Desenvolvimento de técnicas de inteligência artificial no manejo florestal
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Tipo de documento: | Tese |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFLA |
Texto Completo: | http://repositorio.ufla.br/jspui/handle/1/46250 |
Resumo: | The use of computational intelligence in the forestry sector is recurrent for several problems, mainly as an aid in decision making for forest managers. Congruent to this, the expansion of big data in the sector is notable, providing a large number of data. Thus, the application of methodologies that assertively facilitate the compilation and processing of this data becomes essential. Given this perspective, the thesis focuses on the use of the genetic algorithm to solve problems in the forestry sector, focusing on the selection and allocation of variables in a nonlinear tapering model (article 1), in addition to its application with a multiobjective character for selection of trees to be explored in the Amazon rainforest (article 2). In article 1, the objective of the work was to generate an efficient model for predicting the diameter along the shaft, in addition to investigating a biological approach to the selection of morphometric variables. Classical, morphometric, temporal and a constant variable were made available to the genetic algorithm in order to select and allocate these variables in the Kozak model (2004). In addition, the adjustments to the regression coefficients were performed by the algorithm. The model selected by the algorithm showed good diameter predictions along the shaft, with the selected variables having logical behaviors with the diametric increment. Article 2 was intended to use a multiobjective algorithm to assist in decision making in the selective cutting of a Mixed Ombrophilous Deciduous Forest, based on economic and environmental criteria. Which generated multiple solutions classified according to economic, ecological and balanced nature. The genetic algorithm was efficient in reconciling the different objectives, allowing low impact on the remaining stand. When analyzing the results presented in the thesis, it is noted that the genetic algorithm was effective in solving the proposed problems. In addition to its flexibility for different approaches, it is easy to structure for binary and continuous variables, and mono and multiobjective scenarios. |
id |
UFLA_a2ee9b674e710737609541ef33c0cdec |
---|---|
oai_identifier_str |
oai:localhost:1/46250 |
network_acronym_str |
UFLA |
network_name_str |
Repositório Institucional da UFLA |
repository_id_str |
|
spelling |
Desenvolvimento de técnicas de inteligência artificial no manejo florestalDevelopment of artificial intelligence techniques in forest managementAlgoritmo genéticoSeleção de variáveisProblemas multiobjetivosGestão florestalGenetic algorithmFeature selectionMultiobjective problemsForest managementRecursos Florestais e Engenharia FlorestalThe use of computational intelligence in the forestry sector is recurrent for several problems, mainly as an aid in decision making for forest managers. Congruent to this, the expansion of big data in the sector is notable, providing a large number of data. Thus, the application of methodologies that assertively facilitate the compilation and processing of this data becomes essential. Given this perspective, the thesis focuses on the use of the genetic algorithm to solve problems in the forestry sector, focusing on the selection and allocation of variables in a nonlinear tapering model (article 1), in addition to its application with a multiobjective character for selection of trees to be explored in the Amazon rainforest (article 2). In article 1, the objective of the work was to generate an efficient model for predicting the diameter along the shaft, in addition to investigating a biological approach to the selection of morphometric variables. Classical, morphometric, temporal and a constant variable were made available to the genetic algorithm in order to select and allocate these variables in the Kozak model (2004). In addition, the adjustments to the regression coefficients were performed by the algorithm. The model selected by the algorithm showed good diameter predictions along the shaft, with the selected variables having logical behaviors with the diametric increment. Article 2 was intended to use a multiobjective algorithm to assist in decision making in the selective cutting of a Mixed Ombrophilous Deciduous Forest, based on economic and environmental criteria. Which generated multiple solutions classified according to economic, ecological and balanced nature. The genetic algorithm was efficient in reconciling the different objectives, allowing low impact on the remaining stand. When analyzing the results presented in the thesis, it is noted that the genetic algorithm was effective in solving the proposed problems. In addition to its flexibility for different approaches, it is easy to structure for binary and continuous variables, and mono and multiobjective scenarios.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)O uso de inteligência computacional no setor florestal é recorrente para diversos problemas, principalmente como auxiliador na tomada de decisões para os gestores florestais. Congruente a isso, a expansão de big data no setor é notável, proporcionando elevado número de dados. Com isso, a aplicação de metodologias que facilitem, de forma assertiva, a compilação e o processamento desses dados se tornam essencial. Diante dessa perspectiva, a tese foca no uso do algoritmo genético para solução de problemas do setor florestal, tendo como foco a seleção e alocação de variáveis em um modelo não linear de afilamento (artigo 1), além de sua aplicação com caráter multiobjetivo para seleção de árvores a serem exploradas na floreta Amazônica (artigo 2). No artigo 1, o objetivo do trabalho foi gerar um modelo eficiente para predição do diâmetro ao longo do fuste, além de investigar uma abordagem biológica da seleção das variáveis morfométricas. Foram disponibilizadas variáveis clássicas, morfométricas, temporal e uma constante para o algoritmo genético a fim de selecionar e alocar essas variáveis no modelo de Kozak (2004). Além disso, os ajustes dos coeficientes de regressão foram realizados pelo algoritmo. O modelo selecionado pelo algoritmo apresentou boas predições de diâmetro ao longo do fuste, tendo as variáveis selecionadas comportamentos lógicos com o incremento diamétrico. O artigo 2 teve como intuito utilizar um algoritmo multiobjetivo para auxiliar na tomada de decisão no corte seletivo de uma Floresta Decidual Ombrófila Mista, baseando-se em critérios econômicos e ambientais, o qual gerou múltiplas soluções classificadas conforme natureza econômica, ecológica e de equilíbrio. O algoritmo genético foi eficiente em conciliar os diferentes objetivos, possibilitando baixo impacto no povoamento remanescente. Ao se analisar os resultados apresentados na tese, nota-se que o algoritmo genético foi eficaz para solucionar os problemas propostos. Além de sua alta adaptabilidade em diferentes abordagens, sendo de fácil estruturação para variáveis binárias e continuas, e cenários mono e multiobjetivos.Universidade Federal de LavrasPrograma de Pós-Graduação em Engenharia FlorestalUFLAbrasilDepartamento de Ciências FlorestaisGomide, Lucas RezendeBarbosa, Bruno Henrique GronnerGomide, Lucas RezendeSilva, Carolina Souza Jarochinski eScolforo, José Roberto SoaresBarbosa, Bruno Henrique GroennerFigueiredo Filho, AfonsoLacerda, Talles Hudson Souza2021-05-10T17:36:50Z2021-05-10T17:36:50Z2021-05-102021-04-09info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisapplication/pdfLACERDA, T. H. S. Desenvolvimento de técnicas de inteligência artificial no manejo florestal. 2021. 99 p. Tese (Doutorado em Engenharia Florestal) – Universidade Federal de Lavras, Lavras, 2021.http://repositorio.ufla.br/jspui/handle/1/46250porinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFLAinstname:Universidade Federal de Lavras (UFLA)instacron:UFLA2023-05-10T19:07:16Zoai:localhost:1/46250Repositório InstitucionalPUBhttp://repositorio.ufla.br/oai/requestnivaldo@ufla.br || repositorio.biblioteca@ufla.bropendoar:2023-05-10T19:07:16Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA)false |
dc.title.none.fl_str_mv |
Desenvolvimento de técnicas de inteligência artificial no manejo florestal Development of artificial intelligence techniques in forest management |
title |
Desenvolvimento de técnicas de inteligência artificial no manejo florestal |
spellingShingle |
Desenvolvimento de técnicas de inteligência artificial no manejo florestal Lacerda, Talles Hudson Souza Algoritmo genético Seleção de variáveis Problemas multiobjetivos Gestão florestal Genetic algorithm Feature selection Multiobjective problems Forest management Recursos Florestais e Engenharia Florestal |
title_short |
Desenvolvimento de técnicas de inteligência artificial no manejo florestal |
title_full |
Desenvolvimento de técnicas de inteligência artificial no manejo florestal |
title_fullStr |
Desenvolvimento de técnicas de inteligência artificial no manejo florestal |
title_full_unstemmed |
Desenvolvimento de técnicas de inteligência artificial no manejo florestal |
title_sort |
Desenvolvimento de técnicas de inteligência artificial no manejo florestal |
author |
Lacerda, Talles Hudson Souza |
author_facet |
Lacerda, Talles Hudson Souza |
author_role |
author |
dc.contributor.none.fl_str_mv |
Gomide, Lucas Rezende Barbosa, Bruno Henrique Gronner Gomide, Lucas Rezende Silva, Carolina Souza Jarochinski e Scolforo, José Roberto Soares Barbosa, Bruno Henrique Groenner Figueiredo Filho, Afonso |
dc.contributor.author.fl_str_mv |
Lacerda, Talles Hudson Souza |
dc.subject.por.fl_str_mv |
Algoritmo genético Seleção de variáveis Problemas multiobjetivos Gestão florestal Genetic algorithm Feature selection Multiobjective problems Forest management Recursos Florestais e Engenharia Florestal |
topic |
Algoritmo genético Seleção de variáveis Problemas multiobjetivos Gestão florestal Genetic algorithm Feature selection Multiobjective problems Forest management Recursos Florestais e Engenharia Florestal |
description |
The use of computational intelligence in the forestry sector is recurrent for several problems, mainly as an aid in decision making for forest managers. Congruent to this, the expansion of big data in the sector is notable, providing a large number of data. Thus, the application of methodologies that assertively facilitate the compilation and processing of this data becomes essential. Given this perspective, the thesis focuses on the use of the genetic algorithm to solve problems in the forestry sector, focusing on the selection and allocation of variables in a nonlinear tapering model (article 1), in addition to its application with a multiobjective character for selection of trees to be explored in the Amazon rainforest (article 2). In article 1, the objective of the work was to generate an efficient model for predicting the diameter along the shaft, in addition to investigating a biological approach to the selection of morphometric variables. Classical, morphometric, temporal and a constant variable were made available to the genetic algorithm in order to select and allocate these variables in the Kozak model (2004). In addition, the adjustments to the regression coefficients were performed by the algorithm. The model selected by the algorithm showed good diameter predictions along the shaft, with the selected variables having logical behaviors with the diametric increment. Article 2 was intended to use a multiobjective algorithm to assist in decision making in the selective cutting of a Mixed Ombrophilous Deciduous Forest, based on economic and environmental criteria. Which generated multiple solutions classified according to economic, ecological and balanced nature. The genetic algorithm was efficient in reconciling the different objectives, allowing low impact on the remaining stand. When analyzing the results presented in the thesis, it is noted that the genetic algorithm was effective in solving the proposed problems. In addition to its flexibility for different approaches, it is easy to structure for binary and continuous variables, and mono and multiobjective scenarios. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-05-10T17:36:50Z 2021-05-10T17:36:50Z 2021-05-10 2021-04-09 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
LACERDA, T. H. S. Desenvolvimento de técnicas de inteligência artificial no manejo florestal. 2021. 99 p. Tese (Doutorado em Engenharia Florestal) – Universidade Federal de Lavras, Lavras, 2021. http://repositorio.ufla.br/jspui/handle/1/46250 |
identifier_str_mv |
LACERDA, T. H. S. Desenvolvimento de técnicas de inteligência artificial no manejo florestal. 2021. 99 p. Tese (Doutorado em Engenharia Florestal) – Universidade Federal de Lavras, Lavras, 2021. |
url |
http://repositorio.ufla.br/jspui/handle/1/46250 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Lavras Programa de Pós-Graduação em Engenharia Florestal UFLA brasil Departamento de Ciências Florestais |
publisher.none.fl_str_mv |
Universidade Federal de Lavras Programa de Pós-Graduação em Engenharia Florestal UFLA brasil Departamento de Ciências Florestais |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFLA instname:Universidade Federal de Lavras (UFLA) instacron:UFLA |
instname_str |
Universidade Federal de Lavras (UFLA) |
instacron_str |
UFLA |
institution |
UFLA |
reponame_str |
Repositório Institucional da UFLA |
collection |
Repositório Institucional da UFLA |
repository.name.fl_str_mv |
Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA) |
repository.mail.fl_str_mv |
nivaldo@ufla.br || repositorio.biblioteca@ufla.br |
_version_ |
1807835121927061504 |