| spelling |
2023-04-04T13:29:20Z2023-04-04T13:29:20Z2021915461https://doi.org/10.31413/nativa.v9i1.112022318-7670http://hdl.handle.net/1843/51539https://orcid.org/0000-0002-2446-8041https://orcid.org/0000-0003-0909-8633https://orcid.org/0000-0002-8148-083Xhttps://orcid.org/0000-0003-0800-5001https://orcid.org/0000-0003-4268-4458https://orcid.org/0000-0002-1259-3961As informações utilizadas para estimativa da capacidade produtiva de sítios florestais provêm de bases de dados de inventário florestal que podem conter observações discrepantes (outliers). Assim, torna-se necessário a análise de consistência para exclusão destes. Porém, os outliers podem representar determinado padrão de crescimento existente na floresta, logo a exclusão destes pode ser uma ação equivocada. Objetivou-se comparar a performance de diferentes técnicas de modelagem para classificação de sítios florestais, considerando uma base de dados com a presença de outliers. Utilizou-se pares de dados de idade e altura dominante (HD) de parcelas permanentes de Eucalyptus urophyla x Eucalyptus grandis localizadas no norte de Minas Gerais. Foi simulado um outlier de HD. A base de dados foi modelada, com e sem presença de outliers, por regressão linear (RL) e redes neurais artificiais Multilayer Perceptron (MLP) e Radial Basis Function (RBF). Os métodos foram analisados por meio dos critérios estatísticos de precisão: bias, raiz quadrada do erro médio, correlação de Pearson, erro médio percentual e gráfico de dispersão residual. A MLP foi superior para estimativa do índice de sítio. Portanto, a MLP é indicada para classificação de sítios florestais quando há presença de outliers na base de dados.The information used to estimate the productive capacity of forest sites comes from forest inventory databases that may contain discrepant observations (outliers). Thus, consistency analysis is required to exclude these. However, the outliers may represent a certain growth pattern existing in the forest, so their exclusion may be a mistaken action. The objective was to compare the performance of different modeling techniques for forest site classification, considering a database with the presence of outliers. We used pairs of data of age and dominant height (HD) of permanent parcels of Eucalyptus urophila x Eucalyptus grandis located in the north of Minas Gerais. A HD outlier was simulated. The database was modeled, with and without the presence of outliers, by linear regression (RL) and artificial neural networks Multilayer Perceptron (MLP) and Radial Basis Function (RBF). The methods were analyzed by means of precision statistical criteria: bias, square root of mean error, Pearson correlation, mean percentage error and residual scatter plot. The MLP was superior for site index estimation. Therefore, the MLP is indicated for forest site classification when there are outliers in the database.porUniversidade Federal de Minas GeraisUFMGBrasilICA - INSTITUTO DE CIÊNCIAS AGRÁRIASNativaLevantamentos florestaisModelos lineares (Estatística)Redes neurais (Computação)Performance da modelagem para classificação de sítios florestais em bases de dados com outliersPerformance of modeling for classification of forest sites in databases with outliersinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttps://periodicoscientificos.ufmt.br/ojs/index.php/nativa/article/view/11202Pábulo Diogo de SouzaCarlos Alberto Araújo JúniorChristian Dias CabacinhaLeandro Silva de OliveiraCelso Dotta Lopes JúniorWellington de Almeidainfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFMGinstname:Universidade Federal de Minas Gerais (UFMG)instacron:UFMGLICENSELicense.txtLicense.txttext/plain; charset=utf-82042https://repositorio.ufmg.br/bitstream/1843/51539/1/License.txtfa505098d172de0bc8864fc1287ffe22MD51ORIGINALPerformance da modelagem para classificação de sítios florestais em bases de dados com outliers.pdfPerformance da modelagem para classificação de sítios florestais em bases de dados com outliers.pdfapplication/pdf1086212https://repositorio.ufmg.br/bitstream/1843/51539/2/Performance%20da%20modelagem%20para%20classifica%c3%a7%c3%a3o%20de%20s%c3%adtios%20florestais%20em%20bases%20de%20dados%20com%20outliers.pdffdc84316d1906240f32af938c7e89312MD521843/515392023-04-04 16:54:54.974oai:repositorio.ufmg.br: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Repositório InstitucionalPUBhttps://repositorio.ufmg.br/oaiopendoar:2023-04-04T19:54:54Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG)false
|