Soil and satellite remote sensing variables importance using machine learning to predict cotton yield.
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
Texto Completo: | http://www.alice.cnptia.embrapa.br/alice/handle/doc/1156016 https://doi.org/10.1016/j.atech.2023.100292 |
Resumo: | Remote sensing (RS) in agriculture has been widely used for mapping soil, plant, and atmosphere attributes, as well as helping in the sustainable production of the crop by providing the possibility of application at variable rates and estimating the productivity of agricultural crops. In this way, proximal sensors used by RS help producers in decision-making to increase productivity. This research aims to identify the best feature importance ranking to the Random Forest Classifier to predict cotton yield and select which one best correlates with cotton yield. This work was developed in four commercial fields on a Newellton, LA, USA farm. We evaluated the cotton in different years as 2019, 2020, and 2021. The variables evaluated were: soil parameters, topographic indices, elevation derivatives, and orbital remote sensing. The soil sensor used was: GSSI Profiler EMP400 (soil electromagnetic induction sensor) at a frequency of 15 kHz, and the RS data were collected from satellite images from Sentinel 2 (passive sensor) and active sensor from LiDAR (Light Detection and Ranging). For training (70%) and validation (30%) of dataset results, Spearman correlation was used between sensors and cotton yield data, machine learning (Random Forest Classifier and Regressor - RFC and RFR). The metric parameters were the coefficient of determination (R2), the Mean Absolute Error (MAE), and the Root Mean Square Error (RMSE). This study found that profiler, Sentinel-2 (blue, red, and green), TPI, LiDAR, and RTK elevation show the best correlations to predicting cotton yield. |
id |
EMBR_ef6f78178ffead41c99c838aa596ce5e |
---|---|
oai_identifier_str |
oai:www.alice.cnptia.embrapa.br:doc/1156016 |
network_acronym_str |
EMBR |
network_name_str |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
repository_id_str |
2154 |
spelling |
Soil and satellite remote sensing variables importance using machine learning to predict cotton yield.Produção sustentávelSensores proximaisRandom forestSatellite imagerySustainable productionProximal sensorsInteligência artificialImagem de satéliteRSDecision treesÁrvores de decisãoAlgodãoEstrutura do SoloSensoriamento RemotoGossypium HirsutumArtificial intelligenceCottonSoil structureRemote sensingRemote sensing (RS) in agriculture has been widely used for mapping soil, plant, and atmosphere attributes, as well as helping in the sustainable production of the crop by providing the possibility of application at variable rates and estimating the productivity of agricultural crops. In this way, proximal sensors used by RS help producers in decision-making to increase productivity. This research aims to identify the best feature importance ranking to the Random Forest Classifier to predict cotton yield and select which one best correlates with cotton yield. This work was developed in four commercial fields on a Newellton, LA, USA farm. We evaluated the cotton in different years as 2019, 2020, and 2021. The variables evaluated were: soil parameters, topographic indices, elevation derivatives, and orbital remote sensing. The soil sensor used was: GSSI Profiler EMP400 (soil electromagnetic induction sensor) at a frequency of 15 kHz, and the RS data were collected from satellite images from Sentinel 2 (passive sensor) and active sensor from LiDAR (Light Detection and Ranging). For training (70%) and validation (30%) of dataset results, Spearman correlation was used between sensors and cotton yield data, machine learning (Random Forest Classifier and Regressor - RFC and RFR). The metric parameters were the coefficient of determination (R2), the Mean Absolute Error (MAE), and the Root Mean Square Error (RMSE). This study found that profiler, Sentinel-2 (blue, red, and green), TPI, LiDAR, and RTK elevation show the best correlations to predicting cotton yield.FRANCIELE MORLIN CARNEIRO, UTFPR; ARMANDO LOPES DE BRITO FILHO, UNESP; FRANCIELLE MORELLI FERREIRA, UNESP; GETULIO DE FREITAS SEBEN JUNIOR, UNEMAT; ZIANY NEIVA BRANDÃO, CNPA; ROUVERSON PEREIRA DA SILVA, UNESP; LUCIANO SHOZO SHIRATSUCHI, LOUISIANA STATE UNIVERSITY.CARNEIRO, F. M.BRITO FILHO, A. L. deFERREIRA, F. M.SEBEN JUNIOR, G. de F.BRANDÃO, Z. N.SILVA, R. P. daSHIRATSUCHI, L. S.2023-08-21T18:29:35Z2023-08-21T18:29:35Z2023-08-212023info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleSmart Agricultural Technology, v. 5, p. 1-10, 100292, 2023.2772-3755http://www.alice.cnptia.embrapa.br/alice/handle/doc/1156016https://doi.org/10.1016/j.atech.2023.100292enginfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice)instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa)instacron:EMBRAPA2023-08-21T18:29:35Zoai:www.alice.cnptia.embrapa.br:doc/1156016Repositório InstitucionalPUBhttps://www.alice.cnptia.embrapa.br/oai/requestopendoar:21542023-08-21T18:29:35falseRepositório InstitucionalPUBhttps://www.alice.cnptia.embrapa.br/oai/requestcg-riaa@embrapa.bropendoar:21542023-08-21T18:29:35Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa)false |
dc.title.none.fl_str_mv |
Soil and satellite remote sensing variables importance using machine learning to predict cotton yield. |
title |
Soil and satellite remote sensing variables importance using machine learning to predict cotton yield. |
spellingShingle |
Soil and satellite remote sensing variables importance using machine learning to predict cotton yield. CARNEIRO, F. M. Produção sustentável Sensores proximais Random forest Satellite imagery Sustainable production Proximal sensors Inteligência artificial Imagem de satélite RS Decision trees Árvores de decisão Algodão Estrutura do Solo Sensoriamento Remoto Gossypium Hirsutum Artificial intelligence Cotton Soil structure Remote sensing |
title_short |
Soil and satellite remote sensing variables importance using machine learning to predict cotton yield. |
title_full |
Soil and satellite remote sensing variables importance using machine learning to predict cotton yield. |
title_fullStr |
Soil and satellite remote sensing variables importance using machine learning to predict cotton yield. |
title_full_unstemmed |
Soil and satellite remote sensing variables importance using machine learning to predict cotton yield. |
title_sort |
Soil and satellite remote sensing variables importance using machine learning to predict cotton yield. |
author |
CARNEIRO, F. M. |
author_facet |
CARNEIRO, F. M. BRITO FILHO, A. L. de FERREIRA, F. M. SEBEN JUNIOR, G. de F. BRANDÃO, Z. N. SILVA, R. P. da SHIRATSUCHI, L. S. |
author_role |
author |
author2 |
BRITO FILHO, A. L. de FERREIRA, F. M. SEBEN JUNIOR, G. de F. BRANDÃO, Z. N. SILVA, R. P. da SHIRATSUCHI, L. S. |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
FRANCIELE MORLIN CARNEIRO, UTFPR; ARMANDO LOPES DE BRITO FILHO, UNESP; FRANCIELLE MORELLI FERREIRA, UNESP; GETULIO DE FREITAS SEBEN JUNIOR, UNEMAT; ZIANY NEIVA BRANDÃO, CNPA; ROUVERSON PEREIRA DA SILVA, UNESP; LUCIANO SHOZO SHIRATSUCHI, LOUISIANA STATE UNIVERSITY. |
dc.contributor.author.fl_str_mv |
CARNEIRO, F. M. BRITO FILHO, A. L. de FERREIRA, F. M. SEBEN JUNIOR, G. de F. BRANDÃO, Z. N. SILVA, R. P. da SHIRATSUCHI, L. S. |
dc.subject.por.fl_str_mv |
Produção sustentável Sensores proximais Random forest Satellite imagery Sustainable production Proximal sensors Inteligência artificial Imagem de satélite RS Decision trees Árvores de decisão Algodão Estrutura do Solo Sensoriamento Remoto Gossypium Hirsutum Artificial intelligence Cotton Soil structure Remote sensing |
topic |
Produção sustentável Sensores proximais Random forest Satellite imagery Sustainable production Proximal sensors Inteligência artificial Imagem de satélite RS Decision trees Árvores de decisão Algodão Estrutura do Solo Sensoriamento Remoto Gossypium Hirsutum Artificial intelligence Cotton Soil structure Remote sensing |
description |
Remote sensing (RS) in agriculture has been widely used for mapping soil, plant, and atmosphere attributes, as well as helping in the sustainable production of the crop by providing the possibility of application at variable rates and estimating the productivity of agricultural crops. In this way, proximal sensors used by RS help producers in decision-making to increase productivity. This research aims to identify the best feature importance ranking to the Random Forest Classifier to predict cotton yield and select which one best correlates with cotton yield. This work was developed in four commercial fields on a Newellton, LA, USA farm. We evaluated the cotton in different years as 2019, 2020, and 2021. The variables evaluated were: soil parameters, topographic indices, elevation derivatives, and orbital remote sensing. The soil sensor used was: GSSI Profiler EMP400 (soil electromagnetic induction sensor) at a frequency of 15 kHz, and the RS data were collected from satellite images from Sentinel 2 (passive sensor) and active sensor from LiDAR (Light Detection and Ranging). For training (70%) and validation (30%) of dataset results, Spearman correlation was used between sensors and cotton yield data, machine learning (Random Forest Classifier and Regressor - RFC and RFR). The metric parameters were the coefficient of determination (R2), the Mean Absolute Error (MAE), and the Root Mean Square Error (RMSE). This study found that profiler, Sentinel-2 (blue, red, and green), TPI, LiDAR, and RTK elevation show the best correlations to predicting cotton yield. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-08-21T18:29:35Z 2023-08-21T18:29:35Z 2023-08-21 2023 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
Smart Agricultural Technology, v. 5, p. 1-10, 100292, 2023. 2772-3755 http://www.alice.cnptia.embrapa.br/alice/handle/doc/1156016 https://doi.org/10.1016/j.atech.2023.100292 |
identifier_str_mv |
Smart Agricultural Technology, v. 5, p. 1-10, 100292, 2023. 2772-3755 |
url |
http://www.alice.cnptia.embrapa.br/alice/handle/doc/1156016 https://doi.org/10.1016/j.atech.2023.100292 |
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.source.none.fl_str_mv |
reponame:Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) instname:Empresa Brasileira de Pesquisa Agropecuária (Embrapa) instacron:EMBRAPA |
instname_str |
Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
instacron_str |
EMBRAPA |
institution |
EMBRAPA |
reponame_str |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
collection |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) |
repository.name.fl_str_mv |
Repositório Institucional da EMBRAPA (Repository Open Access to Scientific Information from EMBRAPA - Alice) - Empresa Brasileira de Pesquisa Agropecuária (Embrapa) |
repository.mail.fl_str_mv |
cg-riaa@embrapa.br |
_version_ |
1794503548433596416 |