Uso de diferentes metodologias na geração de funções de pedotransferencia para a retenção de água em solos do Rio Grande do Sul
Autor(a) principal: | |
---|---|
Data de Publicação: | 2013 |
Tipo de documento: | Tese |
Idioma: | por |
Título da fonte: | Manancial - Repositório Digital da UFSM |
Texto Completo: | http://repositorio.ufsm.br/handle/1/3601 |
Resumo: | Studies on the dynamics of water in the soil-plant-atmosphere such as water availability cultures infiltration drainage and movement of solutes into the soil, require knowledge of the relation between the water content in soil matric potential and represented by retention curve water. However, its implementation is laborious, requires considerable time and cost. An alternative is your estimate through statistical equations called pedotransfer functions (PTFs). The aim of this study was to generate PTFs for the different soil classes in the state of Rio Grande do Sul, through prediction methodologies. To develop the work we used data available in the literature, with values of hydro-physical characteristics and mineralogical characteristics of soils of the State, to estimate values of soil unit under different stresses. In possession of the database was conducted subdivision thereof, in different textural classes identified in the state in an attempt to improve the predictive ability of pedofunctions, forming more homogeneous subsets. The development of PTFs was from two modeling methods: (i) multiple linear regression (MLR) and (ii) artificial neural networks (ANNs). For the development of PTFs first methodology was used the "stepwise" (SAS, 1997). The PTFs generated from ANNs were implemented through the multilayer perceptron with backpropagation algorithm and Levenberg-Marquardt optimization. Each network is trained by varying the number of neurons in the input layer and the number of neurons in the hidden layer. The output variable was water content in soil matric potentials of 0, -6, -10, -33, -100, -500 and -1500 kPa. For each architecture, the network was trained several times, picking up training at the end of the architecture with lower mean relative error and lower variance in relation to the validation data. The efficiency of PTFs were analyzed graphically by the ratio 1:1 between data versus the observed and estimated by means of the following statistical indicators: correlation coefficient (r); concordance index Wilmont (c); coefficient of determination (R2) and performance index (id). The results showed that the more homogeneous is the data of the variables that compose the PTFs, the greater the precision in estimating the water retention in the soil, for the same. The network architecture consists of 4 inputs, showed high accuracy in the estimation of variables. The PTFs developed by ANNs outperformed the predictive ability of the standard method (MLR). Thus, the estimate of the retention curve of soil water by means of ANNs trained by classes textures, presents itself as a subsidy techniques adopted in irrigated agriculture. |
id |
UFSM-20_941ff7c0fef7856048de5252fab2636e |
---|---|
oai_identifier_str |
oai:repositorio.ufsm.br:1/3601 |
network_acronym_str |
UFSM-20 |
network_name_str |
Manancial - Repositório Digital da UFSM |
repository_id_str |
3913 |
spelling |
2013-07-312013-07-312013-02-01SOARES, Fátima Cibéle. USE OF DIFFERENT METHODOLOGIES IN GENERATION PEDOTRANSFER FUNCTIONS FOR WATER RETENTION IN SOILS OF RIO GRANDE DO SUL. 2013. 200 f. Tese (Doutorado em Engenharia Agrícola) - Universidade Federal de Santa Maria, Santa Maria, 2013.http://repositorio.ufsm.br/handle/1/3601Studies on the dynamics of water in the soil-plant-atmosphere such as water availability cultures infiltration drainage and movement of solutes into the soil, require knowledge of the relation between the water content in soil matric potential and represented by retention curve water. However, its implementation is laborious, requires considerable time and cost. An alternative is your estimate through statistical equations called pedotransfer functions (PTFs). The aim of this study was to generate PTFs for the different soil classes in the state of Rio Grande do Sul, through prediction methodologies. To develop the work we used data available in the literature, with values of hydro-physical characteristics and mineralogical characteristics of soils of the State, to estimate values of soil unit under different stresses. In possession of the database was conducted subdivision thereof, in different textural classes identified in the state in an attempt to improve the predictive ability of pedofunctions, forming more homogeneous subsets. The development of PTFs was from two modeling methods: (i) multiple linear regression (MLR) and (ii) artificial neural networks (ANNs). For the development of PTFs first methodology was used the "stepwise" (SAS, 1997). The PTFs generated from ANNs were implemented through the multilayer perceptron with backpropagation algorithm and Levenberg-Marquardt optimization. Each network is trained by varying the number of neurons in the input layer and the number of neurons in the hidden layer. The output variable was water content in soil matric potentials of 0, -6, -10, -33, -100, -500 and -1500 kPa. For each architecture, the network was trained several times, picking up training at the end of the architecture with lower mean relative error and lower variance in relation to the validation data. The efficiency of PTFs were analyzed graphically by the ratio 1:1 between data versus the observed and estimated by means of the following statistical indicators: correlation coefficient (r); concordance index Wilmont (c); coefficient of determination (R2) and performance index (id). The results showed that the more homogeneous is the data of the variables that compose the PTFs, the greater the precision in estimating the water retention in the soil, for the same. The network architecture consists of 4 inputs, showed high accuracy in the estimation of variables. The PTFs developed by ANNs outperformed the predictive ability of the standard method (MLR). Thus, the estimate of the retention curve of soil water by means of ANNs trained by classes textures, presents itself as a subsidy techniques adopted in irrigated agriculture.Estudos que envolvem a dinâmica da água no sistema solo-planta-atmosfera tais como disponibilidade de água as culturas, infiltração, drenagem e movimento de solutos no solo, necessitam do conhecimento da relação entre o conteúdo de água no solo e o potencial matricial, representada pela curva de retenção de água. No entanto, sua execução é laboriosa, demanda considerável tempo e custos. Uma alternativa é sua estimativa através de equações estatísticas denominadas Funções de Pedotransferência (FPTs). O objetivo deste estudo foi gerar FPTs para as diferentes classes de solos do Estado do Rio Grande do Sul, por meio de metodologias de predição. Para desenvolver o trabalho foram utilizados dados, disponíveis na literatura, com valores de características físico-hídricas e mineralógicas, de solos do Estado, para estimar valores de umidade de solo, sob diferentes tensões. De posse do banco de dados foi realizado a subdivisão do mesmo, nas diferentes classes texturais identificada no Estado, na tentativa de melhorar a capacidade preditiva das pedofunções, formando subconjuntos mais homogêneos. O desenvolvimento das FPTs foi a partir de dois métodos de modelagem: (i) regressão linear múltipla (RLM) e (ii) redes neurais artificiais (RNAs). Para o desenvolvimento das FPTs pela primeira metodologia, foi utilizada a opção stepwise (SAS, 1997). As FPTs geradas a partir de RNAs, foram implementadas através do perceptron multicamadas com algoritmo backpropagation e otimização Levenberg-Marquardt. As redes foram treinadas variando-se o número de neurônios na camada de entrada e número de neurônios na camada escondida. A variável de saída foi conteúdo de água no solo nos potenciais matriciais de 0, -6, -10, -33, -100, -500 e -1500 kPa. Para cada arquitetura, a rede foi treinada diversas vezes, escolhendo-se no final do treinamento a arquitetura com menor erro relativo médio e menor variância em relação aos dados de validação. A eficiência das FPTs foram analisadas graficamente pela relação 1:1, entre os dados estimados versus os observados e, por meio dos seguintes indicadores estatísticos: coeficiente de correlação (r); índice de concordância de Wilmont (c); coeficiente de determinação (R2) e índice de desempenho (id). Os resultados mostraram que quanto mais homogêneos são os dados das variáveis que compõem as FPTs, maior é a precisão na estimativa da retenção de água no solo, pelas mesmas. As redes de arquitetura formada por 4 entradas, apresentaram elevada precisão na estimativa das variáveis. As FPTs desenvolvidas por RNAs superaram a capacidade preditiva do método padrão (RLM). Deste modo, a estimativa da curva de retenção de água no solo, por meio das RNAs treinadas por classes texturais, apresenta-se como um subsídio as técnicas adotadas na agricultura irrigada. Palavras-chave: Pedofunções. Umidade do solo. Potencial matricial. Inteligência artificialCoordenação de Aperfeiçoamento de Pessoal de Nível Superiorapplication/pdfporUniversidade Federal de Santa MariaPrograma de Pós-Graduação em Engenharia AgrícolaUFSMBREngenharia AgrícolaPedofunçõesUmidade do soloPotencial matricialInteligência artificialPedofunctionsSoil moisturePotential matrixArtificial intelligenceCNPQ::CIENCIAS AGRARIAS::ENGENHARIA AGRICOLAUso de diferentes metodologias na geração de funções de pedotransferencia para a retenção de água em solos do Rio Grande do SulUse of different methodologies in generation pedotransfer functions for water retention in soils of Rio Grande do Sulinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisRobaina, Adroaldo Diashttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4721472P9Peiter, Márcia Xavierhttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4790584P6Gomes, Ana Carla dos Santoshttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4774681A7Parizi, Ana Rita Costenarohttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4771175T1Zamberlan, João Fernandohttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4125067U8Schons, Ricardo Luishttp://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4799021D3http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4756138Z6Soares, Fátima Cibéle500300000008400300300300300300300300a461031e-e4dd-4408-ac4e-e2eea463cc610e5e02be-a074-4b47-a099-1c36d475cdb0296314ed-e354-4440-b25a-85ac23c11117e4240a00-0dd7-4422-9454-940b6b1b6f75d7863e73-bc55-4751-866c-bc07b63624d9dbddad2b-55bd-4c1a-b374-e1a9ea39c0ba7d1e571a-da90-4fe7-8d75-e4ac591a55e0info:eu-repo/semantics/openAccessreponame:Manancial - Repositório Digital da UFSMinstname:Universidade Federal de Santa Maria (UFSM)instacron:UFSMORIGINALSOARES, FATIMA CIBELE.pdfapplication/pdf3361819http://repositorio.ufsm.br/bitstream/1/3601/1/SOARES%2c%20FATIMA%20CIBELE.pdf238d5c88daf09a5b88e169778ba8203aMD51TEXTSOARES, FATIMA CIBELE.pdf.txtSOARES, FATIMA CIBELE.pdf.txtExtracted texttext/plain362996http://repositorio.ufsm.br/bitstream/1/3601/2/SOARES%2c%20FATIMA%20CIBELE.pdf.txt94c1abebd000266a9bf9a776d58aa843MD52THUMBNAILSOARES, FATIMA CIBELE.pdf.jpgSOARES, FATIMA CIBELE.pdf.jpgIM Thumbnailimage/jpeg5044http://repositorio.ufsm.br/bitstream/1/3601/3/SOARES%2c%20FATIMA%20CIBELE.pdf.jpgcefce58a7601127beed9516bd3190c13MD531/36012022-01-07 09:34:33.331oai:repositorio.ufsm.br:1/3601Repositório Institucionalhttp://repositorio.ufsm.br/PUBhttp://repositorio.ufsm.br/oai/requestopendoar:39132022-01-07T12:34:33Manancial - Repositório Digital da UFSM - Universidade Federal de Santa Maria (UFSM)false |
dc.title.por.fl_str_mv |
Uso de diferentes metodologias na geração de funções de pedotransferencia para a retenção de água em solos do Rio Grande do Sul |
dc.title.alternative.eng.fl_str_mv |
Use of different methodologies in generation pedotransfer functions for water retention in soils of Rio Grande do Sul |
title |
Uso de diferentes metodologias na geração de funções de pedotransferencia para a retenção de água em solos do Rio Grande do Sul |
spellingShingle |
Uso de diferentes metodologias na geração de funções de pedotransferencia para a retenção de água em solos do Rio Grande do Sul Soares, Fátima Cibéle Pedofunções Umidade do solo Potencial matricial Inteligência artificial Pedofunctions Soil moisture Potential matrix Artificial intelligence CNPQ::CIENCIAS AGRARIAS::ENGENHARIA AGRICOLA |
title_short |
Uso de diferentes metodologias na geração de funções de pedotransferencia para a retenção de água em solos do Rio Grande do Sul |
title_full |
Uso de diferentes metodologias na geração de funções de pedotransferencia para a retenção de água em solos do Rio Grande do Sul |
title_fullStr |
Uso de diferentes metodologias na geração de funções de pedotransferencia para a retenção de água em solos do Rio Grande do Sul |
title_full_unstemmed |
Uso de diferentes metodologias na geração de funções de pedotransferencia para a retenção de água em solos do Rio Grande do Sul |
title_sort |
Uso de diferentes metodologias na geração de funções de pedotransferencia para a retenção de água em solos do Rio Grande do Sul |
author |
Soares, Fátima Cibéle |
author_facet |
Soares, Fátima Cibéle |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Robaina, Adroaldo Dias |
dc.contributor.advisor1Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4721472P9 |
dc.contributor.advisor-co1.fl_str_mv |
Peiter, Márcia Xavier |
dc.contributor.advisor-co1Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4790584P6 |
dc.contributor.referee1.fl_str_mv |
Gomes, Ana Carla dos Santos |
dc.contributor.referee1Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4774681A7 |
dc.contributor.referee2.fl_str_mv |
Parizi, Ana Rita Costenaro |
dc.contributor.referee2Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4771175T1 |
dc.contributor.referee3.fl_str_mv |
Zamberlan, João Fernando |
dc.contributor.referee3Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4125067U8 |
dc.contributor.referee4.fl_str_mv |
Schons, Ricardo Luis |
dc.contributor.referee4Lattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4799021D3 |
dc.contributor.authorLattes.fl_str_mv |
http://buscatextual.cnpq.br/buscatextual/visualizacv.do?id=K4756138Z6 |
dc.contributor.author.fl_str_mv |
Soares, Fátima Cibéle |
contributor_str_mv |
Robaina, Adroaldo Dias Peiter, Márcia Xavier Gomes, Ana Carla dos Santos Parizi, Ana Rita Costenaro Zamberlan, João Fernando Schons, Ricardo Luis |
dc.subject.por.fl_str_mv |
Pedofunções Umidade do solo Potencial matricial Inteligência artificial |
topic |
Pedofunções Umidade do solo Potencial matricial Inteligência artificial Pedofunctions Soil moisture Potential matrix Artificial intelligence CNPQ::CIENCIAS AGRARIAS::ENGENHARIA AGRICOLA |
dc.subject.eng.fl_str_mv |
Pedofunctions Soil moisture Potential matrix Artificial intelligence |
dc.subject.cnpq.fl_str_mv |
CNPQ::CIENCIAS AGRARIAS::ENGENHARIA AGRICOLA |
description |
Studies on the dynamics of water in the soil-plant-atmosphere such as water availability cultures infiltration drainage and movement of solutes into the soil, require knowledge of the relation between the water content in soil matric potential and represented by retention curve water. However, its implementation is laborious, requires considerable time and cost. An alternative is your estimate through statistical equations called pedotransfer functions (PTFs). The aim of this study was to generate PTFs for the different soil classes in the state of Rio Grande do Sul, through prediction methodologies. To develop the work we used data available in the literature, with values of hydro-physical characteristics and mineralogical characteristics of soils of the State, to estimate values of soil unit under different stresses. In possession of the database was conducted subdivision thereof, in different textural classes identified in the state in an attempt to improve the predictive ability of pedofunctions, forming more homogeneous subsets. The development of PTFs was from two modeling methods: (i) multiple linear regression (MLR) and (ii) artificial neural networks (ANNs). For the development of PTFs first methodology was used the "stepwise" (SAS, 1997). The PTFs generated from ANNs were implemented through the multilayer perceptron with backpropagation algorithm and Levenberg-Marquardt optimization. Each network is trained by varying the number of neurons in the input layer and the number of neurons in the hidden layer. The output variable was water content in soil matric potentials of 0, -6, -10, -33, -100, -500 and -1500 kPa. For each architecture, the network was trained several times, picking up training at the end of the architecture with lower mean relative error and lower variance in relation to the validation data. The efficiency of PTFs were analyzed graphically by the ratio 1:1 between data versus the observed and estimated by means of the following statistical indicators: correlation coefficient (r); concordance index Wilmont (c); coefficient of determination (R2) and performance index (id). The results showed that the more homogeneous is the data of the variables that compose the PTFs, the greater the precision in estimating the water retention in the soil, for the same. The network architecture consists of 4 inputs, showed high accuracy in the estimation of variables. The PTFs developed by ANNs outperformed the predictive ability of the standard method (MLR). Thus, the estimate of the retention curve of soil water by means of ANNs trained by classes textures, presents itself as a subsidy techniques adopted in irrigated agriculture. |
publishDate |
2013 |
dc.date.accessioned.fl_str_mv |
2013-07-31 |
dc.date.available.fl_str_mv |
2013-07-31 |
dc.date.issued.fl_str_mv |
2013-02-01 |
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.citation.fl_str_mv |
SOARES, Fátima Cibéle. USE OF DIFFERENT METHODOLOGIES IN GENERATION PEDOTRANSFER FUNCTIONS FOR WATER RETENTION IN SOILS OF RIO GRANDE DO SUL. 2013. 200 f. Tese (Doutorado em Engenharia Agrícola) - Universidade Federal de Santa Maria, Santa Maria, 2013. |
dc.identifier.uri.fl_str_mv |
http://repositorio.ufsm.br/handle/1/3601 |
identifier_str_mv |
SOARES, Fátima Cibéle. USE OF DIFFERENT METHODOLOGIES IN GENERATION PEDOTRANSFER FUNCTIONS FOR WATER RETENTION IN SOILS OF RIO GRANDE DO SUL. 2013. 200 f. Tese (Doutorado em Engenharia Agrícola) - Universidade Federal de Santa Maria, Santa Maria, 2013. |
url |
http://repositorio.ufsm.br/handle/1/3601 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.cnpq.fl_str_mv |
500300000008 |
dc.relation.confidence.fl_str_mv |
400 300 300 300 300 300 300 300 |
dc.relation.authority.fl_str_mv |
a461031e-e4dd-4408-ac4e-e2eea463cc61 0e5e02be-a074-4b47-a099-1c36d475cdb0 296314ed-e354-4440-b25a-85ac23c11117 e4240a00-0dd7-4422-9454-940b6b1b6f75 d7863e73-bc55-4751-866c-bc07b63624d9 dbddad2b-55bd-4c1a-b374-e1a9ea39c0ba 7d1e571a-da90-4fe7-8d75-e4ac591a55e0 |
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 Santa Maria |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Engenharia Agrícola |
dc.publisher.initials.fl_str_mv |
UFSM |
dc.publisher.country.fl_str_mv |
BR |
dc.publisher.department.fl_str_mv |
Engenharia Agrícola |
publisher.none.fl_str_mv |
Universidade Federal de Santa Maria |
dc.source.none.fl_str_mv |
reponame:Manancial - Repositório Digital da UFSM instname:Universidade Federal de Santa Maria (UFSM) instacron:UFSM |
instname_str |
Universidade Federal de Santa Maria (UFSM) |
instacron_str |
UFSM |
institution |
UFSM |
reponame_str |
Manancial - Repositório Digital da UFSM |
collection |
Manancial - Repositório Digital da UFSM |
bitstream.url.fl_str_mv |
http://repositorio.ufsm.br/bitstream/1/3601/1/SOARES%2c%20FATIMA%20CIBELE.pdf http://repositorio.ufsm.br/bitstream/1/3601/2/SOARES%2c%20FATIMA%20CIBELE.pdf.txt http://repositorio.ufsm.br/bitstream/1/3601/3/SOARES%2c%20FATIMA%20CIBELE.pdf.jpg |
bitstream.checksum.fl_str_mv |
238d5c88daf09a5b88e169778ba8203a 94c1abebd000266a9bf9a776d58aa843 cefce58a7601127beed9516bd3190c13 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Manancial - Repositório Digital da UFSM - Universidade Federal de Santa Maria (UFSM) |
repository.mail.fl_str_mv |
|
_version_ |
1794523806997413888 |