Uso de redes neurais artificiais no mapeamento de solos na Bacia do Rio Turvo Sujo - Viçosa MG

Detalhes bibliográficos
Autor(a) principal: Melo, Leonardo Vaz de
Data de Publicação: 2009
Tipo de documento: Dissertação
Idioma: por
Título da fonte: LOCUS Repositório Institucional da UFV
Texto Completo: http://locus.ufv.br/handle/123456789/5473
Resumo: Human occupations have a history of lack of planning and lack of organization that, many times, have compromised people s quality of life and environmental quality. It is observed that soil loss is a major environmental problem associated with the use and occupation of new areas, which, besides affecting the native flora and fauna, can seriously compromise the flow of watercourses and, therefore, people's quality of life. In this context, in any planning process, the availability and the information about the soil resources, in particular of its limitations and capabilities, are important data. Given the above, this study has aimed to: i) evaluate the effectiveness of two different approaches to soil mapping: automated via Artificial Neural Networks (ANN) and the traditional one, made with the help of soil scientists; and ii) estimate the carbon stock of the soil in Bacia do Rio Turvo Sujo, located in the Zona da Mata of Minas Gerais. The methodology consisted of modeling the distribution of soils in the basin area, using existing and new data, Geographic Information System (GIS), RNA's and field checks. The existing data were obtained in theses and documents that contained information on soil profiles in the area. The new data were collected in the field, in modal profiles for specific points of the basin, due to the absence of previous data. In the collections in the field, the profile was described and samples were collected from each horizon. We also raised some points of observation of some classes of soil. In working with GIS, a digital elevation model (DEM) was generated and from it, there were slope mapping, radiation, surface of sun exposure, horizontal distance, vertical distance, and curvature. Combining the curvature, slope, and vertical distance to drainage resulted in a map of units in the landscape of that region: top, terrace, convex and concave hillsides. In addition to these input data, three bands of an ASTER image (from 2001) and the Normalized Difference Vegetation Index (NDVI) were used. Two soil maps were then produced: one made with soil scientists, focused solely on field and laboratory data, and the other, which used GIS and ANN tools. The evaluation of the suitability of soil maps produced was made from the Kappa index. In the conventional map five classes of soil were established, and in the one produced via ANN, seven classes. The results showed greater accuracy of the map produced via ANN (Kappa = 66.6%) compared with that generated in traditional way (Kappa = 42.6%). The carbon stock in the soil, estimated up to one meter depth based on profile data from the basin of Rio Turvo, was around 4.900.000 tons, considering the depth of 1 meter. The relationship between the occurrence of soils and relief attributes, derived from DEM, were decisive in the delineation of soil mapping units in the region studied, which certainly ensured a better performance of the digital map production. Although extrapolation to other regions should be taken with caution, the results indicate that the ANNs were able to map the soils in the Bacia do Rio Turvo Sujo in an automated and appropriate manner, with more detailed results than the traditional procedure. In the conventional classification, it is difficult to perfectly integrate a wide range of information from different sources and in this respect, the ANNs result in helping to obtain a final product of better quality. Obviously, this data processing will not be able to replace human hands and minds in the survey procedures and soil classification, but should be taken as a tool to obtain results increasingly closer to reality.
id UFV_bb066fdc0b2032e8eda6ca3d550b9b32
oai_identifier_str oai:locus.ufv.br:123456789/5473
network_acronym_str UFV
network_name_str LOCUS Repositório Institucional da UFV
repository_id_str 2145
spelling Melo, Leonardo Vaz dehttp://lattes.cnpq.br/8375624046930533Fernandes Filho, Elpídio Ináciohttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4703656Z4Schaefer, Carlos Ernesto Gonçalves Reynaudhttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4723204Y8Fernandes, Raphael Bragança Alveshttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4728400J8Vieira, Carlos Antonio Oliveirahttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4728250D0Chagas, César da Silvahttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4785135D2Moreau, Maurício Santanahttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4701947P52015-03-26T13:53:20Z2012-04-132015-03-26T13:53:20Z2009-03-09MELO, Leonardo Vaz de. The use of artificial neural networks in the soil mapping in Bacia do Rio Turvo Sujo - Viçosa MG. 2009. 95 f. Dissertação (Mestrado em Fertilidade do solo e nutrição de plantas; Gênese, Morfologia e Classificação, Mineralogia, Química,) - Universidade Federal de Viçosa, Viçosa, 2009.http://locus.ufv.br/handle/123456789/5473Human occupations have a history of lack of planning and lack of organization that, many times, have compromised people s quality of life and environmental quality. It is observed that soil loss is a major environmental problem associated with the use and occupation of new areas, which, besides affecting the native flora and fauna, can seriously compromise the flow of watercourses and, therefore, people's quality of life. In this context, in any planning process, the availability and the information about the soil resources, in particular of its limitations and capabilities, are important data. Given the above, this study has aimed to: i) evaluate the effectiveness of two different approaches to soil mapping: automated via Artificial Neural Networks (ANN) and the traditional one, made with the help of soil scientists; and ii) estimate the carbon stock of the soil in Bacia do Rio Turvo Sujo, located in the Zona da Mata of Minas Gerais. The methodology consisted of modeling the distribution of soils in the basin area, using existing and new data, Geographic Information System (GIS), RNA's and field checks. The existing data were obtained in theses and documents that contained information on soil profiles in the area. The new data were collected in the field, in modal profiles for specific points of the basin, due to the absence of previous data. In the collections in the field, the profile was described and samples were collected from each horizon. We also raised some points of observation of some classes of soil. In working with GIS, a digital elevation model (DEM) was generated and from it, there were slope mapping, radiation, surface of sun exposure, horizontal distance, vertical distance, and curvature. Combining the curvature, slope, and vertical distance to drainage resulted in a map of units in the landscape of that region: top, terrace, convex and concave hillsides. In addition to these input data, three bands of an ASTER image (from 2001) and the Normalized Difference Vegetation Index (NDVI) were used. Two soil maps were then produced: one made with soil scientists, focused solely on field and laboratory data, and the other, which used GIS and ANN tools. The evaluation of the suitability of soil maps produced was made from the Kappa index. In the conventional map five classes of soil were established, and in the one produced via ANN, seven classes. The results showed greater accuracy of the map produced via ANN (Kappa = 66.6%) compared with that generated in traditional way (Kappa = 42.6%). The carbon stock in the soil, estimated up to one meter depth based on profile data from the basin of Rio Turvo, was around 4.900.000 tons, considering the depth of 1 meter. The relationship between the occurrence of soils and relief attributes, derived from DEM, were decisive in the delineation of soil mapping units in the region studied, which certainly ensured a better performance of the digital map production. Although extrapolation to other regions should be taken with caution, the results indicate that the ANNs were able to map the soils in the Bacia do Rio Turvo Sujo in an automated and appropriate manner, with more detailed results than the traditional procedure. In the conventional classification, it is difficult to perfectly integrate a wide range of information from different sources and in this respect, the ANNs result in helping to obtain a final product of better quality. Obviously, this data processing will not be able to replace human hands and minds in the survey procedures and soil classification, but should be taken as a tool to obtain results increasingly closer to reality.As ocupações humanas apresentam um histórico de ausência de planejamento e falta de organização que tem, muitas das vezes, comprometido a qualidade de vida da população e a qualidade ambiental. Observa-se que a perda do solo é um dos grandes problemas ambientais associado ao uso e ocupação de novas áreas, que além de afetar a flora e fauna nativas, pode comprometer seriamente a vazão dos cursos d água e, portanto, a qualidade de vida das pessoas. Nesse contexto, em qualquer processo de planejamento, a disponibilidade e o domínio da informação acerca do recurso solo, em especial, de suas limitações e potencialidades são dados importantes. Diante do exposto, o presente trabalho teve como objetivos: i) avaliar a eficiência de duas diferentes metodologias de mapeamento dos solos: automatizada, via Redes Neurais Artificiais (RNA s) e a tradicional, efetuada com auxílio de pedólogos; ii) estimar o estoque de carbono dos solos da Bacia do Rio Turvo Sujo, localizada na Zona da Mata mineira. A metodologia utilizada consistiu da execução da modelagem da distribuição de solos na área da bacia, utilizando-se dados existentes e novos, Sistema de Informações Geográficas (SIG s), RNA s e checagens de campo. Os dados existentes foram obtidos em teses e documentos que continham informações de perfis de solos presentes na área. Os novos dados foram coletados em campo, em perfis modais, para pontos específicos da bacia, em função da ausência de dados anteriores. Nas coletas de campo, o perfil foi descrito e amostras foram coletadas de cada horizonte. Foram levantados também alguns pontos de observação de algumas classes de solo. No trabalho com SIG foi gerado um modelo digital de elevação (MDE) e, a partir dele, os mapas de declividade, radiação, face de exposição solar, distância horizontal, distância vertical e curvatura. Combinando-se a curvatura, a declividade e a distância vertical à drenagem produziu-se um mapa de unidades da paisagem na região: topo, terraço, encostas côncavas e encostas convexas. Além destes dados de entrada, foram usadas três bandas de uma imagem ASTER (do ano de 2001) e o Índice de Vegetação por Diferença Normalizada (NDVI). Dois mapas de solos foram então produzidos: um efetuado juntamente com pedólogos e centrado unicamente nos dados de campo e de laboratório, e o outro, que fez uso das ferramentas de SIG e RNA s. A avaliação da adequabilidade dos mapas de solos produzidos foi efetuada a partir do índice Kappa. No mapa convencional foram estabelecidas cinco classes de solo e, no produzido via RNA, sete classes. Os resultados indicaram maior acerto do mapa produzido via RNA (Kappa = 66,6%), em comparação com aquele gerado pela forma tradicional (Kappa = 42,6%). O estoque de carbono no solo estimado até um metro de profundidade com base nos dados dos perfis da bacia do Rio Turvo Sujo foi em torno de 4.900.000 toneladas, considerando a profundidade de 1 metro. As relações entre a ocorrência dos solos e os atributos do relevo derivados do MDE foram determinantes para o delineamento de unidades de mapeamento de solos na região estudada, o que por certo, garantiu um melhor desempenho do mapa digital produzido. Embora a extrapolação para outras regiões deva ser tomada com ressalvas, os resultados obtidos indicam que as RNA s foram capazes de mapear de forma automatizada e adequada os solos da Bacia do Rio Turvo Sujo, com resultados mais detalhados do que o procedimento tradicional. Na classificação convencional, é difícil a perfeita integração de um grande número de informações de diferentes origens e, sob esse aspecto, as RNA s acabam auxiliando na obtenção de um produto final de melhor qualidade. Obviamente que esse procedimento informático não será capaz de substituir as mãos e a mente humana nos procedimentos de levantamento e classificação de solos, mas deve ser tomado como uma ferramenta para a obtenção de resultados cada vez mais próximos da realidade.Coordenação de Aperfeiçoamento de Pessoal de Nível Superiorapplication/pdfporUniversidade Federal de ViçosaMestrado em Solos e Nutrição de PlantasUFVBRFertilidade do solo e nutrição de plantas; Gênese, Morfologia e Classificação, Mineralogia, Química,GeoprocessamentoBacias hidrográficasClassificação de solosGISWatershedsSoil classificationCNPQ::CIENCIAS AGRARIAS::AGRONOMIA::CIENCIA DO SOLOUso de redes neurais artificiais no mapeamento de solos na Bacia do Rio Turvo Sujo - Viçosa MGThe use of artificial neural networks in the soil mapping in Bacia do Rio Turvo Sujo - Viçosa MGinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/openAccessreponame:LOCUS Repositório Institucional da UFVinstname:Universidade Federal de Viçosa (UFV)instacron:UFVORIGINALtexto completo.pdfapplication/pdf4200275https://locus.ufv.br//bitstream/123456789/5473/1/texto%20completo.pdf4b02f31363027fef3af5dffa77ba3d07MD51TEXTtexto completo.pdf.txttexto completo.pdf.txtExtracted texttext/plain171611https://locus.ufv.br//bitstream/123456789/5473/2/texto%20completo.pdf.txt30a2e78a779cb49f7bcbb7edac4aa242MD52THUMBNAILtexto completo.pdf.jpgtexto completo.pdf.jpgIM Thumbnailimage/jpeg3702https://locus.ufv.br//bitstream/123456789/5473/3/texto%20completo.pdf.jpg541b118d70b065b582fc309a0bb577c2MD53123456789/54732016-04-11 23:04:06.303oai:locus.ufv.br:123456789/5473Repositório InstitucionalPUBhttps://www.locus.ufv.br/oai/requestfabiojreis@ufv.bropendoar:21452016-04-12T02:04:06LOCUS Repositório Institucional da UFV - Universidade Federal de Viçosa (UFV)false
dc.title.por.fl_str_mv Uso de redes neurais artificiais no mapeamento de solos na Bacia do Rio Turvo Sujo - Viçosa MG
dc.title.alternative.eng.fl_str_mv The use of artificial neural networks in the soil mapping in Bacia do Rio Turvo Sujo - Viçosa MG
title Uso de redes neurais artificiais no mapeamento de solos na Bacia do Rio Turvo Sujo - Viçosa MG
spellingShingle Uso de redes neurais artificiais no mapeamento de solos na Bacia do Rio Turvo Sujo - Viçosa MG
Melo, Leonardo Vaz de
Geoprocessamento
Bacias hidrográficas
Classificação de solos
GIS
Watersheds
Soil classification
CNPQ::CIENCIAS AGRARIAS::AGRONOMIA::CIENCIA DO SOLO
title_short Uso de redes neurais artificiais no mapeamento de solos na Bacia do Rio Turvo Sujo - Viçosa MG
title_full Uso de redes neurais artificiais no mapeamento de solos na Bacia do Rio Turvo Sujo - Viçosa MG
title_fullStr Uso de redes neurais artificiais no mapeamento de solos na Bacia do Rio Turvo Sujo - Viçosa MG
title_full_unstemmed Uso de redes neurais artificiais no mapeamento de solos na Bacia do Rio Turvo Sujo - Viçosa MG
title_sort Uso de redes neurais artificiais no mapeamento de solos na Bacia do Rio Turvo Sujo - Viçosa MG
author Melo, Leonardo Vaz de
author_facet Melo, Leonardo Vaz de
author_role author
dc.contributor.authorLattes.por.fl_str_mv http://lattes.cnpq.br/8375624046930533
dc.contributor.author.fl_str_mv Melo, Leonardo Vaz de
dc.contributor.advisor-co1.fl_str_mv Fernandes Filho, Elpídio Inácio
dc.contributor.advisor-co1Lattes.fl_str_mv http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4703656Z4
dc.contributor.advisor-co2.fl_str_mv Schaefer, Carlos Ernesto Gonçalves Reynaud
dc.contributor.advisor-co2Lattes.fl_str_mv http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4723204Y8
dc.contributor.advisor1.fl_str_mv Fernandes, Raphael Bragança Alves
dc.contributor.advisor1Lattes.fl_str_mv http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4728400J8
dc.contributor.referee1.fl_str_mv Vieira, Carlos Antonio Oliveira
dc.contributor.referee1Lattes.fl_str_mv http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4728250D0
dc.contributor.referee2.fl_str_mv Chagas, César da Silva
dc.contributor.referee2Lattes.fl_str_mv http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4785135D2
dc.contributor.referee3.fl_str_mv Moreau, Maurício Santana
dc.contributor.referee3Lattes.fl_str_mv http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4701947P5
contributor_str_mv Fernandes Filho, Elpídio Inácio
Schaefer, Carlos Ernesto Gonçalves Reynaud
Fernandes, Raphael Bragança Alves
Vieira, Carlos Antonio Oliveira
Chagas, César da Silva
Moreau, Maurício Santana
dc.subject.por.fl_str_mv Geoprocessamento
Bacias hidrográficas
Classificação de solos
topic Geoprocessamento
Bacias hidrográficas
Classificação de solos
GIS
Watersheds
Soil classification
CNPQ::CIENCIAS AGRARIAS::AGRONOMIA::CIENCIA DO SOLO
dc.subject.eng.fl_str_mv GIS
Watersheds
Soil classification
dc.subject.cnpq.fl_str_mv CNPQ::CIENCIAS AGRARIAS::AGRONOMIA::CIENCIA DO SOLO
description Human occupations have a history of lack of planning and lack of organization that, many times, have compromised people s quality of life and environmental quality. It is observed that soil loss is a major environmental problem associated with the use and occupation of new areas, which, besides affecting the native flora and fauna, can seriously compromise the flow of watercourses and, therefore, people's quality of life. In this context, in any planning process, the availability and the information about the soil resources, in particular of its limitations and capabilities, are important data. Given the above, this study has aimed to: i) evaluate the effectiveness of two different approaches to soil mapping: automated via Artificial Neural Networks (ANN) and the traditional one, made with the help of soil scientists; and ii) estimate the carbon stock of the soil in Bacia do Rio Turvo Sujo, located in the Zona da Mata of Minas Gerais. The methodology consisted of modeling the distribution of soils in the basin area, using existing and new data, Geographic Information System (GIS), RNA's and field checks. The existing data were obtained in theses and documents that contained information on soil profiles in the area. The new data were collected in the field, in modal profiles for specific points of the basin, due to the absence of previous data. In the collections in the field, the profile was described and samples were collected from each horizon. We also raised some points of observation of some classes of soil. In working with GIS, a digital elevation model (DEM) was generated and from it, there were slope mapping, radiation, surface of sun exposure, horizontal distance, vertical distance, and curvature. Combining the curvature, slope, and vertical distance to drainage resulted in a map of units in the landscape of that region: top, terrace, convex and concave hillsides. In addition to these input data, three bands of an ASTER image (from 2001) and the Normalized Difference Vegetation Index (NDVI) were used. Two soil maps were then produced: one made with soil scientists, focused solely on field and laboratory data, and the other, which used GIS and ANN tools. The evaluation of the suitability of soil maps produced was made from the Kappa index. In the conventional map five classes of soil were established, and in the one produced via ANN, seven classes. The results showed greater accuracy of the map produced via ANN (Kappa = 66.6%) compared with that generated in traditional way (Kappa = 42.6%). The carbon stock in the soil, estimated up to one meter depth based on profile data from the basin of Rio Turvo, was around 4.900.000 tons, considering the depth of 1 meter. The relationship between the occurrence of soils and relief attributes, derived from DEM, were decisive in the delineation of soil mapping units in the region studied, which certainly ensured a better performance of the digital map production. Although extrapolation to other regions should be taken with caution, the results indicate that the ANNs were able to map the soils in the Bacia do Rio Turvo Sujo in an automated and appropriate manner, with more detailed results than the traditional procedure. In the conventional classification, it is difficult to perfectly integrate a wide range of information from different sources and in this respect, the ANNs result in helping to obtain a final product of better quality. Obviously, this data processing will not be able to replace human hands and minds in the survey procedures and soil classification, but should be taken as a tool to obtain results increasingly closer to reality.
publishDate 2009
dc.date.issued.fl_str_mv 2009-03-09
dc.date.available.fl_str_mv 2012-04-13
2015-03-26T13:53:20Z
dc.date.accessioned.fl_str_mv 2015-03-26T13:53:20Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.citation.fl_str_mv MELO, Leonardo Vaz de. The use of artificial neural networks in the soil mapping in Bacia do Rio Turvo Sujo - Viçosa MG. 2009. 95 f. Dissertação (Mestrado em Fertilidade do solo e nutrição de plantas; Gênese, Morfologia e Classificação, Mineralogia, Química,) - Universidade Federal de Viçosa, Viçosa, 2009.
dc.identifier.uri.fl_str_mv http://locus.ufv.br/handle/123456789/5473
identifier_str_mv MELO, Leonardo Vaz de. The use of artificial neural networks in the soil mapping in Bacia do Rio Turvo Sujo - Viçosa MG. 2009. 95 f. Dissertação (Mestrado em Fertilidade do solo e nutrição de plantas; Gênese, Morfologia e Classificação, Mineralogia, Química,) - Universidade Federal de Viçosa, Viçosa, 2009.
url http://locus.ufv.br/handle/123456789/5473
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 Viçosa
dc.publisher.program.fl_str_mv Mestrado em Solos e Nutrição de Plantas
dc.publisher.initials.fl_str_mv UFV
dc.publisher.country.fl_str_mv BR
dc.publisher.department.fl_str_mv Fertilidade do solo e nutrição de plantas; Gênese, Morfologia e Classificação, Mineralogia, Química,
publisher.none.fl_str_mv Universidade Federal de Viçosa
dc.source.none.fl_str_mv reponame:LOCUS Repositório Institucional da UFV
instname:Universidade Federal de Viçosa (UFV)
instacron:UFV
instname_str Universidade Federal de Viçosa (UFV)
instacron_str UFV
institution UFV
reponame_str LOCUS Repositório Institucional da UFV
collection LOCUS Repositório Institucional da UFV
bitstream.url.fl_str_mv https://locus.ufv.br//bitstream/123456789/5473/1/texto%20completo.pdf
https://locus.ufv.br//bitstream/123456789/5473/2/texto%20completo.pdf.txt
https://locus.ufv.br//bitstream/123456789/5473/3/texto%20completo.pdf.jpg
bitstream.checksum.fl_str_mv 4b02f31363027fef3af5dffa77ba3d07
30a2e78a779cb49f7bcbb7edac4aa242
541b118d70b065b582fc309a0bb577c2
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
repository.name.fl_str_mv LOCUS Repositório Institucional da UFV - Universidade Federal de Viçosa (UFV)
repository.mail.fl_str_mv fabiojreis@ufv.br
_version_ 1801213132647956480