High-resolution data for mapping the spatio-temporal variability of sugarcane fields

Detalhes bibliográficos
Autor(a) principal: Canata, Tatiana Fernanda
Data de Publicação: 2021
Tipo de documento: Tese
Idioma: eng
Título da fonte: Biblioteca Digital de Teses e Dissertações da USP
Texto Completo: https://www.teses.usp.br/teses/disponiveis/11/11152/tde-15092021-120624/
Resumo: Data-driven solutions have been more common in agriculture, mainly, with the progress of technology to optimize the operations at the field. Precision agriculture and remote sensing techniques have enabled the data acquisition of agronomical variables and more accurate diagnostics than using traditional methods. The crop monitoring for sugarcane area is commonly associated with regional scale or classification of sugarcane areas based on satellite imagery. Some alternative techniques can support the assessment of the spatio-temporal variability of the fields using three-dimensional (3D) sensing data provided by LiDAR (Light Detection and Ranging) technology, which have contributed to the site-specific crop management considering the canopy height or volume variation. Researchers have applied LiDAR data and aerial images in small areas, which indicated the requirement of understanding better the data acquisition and processing for large-scale applications, such as sugarcane areas in Brazil. This study aims to investigate the potential of 3D sensing data and satellite imagery to map the spatio-temporal variability of sugarcane fields before harvesting. Chapters 1 and 2 introduce the topic of the thesis and highlight the state of the art of the concepts used in the research. Chapter 3 describes the applied methods for data processing of 3D sensing data and aerial images in order to assess the spatio-temporal variability of a commercial sugarcane field. The sugarcane yield map was generated by a sensor-system that measures the mass flow based on the difference of hydraulic pressure of the chopper system in the harvester. The plant height of sugarcane fields was obtained with an ALS (Airborne Laser Scanning) in the final crop production cycle for two consecutive seasons. The point cloud generated, followed by the data filtering, enabled to obtain the canopy height model (CHM) as an information to investigate the association between the spatial variation of crop height and the yield map. A moderate relationship was found between the CHM and the yield map, which demonstrated the potential of high-resolution data to identify the spatial variability at the field level. Chapter 4 explores the use of orbital images for sugarcane yield mapping using reflectance data and vegetation index over the crop cycle for three consecutive crop seasons. The yield prediction models were developed by integrating satellite images, machine learning and multiple linear regression. The regression using Random Forest (RF) showed greater accuracy, since the non-linearity of the dataset was observed, and the spectral bands showed a lower error in estimation of yield. Crop vigor mapping using time-series analysis of satellite imagery supports the identification of the spatial variability of sugarcane fields. The results of this research demonstrated the potential applications of high-resolution data for guiding complementary diagnostics and local interventions in agricultural systems, since it indicates the crop height or vigor variation in large-scale before harvesting.
id USP_4e7bbd7667b50bf6d6f6793d94074bda
oai_identifier_str oai:teses.usp.br:tde-15092021-120624
network_acronym_str USP
network_name_str Biblioteca Digital de Teses e Dissertações da USP
repository_id_str 2721
spelling High-resolution data for mapping the spatio-temporal variability of sugarcane fieldsDados de alta resolução para o mapeamento da variabilidade espaço-temporal de talhões de cana-de-açúcarAgricultura de precisãoÍndices de vegetaçãoNuvem de pontosPoint cloudPrecision agricultureRemote sensingSensoriamento remotoVegetation indexData-driven solutions have been more common in agriculture, mainly, with the progress of technology to optimize the operations at the field. Precision agriculture and remote sensing techniques have enabled the data acquisition of agronomical variables and more accurate diagnostics than using traditional methods. The crop monitoring for sugarcane area is commonly associated with regional scale or classification of sugarcane areas based on satellite imagery. Some alternative techniques can support the assessment of the spatio-temporal variability of the fields using three-dimensional (3D) sensing data provided by LiDAR (Light Detection and Ranging) technology, which have contributed to the site-specific crop management considering the canopy height or volume variation. Researchers have applied LiDAR data and aerial images in small areas, which indicated the requirement of understanding better the data acquisition and processing for large-scale applications, such as sugarcane areas in Brazil. This study aims to investigate the potential of 3D sensing data and satellite imagery to map the spatio-temporal variability of sugarcane fields before harvesting. Chapters 1 and 2 introduce the topic of the thesis and highlight the state of the art of the concepts used in the research. Chapter 3 describes the applied methods for data processing of 3D sensing data and aerial images in order to assess the spatio-temporal variability of a commercial sugarcane field. The sugarcane yield map was generated by a sensor-system that measures the mass flow based on the difference of hydraulic pressure of the chopper system in the harvester. The plant height of sugarcane fields was obtained with an ALS (Airborne Laser Scanning) in the final crop production cycle for two consecutive seasons. The point cloud generated, followed by the data filtering, enabled to obtain the canopy height model (CHM) as an information to investigate the association between the spatial variation of crop height and the yield map. A moderate relationship was found between the CHM and the yield map, which demonstrated the potential of high-resolution data to identify the spatial variability at the field level. Chapter 4 explores the use of orbital images for sugarcane yield mapping using reflectance data and vegetation index over the crop cycle for three consecutive crop seasons. The yield prediction models were developed by integrating satellite images, machine learning and multiple linear regression. The regression using Random Forest (RF) showed greater accuracy, since the non-linearity of the dataset was observed, and the spectral bands showed a lower error in estimation of yield. Crop vigor mapping using time-series analysis of satellite imagery supports the identification of the spatial variability of sugarcane fields. The results of this research demonstrated the potential applications of high-resolution data for guiding complementary diagnostics and local interventions in agricultural systems, since it indicates the crop height or vigor variation in large-scale before harvesting.As soluções direcionadas por dados têm sido mais comuns na agricultura, principalmente, com o avanço da tecnologia para otimizar as operações no campo. As técnicas de agricultura de precisão e sensoriamento remoto tem permitido a aquisição de dados de variáveis agronômicas e diagnósticos mais precisos do que por meio dos métodos tradicionais. O monitoramento de áreas de cana-de-açúcar é comumente associado à escala regional ou a classificação de áreas de cana-de-açúcar baseada em imagens de satélite. Algumas técnicas podem apoiar a avaliação da variabilidade espaço-temporal dos talhões utilizando dados tridimensionais (3D) a partir da tecnologia LiDAR (Light Detection and Ranging), a qual tem contribuído no manejo específico da cultura considerando a variação da altura ou volume de plantas. Os pesquisadores têm aplicado os dados LiDAR e imagens aéreas em pequenas áreas, o que indica a necessidade de se compreender melhor a aquisição e o processamento de dados para as aplicações em larga escala, como nas áreas de cana-de-açúcar no Brasil. Este estudo tem como objetivo investigar o potencial dos dados 3D e imagens de satélite para mapear a variabilidade espaço-temporal dos talhões de cana-de-açúcar previamente a colheita. Os Capítulos 1 e 2 introduzem o tema da tese e destacam o estado da arte dos conceitos utilizados na pesquisa. No Capítulo 3 são descritos os métodos aplicados no processamento de dados 3D e imagens aéreas para avaliar a variabilidade espaço-temporal de uma área comercial de cana-de-açúcar. O mapa de produtividade foi gerado por um sistema-sensor que mede o fluxo de massa de acordo com a diferença da pressão hidráulica do picador na colhedora. A altura de plantas foi obtida com ALS (Airborne Laser Scanning) no ciclo final de produção da cultura por duas safras consecutivas. A nuvem de pontos gerada, seguida da filtragem de dados, possibilitou a obtenção do modelo de altura do dossel (CHM) como uma informação para investigar a associação entre a variação espacial da altura de plantas e o mapa de produtividade. Foi encontrada uma relação moderada entre o CHM e o mapa de produtividade, o que demonstrou o potencial dos dados de alta resolução para identificar a variabilidade espacial ao nível de talhão. O Capítulo 4 explora o uso de imagens orbitais para o mapeamento da produtividade de cana-de-açúcar usando dados de refletância e índices de vegetação ao longo do ciclo da cultura por três safras consecutivas. Os modelos de predição de produtividade foram desenvolvidos integrando imagens de satélite, aprendizado de máquina e regressão linear múltipla. A regressão utilizando Random Forest (RF) apresentou maior acurácia, uma vez que foi observada a não-linearidade do conjunto de dados, e as bandas espectrais apresentaram um menor erro na estimativa de produtividade. O mapeamento do vigor da cultura por meio da análise de séries temporais de imagens de satélite auxiliaram na identificação da variabilidade espacial dos talhões de cana-de-açúcar. Os resultados desta pesquisa demonstram o potencial de aplicação dos dados de alta resolução para orientar diagnósticos complementares e intervenções locais nos sistemas agrícolas, uma vez que indicam a variação do porte e vigor de plantas em larga escala antes da colheita.Biblioteca Digitais de Teses e Dissertações da USPMolin, Jose PauloCanata, Tatiana Fernanda2021-07-13info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisapplication/pdfhttps://www.teses.usp.br/teses/disponiveis/11/11152/tde-15092021-120624/reponame:Biblioteca Digital de Teses e Dissertações da USPinstname:Universidade de São Paulo (USP)instacron:USPLiberar o conteúdo para acesso público.info:eu-repo/semantics/openAccesseng2021-09-16T13:05:02Zoai:teses.usp.br:tde-15092021-120624Biblioteca Digital de Teses e Dissertaçõeshttp://www.teses.usp.br/PUBhttp://www.teses.usp.br/cgi-bin/mtd2br.plvirginia@if.usp.br|| atendimento@aguia.usp.br||virginia@if.usp.bropendoar:27212021-09-16T13:05:02Biblioteca Digital de Teses e Dissertações da USP - Universidade de São Paulo (USP)false
dc.title.none.fl_str_mv High-resolution data for mapping the spatio-temporal variability of sugarcane fields
Dados de alta resolução para o mapeamento da variabilidade espaço-temporal de talhões de cana-de-açúcar
title High-resolution data for mapping the spatio-temporal variability of sugarcane fields
spellingShingle High-resolution data for mapping the spatio-temporal variability of sugarcane fields
Canata, Tatiana Fernanda
Agricultura de precisão
Índices de vegetação
Nuvem de pontos
Point cloud
Precision agriculture
Remote sensing
Sensoriamento remoto
Vegetation index
title_short High-resolution data for mapping the spatio-temporal variability of sugarcane fields
title_full High-resolution data for mapping the spatio-temporal variability of sugarcane fields
title_fullStr High-resolution data for mapping the spatio-temporal variability of sugarcane fields
title_full_unstemmed High-resolution data for mapping the spatio-temporal variability of sugarcane fields
title_sort High-resolution data for mapping the spatio-temporal variability of sugarcane fields
author Canata, Tatiana Fernanda
author_facet Canata, Tatiana Fernanda
author_role author
dc.contributor.none.fl_str_mv Molin, Jose Paulo
dc.contributor.author.fl_str_mv Canata, Tatiana Fernanda
dc.subject.por.fl_str_mv Agricultura de precisão
Índices de vegetação
Nuvem de pontos
Point cloud
Precision agriculture
Remote sensing
Sensoriamento remoto
Vegetation index
topic Agricultura de precisão
Índices de vegetação
Nuvem de pontos
Point cloud
Precision agriculture
Remote sensing
Sensoriamento remoto
Vegetation index
description Data-driven solutions have been more common in agriculture, mainly, with the progress of technology to optimize the operations at the field. Precision agriculture and remote sensing techniques have enabled the data acquisition of agronomical variables and more accurate diagnostics than using traditional methods. The crop monitoring for sugarcane area is commonly associated with regional scale or classification of sugarcane areas based on satellite imagery. Some alternative techniques can support the assessment of the spatio-temporal variability of the fields using three-dimensional (3D) sensing data provided by LiDAR (Light Detection and Ranging) technology, which have contributed to the site-specific crop management considering the canopy height or volume variation. Researchers have applied LiDAR data and aerial images in small areas, which indicated the requirement of understanding better the data acquisition and processing for large-scale applications, such as sugarcane areas in Brazil. This study aims to investigate the potential of 3D sensing data and satellite imagery to map the spatio-temporal variability of sugarcane fields before harvesting. Chapters 1 and 2 introduce the topic of the thesis and highlight the state of the art of the concepts used in the research. Chapter 3 describes the applied methods for data processing of 3D sensing data and aerial images in order to assess the spatio-temporal variability of a commercial sugarcane field. The sugarcane yield map was generated by a sensor-system that measures the mass flow based on the difference of hydraulic pressure of the chopper system in the harvester. The plant height of sugarcane fields was obtained with an ALS (Airborne Laser Scanning) in the final crop production cycle for two consecutive seasons. The point cloud generated, followed by the data filtering, enabled to obtain the canopy height model (CHM) as an information to investigate the association between the spatial variation of crop height and the yield map. A moderate relationship was found between the CHM and the yield map, which demonstrated the potential of high-resolution data to identify the spatial variability at the field level. Chapter 4 explores the use of orbital images for sugarcane yield mapping using reflectance data and vegetation index over the crop cycle for three consecutive crop seasons. The yield prediction models were developed by integrating satellite images, machine learning and multiple linear regression. The regression using Random Forest (RF) showed greater accuracy, since the non-linearity of the dataset was observed, and the spectral bands showed a lower error in estimation of yield. Crop vigor mapping using time-series analysis of satellite imagery supports the identification of the spatial variability of sugarcane fields. The results of this research demonstrated the potential applications of high-resolution data for guiding complementary diagnostics and local interventions in agricultural systems, since it indicates the crop height or vigor variation in large-scale before harvesting.
publishDate 2021
dc.date.none.fl_str_mv 2021-07-13
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 https://www.teses.usp.br/teses/disponiveis/11/11152/tde-15092021-120624/
url https://www.teses.usp.br/teses/disponiveis/11/11152/tde-15092021-120624/
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv
dc.rights.driver.fl_str_mv Liberar o conteúdo para acesso público.
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Liberar o conteúdo para acesso público.
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.coverage.none.fl_str_mv
dc.publisher.none.fl_str_mv Biblioteca Digitais de Teses e Dissertações da USP
publisher.none.fl_str_mv Biblioteca Digitais de Teses e Dissertações da USP
dc.source.none.fl_str_mv
reponame:Biblioteca Digital de Teses e Dissertações da USP
instname:Universidade de São Paulo (USP)
instacron:USP
instname_str Universidade de São Paulo (USP)
instacron_str USP
institution USP
reponame_str Biblioteca Digital de Teses e Dissertações da USP
collection Biblioteca Digital de Teses e Dissertações da USP
repository.name.fl_str_mv Biblioteca Digital de Teses e Dissertações da USP - Universidade de São Paulo (USP)
repository.mail.fl_str_mv virginia@if.usp.br|| atendimento@aguia.usp.br||virginia@if.usp.br
_version_ 1815257030906085376