Determination of crop coefficient (kc) based on machine learning NDVI time series models
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10071/27012 |
Resumo: | This dissertation aims to meet the required challenge of providing reflectance-based crop coefficient models to reduce water consumption in agriculture irrigation. In this work, 6 different models were created for each crop by using normalized difference vegetation index (NDVI) to estimate crop coefficients (Kc) for maize, tomato, potato and sunflower for Lezíria do Tejo region combining different pre-selection methods of time series and mean and k-means to create new time series and use linear and polynomial regression to fit the new generate time series with theoretical Kc curves to use these models to determine Kc in this region. These models’ performance was assessed using the coefficient of determination (R2), root mean square error (RMSE) and a visual inspection of test set predictions. The results show that the Kc-NDVI models created were able to capture the theoretical curves of Kc well, and the use of a pre-selection of time series, mean and k-means for these crops is useful to capture the curves of the crop coefficients since some of the best results obtained were when they were used. The best methodologies depend on each crop; no one is globally better than the others. The results shown are promising and can be seen as potential methods to better determine crop coefficients and the models are suitable for their use at least in the region of this study. |
id |
RCAP_6b4020cb75e7ed936c49aa9419cc5cdd |
---|---|
oai_identifier_str |
oai:repositorio.iscte-iul.pt:10071/27012 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Determination of crop coefficient (kc) based on machine learning NDVI time series modelsNDVIKcMachine learningSéries temporais -- Time seriesTeledetecção -- Remote sensingThis dissertation aims to meet the required challenge of providing reflectance-based crop coefficient models to reduce water consumption in agriculture irrigation. In this work, 6 different models were created for each crop by using normalized difference vegetation index (NDVI) to estimate crop coefficients (Kc) for maize, tomato, potato and sunflower for Lezíria do Tejo region combining different pre-selection methods of time series and mean and k-means to create new time series and use linear and polynomial regression to fit the new generate time series with theoretical Kc curves to use these models to determine Kc in this region. These models’ performance was assessed using the coefficient of determination (R2), root mean square error (RMSE) and a visual inspection of test set predictions. The results show that the Kc-NDVI models created were able to capture the theoretical curves of Kc well, and the use of a pre-selection of time series, mean and k-means for these crops is useful to capture the curves of the crop coefficients since some of the best results obtained were when they were used. The best methodologies depend on each crop; no one is globally better than the others. The results shown are promising and can be seen as potential methods to better determine crop coefficients and the models are suitable for their use at least in the region of this study.O objetivo da dissertação é enfrentar o desafio necessário de fornecer modelos de coeficiente de cultura (Kc) baseados em refletância para reduzir o consumo de água na irrigação agrícola. Neste trabalho, foram criados 6 modelos diferentes para cada uma das culturas usando o índice de vegetação por diferença normalizada (NDVI) para estimar os coeficientes de cultura para milho, tomate, batata e girassol na região da Lezíria do Tejo combinando diferentes métodos de pré-seleção de séries temporais e usando a média e k-means para criar novas séries temporais, bem como usar regressão linear e polinomial para ajustar as novas séries temporais geradas com curvas Kc teóricas com o objetivo de usar esses modelos para determinar Kc nesta região. O desempenho desses modelos foi avaliado usando o coeficiente de determinação (R2), a raiz quadrada do erro quadrático médio (RMSE) e uma inspeção visual das previsões no conjunto de teste. Os resultados mostram que os modelos Kc-NDVI criados conseguiram capturar bem as curvas teóricas de Kc, bem como o uso de uma pré-seleção das séries temporais, média e k-means para estas culturas são úteis para capturar as curvas dos coeficientes de cultura, uma vez que alguns dos melhores resultados obtidos foram quando estas foram utilizadas. As melhores metodologias dependem de cada cultura e não existe uma que seja globalmente melhor. Estes resultados obtidos são promissores e podem ser vistos como métodos potenciais para melhor determinar os coeficientes de cultura e os modelos são adequados para seu uso pelo menos na região estudada.2023-01-05T11:40:11Z2022-12-09T00:00:00Z2022-12-092022-10info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10071/27012TID:203134737engDuarte, Guilherme Filipe Toméinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-09T17:49:44Zoai:repositorio.iscte-iul.pt:10071/27012Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:24:27.307801Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Determination of crop coefficient (kc) based on machine learning NDVI time series models |
title |
Determination of crop coefficient (kc) based on machine learning NDVI time series models |
spellingShingle |
Determination of crop coefficient (kc) based on machine learning NDVI time series models Duarte, Guilherme Filipe Tomé NDVI Kc Machine learning Séries temporais -- Time series Teledetecção -- Remote sensing |
title_short |
Determination of crop coefficient (kc) based on machine learning NDVI time series models |
title_full |
Determination of crop coefficient (kc) based on machine learning NDVI time series models |
title_fullStr |
Determination of crop coefficient (kc) based on machine learning NDVI time series models |
title_full_unstemmed |
Determination of crop coefficient (kc) based on machine learning NDVI time series models |
title_sort |
Determination of crop coefficient (kc) based on machine learning NDVI time series models |
author |
Duarte, Guilherme Filipe Tomé |
author_facet |
Duarte, Guilherme Filipe Tomé |
author_role |
author |
dc.contributor.author.fl_str_mv |
Duarte, Guilherme Filipe Tomé |
dc.subject.por.fl_str_mv |
NDVI Kc Machine learning Séries temporais -- Time series Teledetecção -- Remote sensing |
topic |
NDVI Kc Machine learning Séries temporais -- Time series Teledetecção -- Remote sensing |
description |
This dissertation aims to meet the required challenge of providing reflectance-based crop coefficient models to reduce water consumption in agriculture irrigation. In this work, 6 different models were created for each crop by using normalized difference vegetation index (NDVI) to estimate crop coefficients (Kc) for maize, tomato, potato and sunflower for Lezíria do Tejo region combining different pre-selection methods of time series and mean and k-means to create new time series and use linear and polynomial regression to fit the new generate time series with theoretical Kc curves to use these models to determine Kc in this region. These models’ performance was assessed using the coefficient of determination (R2), root mean square error (RMSE) and a visual inspection of test set predictions. The results show that the Kc-NDVI models created were able to capture the theoretical curves of Kc well, and the use of a pre-selection of time series, mean and k-means for these crops is useful to capture the curves of the crop coefficients since some of the best results obtained were when they were used. The best methodologies depend on each crop; no one is globally better than the others. The results shown are promising and can be seen as potential methods to better determine crop coefficients and the models are suitable for their use at least in the region of this study. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-12-09T00:00:00Z 2022-12-09 2022-10 2023-01-05T11:40:11Z |
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.uri.fl_str_mv |
http://hdl.handle.net/10071/27012 TID:203134737 |
url |
http://hdl.handle.net/10071/27012 |
identifier_str_mv |
TID:203134737 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
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.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134806882123776 |