A comparison between support vector machine and water cloud model for estimating crop leaf area index

Autores
Hosseini, Mehdi; McNairn, Heather; Mitchell, Scott; Robertson, Laura Dingle; Davidson, Andrew; Ahmadian, Nima; Bhattacharya, Avik; Borg, Erik; Conrad, Christopher; Dabrowska Zielinska, Katarzyna; de Abelleyra, Diego; Gurdak, Radoslaw; Kumar, Vineet; Kussul, Nataliia; Mandal, Dipankar; Rao, Y.S.; Saliendra, Nicanor; Shelestov, Andrii; Spengler, Daniel; Verón, Santiago Ramón; Homayouni, Saeid; Becker Reshef, Inbal
Año de publicación
2021
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The water cloud model (WCM) can be inverted to estimate leaf area index (LAI) using the intensity of backscatter from synthetic aperture radar (SAR) sensors. Published studies have demonstrated that the WCM can accurately estimate LAI if the model is effectively calibrated. However, calibration of this model requires access to field measures of LAI as well as soil moisture. In contrast, machine learning (ML) algorithms can be trained to estimate LAI from satellite data, even if field moisture measures are not available. In this study, a support vector machine (SVM) was trained to estimate the LAI for corn, soybeans, rice, and wheat crops. These results were compared to LAI estimates from the WCM. To complete this comparison, in situ and satellite data were collected from seven Joint Experiment for Crop Assessment and Monitoring (JECAM) sites located in Argentina, Canada, Germany, India, Poland, Ukraine and the United States of America (U.S.A.). The models used C-Band backscatter intensity for two polarizations (like-polarization (VV) and cross-polarization (VH)) acquired by the RADARSAT-2 and Sentinel-1 SAR satellites. Both the WCM and SVM models performed well in estimating the LAI of corn. For the SVM, the correlation (R) between estimated LAI for corn and LAI measured in situ was reported as 0.93, with a root mean square error (RMSE) of 0.64 m2m-2 and mean absolute error (MAE) of 0.51 m2m-2. The WCM produced an R-value of 0.89, with only slightly higher errors (RMSE of 0.75 m2m-2 and MAE of 0.61 m2m-2) when estimating corn LAI. For rice, only the SVM model was tested, given the lack of soil moisture measures for this crop. In this case, both high correlations and low errors were observed in estimating the LAI of rice using SVM (R of 0.96, RMSE of 0.41 m2m-2 and MAE of 0.30 m2m-2). However, the results demonstrated that when the calibration points were limited (in this case for soybeans), the WCM outperformed the SVM model. This study demonstrates the importance of testing different modeling approaches over diverse agro-ecosystems to increase confidence in model performance.
Fil: Hosseini, Mehdi. University of Maryland; Estados Unidos. Carleton University; Canadá
Fil: McNairn, Heather. Carleton University; Canadá. Science and Technology Branch, Agriculture and Agri-Food Canada; Canadá
Fil: Mitchell, Scott. Carleton University; Canadá
Fil: Robertson, Laura Dingle. Science and Technology Branch, Agriculture and Agri-Food Canada; Canadá
Fil: Davidson, Andrew. Carleton University; Canadá. Science and Technology Branch, Agriculture and Agri-Food Canada; Canadá
Fil: Ahmadian, Nima. Universität Würzburg; Alemania
Fil: Bhattacharya, Avik. Indian Institute Of Technology Bombay; India
Fil: Borg, Erik. German Aerospace Center; Alemania
Fil: Conrad, Christopher. Leibniz Institut Fur Pflanzenbiochemie (ipb Halle);
Fil: Dabrowska Zielinska, Katarzyna. Institute of Geodesy and Cartography; Polonia
Fil: de Abelleyra, Diego. Instituto Nacional de Tecnología Agropecuaria. Centro de Investigación de Recursos Naturales. Instituto de Clima y Agua; Argentina
Fil: Gurdak, Radoslaw. Institute of Geodesy and Cartography; Polonia
Fil: Kumar, Vineet. Indian Institute Of Technology Bombay; India. Delft University of Technology; Países Bajos
Fil: Kussul, Nataliia. National Academy Of Sciences In Ukraine; Ucrania
Fil: Mandal, Dipankar. Indian Institute Of Technology Bombay; India
Fil: Rao, Y.S.. Indian Institute Of Technology Bombay; India
Fil: Saliendra, Nicanor. USDA-ARS Northern Great Plains Research Laboratory; Estados Unidos
Fil: Shelestov, Andrii. National Academy Of Sciences In Ukraine; Ucrania
Fil: Spengler, Daniel. German Research Centre for Geosciences; Alemania
Fil: Verón, Santiago Ramón. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Instituto Nacional de Tecnología Agropecuaria. Centro de Investigación de Recursos Naturales. Instituto de Clima y Agua; Argentina
Fil: Homayouni, Saeid. Centre Eau Terre Environnement; Canadá
Fil: Becker Reshef, Inbal. University of Maryland; Estados Unidos
Materia
LEAF AREA INDEX
MACHINE LEARNING
RADARSAT-2
SENTINEL-1
WATER CLOUD MODEL
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/213317
Acceder
id CONICETDig_620c1e9a0977adec645449cb51e70d14
oai_identifier_str oai:ri.conicet.gov.ar:11336/213317
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling A comparison between support vector machine and water cloud model for estimating crop leaf area indexHosseini, MehdiMcNairn, HeatherMitchell, ScottRobertson, Laura DingleDavidson, AndrewAhmadian, NimaBhattacharya, AvikBorg, ErikConrad, ChristopherDabrowska Zielinska, Katarzynade Abelleyra, DiegoGurdak, RadoslawKumar, VineetKussul, NataliiaMandal, DipankarRao, Y.S.Saliendra, NicanorShelestov, AndriiSpengler, DanielVerón, Santiago RamónHomayouni, SaeidBecker Reshef, InbalLEAF AREA INDEXMACHINE LEARNINGRADARSAT-2SENTINEL-1WATER CLOUD MODELhttps://purl.org/becyt/ford/1.5https://purl.org/becyt/ford/1The water cloud model (WCM) can be inverted to estimate leaf area index (LAI) using the intensity of backscatter from synthetic aperture radar (SAR) sensors. Published studies have demonstrated that the WCM can accurately estimate LAI if the model is effectively calibrated. However, calibration of this model requires access to field measures of LAI as well as soil moisture. In contrast, machine learning (ML) algorithms can be trained to estimate LAI from satellite data, even if field moisture measures are not available. In this study, a support vector machine (SVM) was trained to estimate the LAI for corn, soybeans, rice, and wheat crops. These results were compared to LAI estimates from the WCM. To complete this comparison, in situ and satellite data were collected from seven Joint Experiment for Crop Assessment and Monitoring (JECAM) sites located in Argentina, Canada, Germany, India, Poland, Ukraine and the United States of America (U.S.A.). The models used C-Band backscatter intensity for two polarizations (like-polarization (VV) and cross-polarization (VH)) acquired by the RADARSAT-2 and Sentinel-1 SAR satellites. Both the WCM and SVM models performed well in estimating the LAI of corn. For the SVM, the correlation (R) between estimated LAI for corn and LAI measured in situ was reported as 0.93, with a root mean square error (RMSE) of 0.64 m2m-2 and mean absolute error (MAE) of 0.51 m2m-2. The WCM produced an R-value of 0.89, with only slightly higher errors (RMSE of 0.75 m2m-2 and MAE of 0.61 m2m-2) when estimating corn LAI. For rice, only the SVM model was tested, given the lack of soil moisture measures for this crop. In this case, both high correlations and low errors were observed in estimating the LAI of rice using SVM (R of 0.96, RMSE of 0.41 m2m-2 and MAE of 0.30 m2m-2). However, the results demonstrated that when the calibration points were limited (in this case for soybeans), the WCM outperformed the SVM model. This study demonstrates the importance of testing different modeling approaches over diverse agro-ecosystems to increase confidence in model performance.Fil: Hosseini, Mehdi. University of Maryland; Estados Unidos. Carleton University; CanadáFil: McNairn, Heather. Carleton University; Canadá. Science and Technology Branch, Agriculture and Agri-Food Canada; CanadáFil: Mitchell, Scott. Carleton University; CanadáFil: Robertson, Laura Dingle. Science and Technology Branch, Agriculture and Agri-Food Canada; CanadáFil: Davidson, Andrew. Carleton University; Canadá. Science and Technology Branch, Agriculture and Agri-Food Canada; CanadáFil: Ahmadian, Nima. Universität Würzburg; AlemaniaFil: Bhattacharya, Avik. Indian Institute Of Technology Bombay; IndiaFil: Borg, Erik. German Aerospace Center; AlemaniaFil: Conrad, Christopher. Leibniz Institut Fur Pflanzenbiochemie (ipb Halle);Fil: Dabrowska Zielinska, Katarzyna. Institute of Geodesy and Cartography; PoloniaFil: de Abelleyra, Diego. Instituto Nacional de Tecnología Agropecuaria. Centro de Investigación de Recursos Naturales. Instituto de Clima y Agua; ArgentinaFil: Gurdak, Radoslaw. Institute of Geodesy and Cartography; PoloniaFil: Kumar, Vineet. Indian Institute Of Technology Bombay; India. Delft University of Technology; Países BajosFil: Kussul, Nataliia. National Academy Of Sciences In Ukraine; UcraniaFil: Mandal, Dipankar. Indian Institute Of Technology Bombay; IndiaFil: Rao, Y.S.. Indian Institute Of Technology Bombay; IndiaFil: Saliendra, Nicanor. USDA-ARS Northern Great Plains Research Laboratory; Estados UnidosFil: Shelestov, Andrii. National Academy Of Sciences In Ukraine; UcraniaFil: Spengler, Daniel. German Research Centre for Geosciences; AlemaniaFil: Verón, Santiago Ramón. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Instituto Nacional de Tecnología Agropecuaria. Centro de Investigación de Recursos Naturales. Instituto de Clima y Agua; ArgentinaFil: Homayouni, Saeid. Centre Eau Terre Environnement; CanadáFil: Becker Reshef, Inbal. University of Maryland; Estados UnidosMultidisciplinary Digital Publishing Institute2021-04info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/213317Hosseini, Mehdi; McNairn, Heather; Mitchell, Scott; Robertson, Laura Dingle; Davidson, Andrew; et al.; A comparison between support vector machine and water cloud model for estimating crop leaf area index; Multidisciplinary Digital Publishing Institute; Remote Sensing; 13; 7; 4-2021; 1-202072-4292CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/10.3390/rs13071348info:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2072-4292/13/7/1348info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-08-25T14:39:42Zoai:ri.conicet.gov.ar:11336/213317instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982026-08-25 14:39:42.802CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv A comparison between support vector machine and water cloud model for estimating crop leaf area index
title A comparison between support vector machine and water cloud model for estimating crop leaf area index
spellingShingle A comparison between support vector machine and water cloud model for estimating crop leaf area index
Hosseini, Mehdi
LEAF AREA INDEX
MACHINE LEARNING
RADARSAT-2
SENTINEL-1
WATER CLOUD MODEL
title_short A comparison between support vector machine and water cloud model for estimating crop leaf area index
title_full A comparison between support vector machine and water cloud model for estimating crop leaf area index
title_fullStr A comparison between support vector machine and water cloud model for estimating crop leaf area index
title_full_unstemmed A comparison between support vector machine and water cloud model for estimating crop leaf area index
title_sort A comparison between support vector machine and water cloud model for estimating crop leaf area index
dc.creator.none.fl_str_mv Hosseini, Mehdi
McNairn, Heather
Mitchell, Scott
Robertson, Laura Dingle
Davidson, Andrew
Ahmadian, Nima
Bhattacharya, Avik
Borg, Erik
Conrad, Christopher
Dabrowska Zielinska, Katarzyna
de Abelleyra, Diego
Gurdak, Radoslaw
Kumar, Vineet
Kussul, Nataliia
Mandal, Dipankar
Rao, Y.S.
Saliendra, Nicanor
Shelestov, Andrii
Spengler, Daniel
Verón, Santiago Ramón
Homayouni, Saeid
Becker Reshef, Inbal
author Hosseini, Mehdi
author_facet Hosseini, Mehdi
McNairn, Heather
Mitchell, Scott
Robertson, Laura Dingle
Davidson, Andrew
Ahmadian, Nima
Bhattacharya, Avik
Borg, Erik
Conrad, Christopher
Dabrowska Zielinska, Katarzyna
de Abelleyra, Diego
Gurdak, Radoslaw
Kumar, Vineet
Kussul, Nataliia
Mandal, Dipankar
Rao, Y.S.
Saliendra, Nicanor
Shelestov, Andrii
Spengler, Daniel
Verón, Santiago Ramón
Homayouni, Saeid
Becker Reshef, Inbal
author_role author
author2 McNairn, Heather
Mitchell, Scott
Robertson, Laura Dingle
Davidson, Andrew
Ahmadian, Nima
Bhattacharya, Avik
Borg, Erik
Conrad, Christopher
Dabrowska Zielinska, Katarzyna
de Abelleyra, Diego
Gurdak, Radoslaw
Kumar, Vineet
Kussul, Nataliia
Mandal, Dipankar
Rao, Y.S.
Saliendra, Nicanor
Shelestov, Andrii
Spengler, Daniel
Verón, Santiago Ramón
Homayouni, Saeid
Becker Reshef, Inbal
author2_role author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv LEAF AREA INDEX
MACHINE LEARNING
RADARSAT-2
SENTINEL-1
WATER CLOUD MODEL
topic LEAF AREA INDEX
MACHINE LEARNING
RADARSAT-2
SENTINEL-1
WATER CLOUD MODEL
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.5
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv The water cloud model (WCM) can be inverted to estimate leaf area index (LAI) using the intensity of backscatter from synthetic aperture radar (SAR) sensors. Published studies have demonstrated that the WCM can accurately estimate LAI if the model is effectively calibrated. However, calibration of this model requires access to field measures of LAI as well as soil moisture. In contrast, machine learning (ML) algorithms can be trained to estimate LAI from satellite data, even if field moisture measures are not available. In this study, a support vector machine (SVM) was trained to estimate the LAI for corn, soybeans, rice, and wheat crops. These results were compared to LAI estimates from the WCM. To complete this comparison, in situ and satellite data were collected from seven Joint Experiment for Crop Assessment and Monitoring (JECAM) sites located in Argentina, Canada, Germany, India, Poland, Ukraine and the United States of America (U.S.A.). The models used C-Band backscatter intensity for two polarizations (like-polarization (VV) and cross-polarization (VH)) acquired by the RADARSAT-2 and Sentinel-1 SAR satellites. Both the WCM and SVM models performed well in estimating the LAI of corn. For the SVM, the correlation (R) between estimated LAI for corn and LAI measured in situ was reported as 0.93, with a root mean square error (RMSE) of 0.64 m2m-2 and mean absolute error (MAE) of 0.51 m2m-2. The WCM produced an R-value of 0.89, with only slightly higher errors (RMSE of 0.75 m2m-2 and MAE of 0.61 m2m-2) when estimating corn LAI. For rice, only the SVM model was tested, given the lack of soil moisture measures for this crop. In this case, both high correlations and low errors were observed in estimating the LAI of rice using SVM (R of 0.96, RMSE of 0.41 m2m-2 and MAE of 0.30 m2m-2). However, the results demonstrated that when the calibration points were limited (in this case for soybeans), the WCM outperformed the SVM model. This study demonstrates the importance of testing different modeling approaches over diverse agro-ecosystems to increase confidence in model performance.
Fil: Hosseini, Mehdi. University of Maryland; Estados Unidos. Carleton University; Canadá
Fil: McNairn, Heather. Carleton University; Canadá. Science and Technology Branch, Agriculture and Agri-Food Canada; Canadá
Fil: Mitchell, Scott. Carleton University; Canadá
Fil: Robertson, Laura Dingle. Science and Technology Branch, Agriculture and Agri-Food Canada; Canadá
Fil: Davidson, Andrew. Carleton University; Canadá. Science and Technology Branch, Agriculture and Agri-Food Canada; Canadá
Fil: Ahmadian, Nima. Universität Würzburg; Alemania
Fil: Bhattacharya, Avik. Indian Institute Of Technology Bombay; India
Fil: Borg, Erik. German Aerospace Center; Alemania
Fil: Conrad, Christopher. Leibniz Institut Fur Pflanzenbiochemie (ipb Halle);
Fil: Dabrowska Zielinska, Katarzyna. Institute of Geodesy and Cartography; Polonia
Fil: de Abelleyra, Diego. Instituto Nacional de Tecnología Agropecuaria. Centro de Investigación de Recursos Naturales. Instituto de Clima y Agua; Argentina
Fil: Gurdak, Radoslaw. Institute of Geodesy and Cartography; Polonia
Fil: Kumar, Vineet. Indian Institute Of Technology Bombay; India. Delft University of Technology; Países Bajos
Fil: Kussul, Nataliia. National Academy Of Sciences In Ukraine; Ucrania
Fil: Mandal, Dipankar. Indian Institute Of Technology Bombay; India
Fil: Rao, Y.S.. Indian Institute Of Technology Bombay; India
Fil: Saliendra, Nicanor. USDA-ARS Northern Great Plains Research Laboratory; Estados Unidos
Fil: Shelestov, Andrii. National Academy Of Sciences In Ukraine; Ucrania
Fil: Spengler, Daniel. German Research Centre for Geosciences; Alemania
Fil: Verón, Santiago Ramón. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Instituto Nacional de Tecnología Agropecuaria. Centro de Investigación de Recursos Naturales. Instituto de Clima y Agua; Argentina
Fil: Homayouni, Saeid. Centre Eau Terre Environnement; Canadá
Fil: Becker Reshef, Inbal. University of Maryland; Estados Unidos
description The water cloud model (WCM) can be inverted to estimate leaf area index (LAI) using the intensity of backscatter from synthetic aperture radar (SAR) sensors. Published studies have demonstrated that the WCM can accurately estimate LAI if the model is effectively calibrated. However, calibration of this model requires access to field measures of LAI as well as soil moisture. In contrast, machine learning (ML) algorithms can be trained to estimate LAI from satellite data, even if field moisture measures are not available. In this study, a support vector machine (SVM) was trained to estimate the LAI for corn, soybeans, rice, and wheat crops. These results were compared to LAI estimates from the WCM. To complete this comparison, in situ and satellite data were collected from seven Joint Experiment for Crop Assessment and Monitoring (JECAM) sites located in Argentina, Canada, Germany, India, Poland, Ukraine and the United States of America (U.S.A.). The models used C-Band backscatter intensity for two polarizations (like-polarization (VV) and cross-polarization (VH)) acquired by the RADARSAT-2 and Sentinel-1 SAR satellites. Both the WCM and SVM models performed well in estimating the LAI of corn. For the SVM, the correlation (R) between estimated LAI for corn and LAI measured in situ was reported as 0.93, with a root mean square error (RMSE) of 0.64 m2m-2 and mean absolute error (MAE) of 0.51 m2m-2. The WCM produced an R-value of 0.89, with only slightly higher errors (RMSE of 0.75 m2m-2 and MAE of 0.61 m2m-2) when estimating corn LAI. For rice, only the SVM model was tested, given the lack of soil moisture measures for this crop. In this case, both high correlations and low errors were observed in estimating the LAI of rice using SVM (R of 0.96, RMSE of 0.41 m2m-2 and MAE of 0.30 m2m-2). However, the results demonstrated that when the calibration points were limited (in this case for soybeans), the WCM outperformed the SVM model. This study demonstrates the importance of testing different modeling approaches over diverse agro-ecosystems to increase confidence in model performance.
publishDate 2021
dc.date.none.fl_str_mv 2021-04
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/213317
Hosseini, Mehdi; McNairn, Heather; Mitchell, Scott; Robertson, Laura Dingle; Davidson, Andrew; et al.; A comparison between support vector machine and water cloud model for estimating crop leaf area index; Multidisciplinary Digital Publishing Institute; Remote Sensing; 13; 7; 4-2021; 1-20
2072-4292
CONICET Digital
CONICET
url http://hdl.handle.net/11336/213317
identifier_str_mv Hosseini, Mehdi; McNairn, Heather; Mitchell, Scott; Robertson, Laura Dingle; Davidson, Andrew; et al.; A comparison between support vector machine and water cloud model for estimating crop leaf area index; Multidisciplinary Digital Publishing Institute; Remote Sensing; 13; 7; 4-2021; 1-20
2072-4292
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.3390/rs13071348
info:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2072-4292/13/7/1348
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute
publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1874774408523939840
score 13.265058

Publicaciones similares