Artificial Neural Networks for estimating the biometric variables of seedlings from forest species produced in different substrates
DOI:
https://doi.org/10.5965/223811711812019047Keywords:
recovery of degraded areas, artificial intelligence, organic substratesAbstract
The aim of this study was to evaluate the stem growth in diameter and height as well as the production of total dry matter from seedlings of Myracrodruon urundeuva, Jacaranda brasiliana and Mimosa caesalpiniaefolia. Concurrently, an Artificial Neural Network (RNA) of Multilayer Perceptron type that would be able to estimate the H and the MST of the seedlings of the studied species was developed. The seedlings were cultivated in a protected environment with 50% shade. Thus, the treatments were considered with five proportions of the organic material (0, 20, 40, 60 and 80% v/v) in the final substrate composition (desertified area soil). At 120 days after sowing, the seedlings were collected to determine the biometric variables. The MLP network was used with help of the Levenberg-Marquardat training algorithm. The variables used as input of the MLP for height and dry mass estimation of the seedlings were: stem diameter, minimum, medium and maximum diameter of stem; and species and sources of organic residues (cattle manure, goat manure and rice straw), totaling ten entries. The hyperbolic tangent activation function was conducted. As a result, a 80:20% ratio (bovine manure and/or goat manure: soil from the degraded area) is recommended to be used in the growing substrate for seedling growth. The addition of bovine manure and goat manure doses influenced the Jacaranda brasiliana DC, with the linear effect increasing with the estimated value of 2.66 mm plant-1. For H, the addition of bovine and goat manure influenced the growth of Myracrodruon urundeuva seedlings. The MST production of seedlings from the three species was also distributed as a function of the increasing proportions of organic residues incorporated into the culture substrate. The use of the Artificial Neural Network of Multilayer Perceptron type was efficient for the estimation of the height and total dry mass of the species studied.
Downloads
References
ARAÚJO EF et al. 2017. Crescimento e qualidade de mudas de paricá produzidas em substratos à base de resíduos orgânicos. Nativa 5: 16-23.
ASHRAF MI et al. 2015. A novel modelling approach for predicting forest growth and yield under climate change. PloS one 10: 1-18.
BINOTI MLMS et al. 2013. Aplicação de redes neurais artificiais para estimação da altura de povoamentos equiâneos de eucalipto. Revista Árvore 37: 639-645.
BINOTI MLMS et al. 2014. Redes neurais artificiais para estimação do volume de árvores. Revista Árvore 38: 283-288.
BINOTI MLMS et al. 2015. Prognose em nível de povoamento de clones de eucalipto empregando redes neurais artificiais. Cerne 21: 97-105.
BRAGA AP et al. 2007. Redes neurais artificiais: teoria e aplicações. 2.ed. Rio de Janeiro: LTC. 248p.
BRASIL. 2010. Política nacional de resíduos sólidos, Lei 12.305, de 2 de agosto de 2010. Institui a Política Nacional de Resíduos Sólidos. DOU 3/10/2010. Seção 1. p.3.
CABACINHA CD & LAFETÁ BO 2017. Floristic diversity and equitability in forest fragments using artificial neural networks. Ciência Florestal 27: 143-152.
CABREIRA GV et al. 2017. Biossólido como componente de substrato para produção de mudas florestais. Floresta 47: 165-176.
CARNEIRO JGA. 1995. Produção e controle de qualidade de mudas florestais. 1.ed. Curitiba: UFPR. 451p.
CRUZ CAF et al. 2006. Efeito da adubação nitrogenada na produção de mudas de Sete-Cascas (Samanea inopinata (Harms) Ducke). Revista Árvore 30: 537-546.
CRUZ CAF et al. 2011. Efeito de macronutrientes sobre o crescimento e qualidade de mudas de canafístula cultivadas em Latossolo Vermelho-Amarelo distrófico. Revista Árvore 35: 983-995.
DONAGEMA GK et al. 2011. Manual de métodos de análise do solo. 2.ed. Rio de Janeiro: Embrapa Solos. 225p.
FERNANDES MM et al. 2014. Aspectos biológicos e espécies potenciais para restauração ecológica de áreas em desertificação no Sul do Piauí - Brasil. Revista Verde de Agroecologia e Desenvolvimento Sustentável 9: 6-13.
FERREIRA JCB et al. 2014. Altura de mudas de Tibouchina granulosa Cogn. (melastomataceae) estimada por redes neurais artificiais. Revista da Sociedade Brasileira de Arborização Urbana 9: 151-160.
GASPARIN E et al. 2014. Influência do substrato e do volume de recipiente na qualidade das mudas de Cabralea canjerana (Vell.) Mart. em viveiro e no campo. Ciência Florestal 24: 553-563.
GOMES JM & PAIVA HN. 2012. Viveiros florestais: propagação sexuada. Viçosa: UFV. 116p.
HAYKIN S. 2001. Redes neurais: princípios e prática. 2.ed. Porto Alegre: Bookman. 900p.
LARCHER W. 2000. Ecofisiologia vegetal. 1.ed. São Carlos: RIMA Artes e Textos. 532p.
LEITE HG et al. 2011. Estimation of inside-bark diameter and heart wood diameter for Tectona grandis Linn. trees using artificial neural networks. European Journal of Forest Research 130: 263-269.
LUSTOSA FILHO JF et al. 2015. Influence of organic substrates on growth and nutrient contents of jatobá (Hymenaea stigonocarpa). African Journal of Agricultural Research 10: 2544-2552.
MAEDA EE et al. 2009. Predicting forest fire in the Brazilian Amazon using MODIS imagery and artificial neural networks. International Journal of Applied Earth Observation and Geoinformation 11: 265-272.
NUNES MH & GÖRGENS EB. 2016. Artificial Intelligence Procedures for Tree Taper Estimation within a Complex Vegetation Mosaic in Brazil. PloS one 11: 1-16.
RECKNAGEL F. 2001. Applications of machine learning to ecological modelling. Ecological Modelling 146: 303-310.
SILVA MLM et al. 2009. Ajuste do modelo de Schumacher e Hall e aplicação de redes neurais artificiais para estimar volume de árvores de eucalipto. Revista Árvore 33: 1133-1139.
Downloads
Published
Issue
Section
License
Copyright (c) 2019 Revista de Ciências Agroveterinárias (Journal of Agroveterinary Sciences)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors publishing in this journal are in agreement with the following terms:
a) Authors maintain the copyrights and concede to the journal the copyright for the first publication, according to Creative Commons Attribution Licence.
b) Authors have the authority to assume additional contracts with the content of the manuscript.
c) Authors may supply and distribute the manuscript published by this journal.
