti MLMS (2012) Emprego de redes neurais artificiais em mensuração e manejo florestal. Universidade Federal de Viçosa, Viçosa
Binoti DHB, Binoti MLMDS, Leite HG et al (2012) Descrição da distribuição diamétrica de sistemas agrossilvipastoris utilizando as funções Weibull e Hiperbólica. Revista Árvore 36:349–356
Binoti MLMS, Binoti DHB, Leite HG (2013) Aplicação de redes neurais artificiais para estimação da altura de povoamentos equiâneos de eucalipto. Revista Árvore 37:639–645
Binoti MLMS, Binoti DHB, Leite HG et al (2014) Redes neurais artificiais para estimação do volume de árvores. Rev Árvore 38:283–288. https://doi.org/10.1590/S0100-67622014000200008
Binoti MLMS, Leite HG, Binoti DHB et al (2015) Prognose em nível de povoamento de clones de eucalipto empregando redes neurais artificiais. Cerne 21:97–105. https://doi.org/10.1590/01047760201521011153
Binoti DHB, Duarte PJ, Silva MLM da et al (2017) Estimation of height of Eucalyptus trees with neuroevolution of Augmenting Topologies (NEAT). Revista Árvore 41
Bishaw Z, Struik PC, Van Gastel AJG (2013) Farmer’s seed sources and seed quality: 2. Seed health. Int J Plant Prod 7:637–657
Bisseleua HBD, Fotio D, Yede ADM, Vidal S (2013) Shade tree diversity, cocoa pest damage, yield compensating inputs and farmers’ net returns in West Africa. PLoS ONE 8:e56115
Braga AP, Carvalho APLF, Ludemir TB (2000) Redes Neurais Artificiais: Teoria e Aplicações. LTC - Livros Técnicos e Científicos Editora S.A
Brüning LZ, Krieger M, Meneses-Pelayo E et al (2018) Land-use heterogeneity by small-scale agriculture promotes amphibian diversity in montane agroforestry systems of northeast Colombia. Agr Ecosyst Environ 264:15–23
Burkhart HE, Tomé M (2012) Modeling forest trees and stands. Springer, Berlin
Campos JCC, Leite HG (2013) Mensuração Florestal: Perguntas E Respostas. Atual. E Ampl. Viçosa, Mg: Editora Ufv
Campos JCC, Ribeiro J, Paula Neto F (1984) Inventário florestal nacional, reflorestamento: Minas Gerais. IBDF, Brasília
Campos BPF, da Silva GF, Binoti DHB et al (2016) Predição da altura total de árvores em plantios de diferentes espécies por meio de redes neurais artificiais. Pesquisa Florestal Brasileira 36:375–385
Cardoso IM, Guijt I, Franco FS et al (2001) Continual learning for agroforestry system design: university, NGO and farmer partnership in Minas Gerais, Brazil. Agric Syst 69:235–257
Che S, Tan X, Xiang C et al (2018) Stand basal area modelling for Chinese fir plantations using an artificial neural network model. J For Res 30:1641–1649
Clutter JL, Fortson JC, Pienaar LV et al (1983) Timber management: a quantitative approach. Wiley, London
Cordeiro AAC, Coelho SD, Ramos NC, Meira-Neto JAA (2018) Agroforestry systems reduce invasive species richness and diversity in the surroundings of protected areas. Agrofor Syst 92:1495–1505
da Silva R, Hakamada R, Bazani J et al (2016) Fertilization response, light use, and growth efficiency in eucalyptus plantations across soil and climate gradients in Brazil. Forests 7:117. https://doi.org/10.3390/f7060117
de Freitas ECS, de Oliveira Neto SN, da Fonseca DM et al (2013) Deposição de serapilheira e de nutrientes no solo em sistema agrossilvipastoril com eucalipto e acácia. Revista Árvore 37:409–417
Diamantopoulou MJ (2012) Assessing a reliable modeling approach of features of trees through neural network models for sustainable forests. Sustain Comput Inform Syst 2:190–197
Diamantopoulou MJ, Milios E (2010) Modelling total volume of dominant pine trees in reforestations via multivariate analysis and artificial neural network models. Biosyst Eng 105:306–315
Diamantopoulou MJ, Milios E, Doganos D, Bistinas I (2009) Artificial neural network modeling for reforestation design through the dominant trees bole-volume estimation. Nat Resour Model 22:511–543
Diamantopoulou MJ, Özçelik R, Crecente-Campo F et al (2015) Estimation of Weibull function parameters for modelling tree diameter distribution using least squares and artificial neural networks methods. Biosyst Eng 133:33–45. https://doi.org/10.1016/j.biosystemseng.2015.02.013
Do Vale R, Couto L, da Silva M et al (2004) Análise da viabilidade econômica de um sistema silvipastoril com eucalipto para a Zona da Mata de Minas Gerais. Agrossilvicultura 1:2
Dolácio CJF, Oliveira RS, Nakajima NY et al (2020) Integration of principal component analysis and artificial neural network to modeling productive capacity of eucalypt stands from biophysical attributes. For Ecol Manag 460:117862
Dube F, Couto L, da Silva M et al (2002) A simulation model for evaluating technical and economic aspects of an industrial eucalyptus-based agroforestry system in Minas Gerais, Brazil. Agrofor Syst 55:73–80
Ferreira AD, Serra AP, Laura VA et al (2017) Influência de arranjos espaciais sobre as características silviculturais de três clones de eucalipto em sistemas de integração lavoura-pecuária-floresta
Ferreiro-Domínguez N, Rigueiro-Rodríguez A, Mosquera-Losada MR (2011) Response to sewage sludge fertilisation in a Quercus rubra L. silvopastoral system: soil, plant biodiversity and tree and pasture production. Agric Ecosyst Environ 141:49–57
Fontan IC, Reis GG, Reis MG et al (2011) Growth of pruned eucalypt clone in an agroforestry system in southeastern Brazil. Agrofor Syst 83:121
Görgens EB, Leite HG, Santos HN et al (2009) Estimação do volume de árvores utilizando redes neurais artificiais. Revista Árvore 33:1141–1147
Graybill FA (1976) Theory and application of the linear model, vol 183. Duxbury press, North Scituate, MA
Gujarati DN, Porter DC (2011) Econometria Básica-5. Amgh Editora
Haykin S (2001) Redes neurais: princípios e prática, 2nd edn. Bookman, Porto Alegre
Haykin S (2009) Neural networks and learning machines, 3rd edn. Prentice Hall, New Jersey
Hott MC, De Carvalho LMT, Antunes MAH et al (2016) Vegetative growth of grasslands based on hyper-temporal NDVI data from the Modis sensor. Pesqui Agropecu Bras 51:858–868. https://doi.org/10.1590/S0100-204X2016000700009
Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks, pp 4700–4708
IBÁ (2019) Relatório Anual. O setor Brasileiro de àrvores. https://iba.org/datafiles/publicacoes/relatorios/iba-relatorioanual2019.pdf
Kay S, Graves A, Palma J, Moreno G et al (2019) Agroforestry is paying off—economic evaluation of ecosystem services in European landscapes with and without agroforestry systems. Ecosyst Serv 36:10. https://doi.org/10.1016/j.ecoser.2019.100896
Khan GS, Chaudhry AK (2007) Effect of spacing and plant density on the growth of poplar (Populus deltoides) trees under agro-forestry system
Kim TJ, Bullock BP, Stape JL (2015) Effects of silvicultural treatments on temporal variations of spatial autocorrelation in Eucalyptus plantations in Brazil. For Ecol Manag 358:90–97. https://doi.org/10.1016/j.foreco.2015.09.004
Kruschewsky GC, Macedo RLG, Venturin N, de Oliveira TK (2007) Arranjo estrutural e dinâmica de crescimento de Eucalyptus spp., em sistema agrossilvipastoril no cerrado. Cerne 13:360–367
Lacerda F, Miranda I, Kato OR et al (2013) Weed dynamics during the change of a degraded pasture to agroforestry system. Agrofor Syst 87:909–916
Lacerda THS, Cabacinha CD, Araújo Júnior CA et al (2017) Artificial neural networks for estimating tree volume in the Brazilian savanna. Cerne 23:483–491
Lana ÂMQ, Lana RMQ, Lemes EM et al (2018) Influence of native or exotic trees on soil fertility in decades of silvopastoral system at the Brazilian savannah biome. Agrofor Syst 92:415–424. https://doi.org/10.1007/s10457-016-9998-8
Leal FA, Miguel EP, Matricardi EAT et al (2015) Redes neurais artificiais na estimativa de volume em um plantio de eucalipto em função de fotografias hemisféricas e número de árvores. Revista Brasileira de Biometria 33:233–249
Leite HG, Nogueira GS, Moreira AM (2006) Efeito do espaçamento e da idade sobre variáveis de povoamentos de Pinus taeda L. Revista Árvore 30:603–612. https://doi.org/10.1590/S0100-67622006000400013
Lemaire G, Franzluebbers A, de Carvalho PCF, Dedieu B (2014) Integrated crop–livestock systems: strategies to achieve synergy between agricultural production and environmental quality. Agr Ecosyst Environ 190:4–8. https://doi.org/10.1016/j.agee.2013.08.009
Lemos-Junior JM, Souza KR, Guimaraes LE et al (2016) Volumetric models for Eucalyptus grandis × urophylla in a crop-livestock-forest integration (CLFI) system in the Brazilian cerrado. Afr J Agric Res 11:1336–1343
Lin Y, Yang H, Ivković M et al (2013) Effect of genotype by spacing interaction on radiata pine genetic parameters for height and diameter growth. For Ecol Manag 304:204–211. https://doi.org/10.1016/j.foreco.2013.05.015
Liziniewicz M, Ekö PM, Agestam E (2012) Effect of spacing on 23-year-old lodgepole pine (Pinus contorta Dougl. var. latifolia) in southern Sweden. Scand J For Res 27:361–371
Magalhães WM, Macedo RLG, Venturin N et al (2007) Desempenho silvicultural de clones e espécies/procedências de Eucalyptus na região noroeste de Minas Gerais. Cerne 13:368–375
Müller MD, Salles TT, Paciullo DSC, Al Et (2014) Equações de altura, volume e afilamento para eucalipto e acácia estabelecidos em sistema silvipastoril. Floresta 44:473–484. https://doi.org/10.5380/rf.v44i3.33149
Nair PKR (1993) An introduction to agroforestry. Springer, Berlin
Ogut F, Maltecca C, Whetten R et al (2014) Genetic analysis of diallel progeny test data using factor analytic linear mixed models. For Sci 60:119–127. https://doi.org/10.5849/forsci.12-108
Oliveira Neto SN, Reis GG, Reis MGF (2007) Eucalipto: as questões ambientais e seu potencial para Sistemas agrossilvipastoris. In: Fernandes EM, Pacuillo DS, Castro CRT, Müller MD, Arcuri PB, Carneiro JC (eds) Sistemas agrossilvipastoris na América do Sul: desafios e potencialidades. Embrapa Gado de Leite, Juiz de Fora, pp 245–282
Oliveira CH, Reis GG, Reis MG et al (2016) Dynamics of eucalypt clones canopy and Brachiaria brizantha production in silvopastoral systems with different spatial arrangements. Agrofor Syst 90:1077–1088
Oliveira CC, Alves FV, de Almeida RG et al (2018) Thermal comfort indices assessed in integrated production systems in the Brazilian savannah. Agrofor Syst 92:1659–1672
Özçelik R, Diamantopoulou MJ, Crecente-Campo F, Eler U (2013) Estimating Crimean juniper tree height using nonlinear regression and artificial neural network models. For Ecol Manag 306:52–60
Pereira Filho GM, Jacovine LAG, Schettini BLS (2020) Influence of the replanting age on yield and growth of eucalypt clonal stands. Revista Árvore 44
Pereira LF, Ferreira CFC, Guimarães RMF (2018) Manejo, qualidade e dinâmica da degradação de pastagens na Mata Atlântica de Minas Gerais-Brasil. Nativa Sinop 6:370–379
Peri PL, Hansen NE, Bahamonde HA et al (2016) Silvopastoral systems under native forest in Patagonia Argentina. In: Silvopastoral systems in Southern South America. Springer, Cham, pp 117–168. https://doi.org/10.1007/978-3-319-24109-8_6
Plano ABC (2012) Plano Setorial de Mitigação e de Adaptação às Mudanças Climáticas para a Consolidação de uma Economia de Baixa Emissão de Carbono na Agricultura. Brasília
Resende RT, Soares AA, Forrester DI et al (2018) Environmental uniformity, site quality and tree competition interact to determine stand productivity of clonal Eucalyptus. For Ecol Manag 410:76–83
Riedmiller M, Braun H (1993) A direct adaptive method for faster backpropagation learning: The RPROP algorithm. In: IEEE international conference on neural networks. IEEE, pp 586–591
Rocha SJSS, Torres CMME, Jacovine LAG et al (2018) Artificial neural networks: modeling tree survival and mortality in the Atlantic Forest biome in Brazil. Sci Total Environ 645:655–661
Salles TT, Leite HG, de Oliveira Neto SN et al (2012) Modelo de Clutter na modelagem de crescimento e produção de eucalipto em sistemas de integração lavoura-pecuária-floresta. Pesquisa Agropecuária Brasileira 47:253–260
Salles TT, Nogueira DA, Beijo LA et al (2019) Bayesian approach and extreme value theory in economic analysis of forestry projects. For Policy Econ 105:64–71. https://doi.org/10.1016/j.forpol.2019.05.021
Santi E, Paloscia S, Pettinato S et al (2017) The potential of multifrequency SAR images for estimating forest biomass in Mediterranean areas. Remote Sens Environ 200:63–73. https://doi.org/10.1016/j.rse.2017.07.038
Schumacher FX, Hall FS (1933) Logarithmic expression of timber-tree volume. J Agric Res 47:719–734
Scolforo HF, McTague JP, Burkhart H et al (2019) Eucalyptus growth and yield system: linking individual-tree and stand-level growth models in clonal Eucalypt plantations in Brazil. For Ecol Manag 432:1–16. https://doi.org/10.1016/j.foreco.2018.08.04
Silveira DP, Leite HG, Silveira VDP et al (2011) Classification of eucalyptus trees for poles in agroforestry system. Revista Árvore 35:875–882. https://doi.org/10.1590/S0100-67622011000500013
Soares FAA, Flôres EL, Cabacinha CD et al (2011) Recursive diameter prediction and volume calculation of eucalyptus trees using Multilayer Perceptron Networks. Comput Electron Agric 78:19–27
Soares AAV, Leite HG, Cruz JP, Forrester DI (2017) Development of stand structural heterogeneity and growth dominance in thinned Eucalyptus stands in Brazil. For Ecol Manag 384:339–346. https://doi.org/10.1016/j.foreco.2016.11.010
Socha J, Netzel P, Cywicka D (2020) Stem taper approximation by artificial neural network and a regression set models. Forests 11:79. https://doi.org/10.3390/f11010079
Somarriba EC, Suárez-Islas A, Calero-Borge W et al (2014) Cocoa–timber agroforestry systems: theobroma cacao–Cordia alliodora in Central America. Agrofor Syst 88:1001–1019
Souza HN, de Goede RG, Brussaard L et al (2012) Protective shade, tree diversity and soil properties in coffee agroforestry systems in the Atlantic Rainforest biome. Agric Ecosyst Environ 146:179–196
Souza GSA, Cosenza DN, Araújo ACSC et al (2018) Evaluation of non-linear taper equations for predicting the diameter of eucalyptus trees. Revista Árvore 42:1
Srivastava RK, Greff K, Schmidhuber J (2015) Training very deep networks. In: Advances in neural information processing systems, pp 2377–2385
Stabile MCC, Azevedo A, Nepstad D (2012) Brazil’s “Low Carbon Agriculture Program”: barriers to implementation. Amazon Environmental Research Institute (IPAM), Belém
Tavares Júnior IS, da Rocha JEC, Ebling ÂA et al (2019) Artificial neural networks and linear regression reduce sample intensity to predict the commercial volume of eucalyptus clones. Forests 10:268. https://doi.org/10.3390/f1003026
R Core Team (2013) R: a language and environment for statistical computing. Vienna, Austria, 2011. http://www.R-project.org
Tonini H, Magalhães CADS, Faria Neto ALD (2019) Technical thinning age of eucalyptus trees grown in crop-forest integration systems. Pesquisa Agropecuária Brasileira 54
Torres CMME, Oliveira AC, Pereira BLC et al (2016) Estimativas da produção e propriedades da madeira de eucalipto em Sistemas Agroflorestais. Sci For Sci 44:137–148. https://doi.org/10.18671/scifor.v44n109.13
Trindade C, Jacovine L, Rezende J, Sartorio M (2012) Gestão e controle da qualidade na atividade florestal. Viçosa: Editora UFV 2
van Laar A, Akça A (2007) Forest mensuration. Springer, Berlin
Villanova PH, Jacovine LAG, Torres CEMM et al (2018) Accumulation of carbon and age of thinning of the tree component in agroforestry systems. Braz J Agric Sci 13:1–16
Zhao D, Kane M, Borders BE (2011) Growth responses to planting density and management intensity in loblolly pine plantations in the southeastern USA Lower Coastal Plain. Ann For Sci 68:625–635. https://doi.org/10.1007/s13595-011-0045-7
Zianis D, Pantera A, Papadopoulos A, Losada MRM (2019) Bayesian and classical biomass allometries for open grown valonian oaks (Q. ithaburensis subs. macrolepis L.) in a silvopastoral system. Agrofor Syst 93:241–253. https://doi.org/10.1007/s10457-016-0060-7
Acknowledgements
We acknowledge Conselho Nacional de Desenvolvimento Cientifico e Tecnológico (CNPq) for funding the research. To Agronomist Rogério Jacinto Gomes, to Professor Lino Roberto Ferreira, coordinators of the Forest Integration Zone-Farming-Livestock-Forest Circuit (Partnership EMATER-MG/Universidade Federal De Viçosa). To farmers for the availability of field demonstration units for data collection. To Amana Obolari, Bruno Schettini, Ricardo Pena, Maria Tereza Nunes, and Cristina Nolasco for their assistance in data collection. We would like to thank Editage (www.editage.com) for English language editing.
Author information
Authors and Affiliations
Contributions
Conceptualization, S.S., S. N. O. N. and H. G. L.; Formal analysis, S.S., R. R. O. N., G. S. A. S., S. N. O. N. and H. G. L.; Methodology, S. S.;S.N.O. N. and H. G. L; Writing-original draft S. S.; Writing-review and editing, S. S., S. N. O. N., R. R. O.N., A. E. M. A., H. G. L.; G. S. A. S.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Silva, S., de Oliveira Neto, S.N., Leite, H.G. et al. Productivity estimate using regression and artificial neural networks in small familiar areas with agrosilvopastoral systems. Agroforest Syst 94, 2081–2097 (2020). https://doi.org/10.1007/s10457-020-00526-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10457-020-00526-1