Sunpheno : a deep neural network for phenological classification of sunflower images

Leaf senescence is a complex trait which becomes crucial for grain filling because photoassimilates are translocated to the seeds. Therefore, a correct sync between leaf senescence and phenological stages is necessary to obtain increasing yields. In this study, we evaluated the performance of five d...

Descripción completa

Detalles Bibliográficos
Autores principales: Bengoa Luoni, Sofía Ailin, Ricci, Riccardo, Corzo, Melanie Anahi, Hoxha, Genc, Melgani, Farid, Fernandez, Paula Del Carmen
Formato: info:ar-repo/semantics/artículo
Lenguaje:Inglés
Publicado: MDPI 2024
Materias:
Acceso en línea:http://hdl.handle.net/20.500.12123/18739
https://www.mdpi.com/2223-7747/13/14/1998
https://doi.org/10.3390/plants13141998
_version_ 1855037908259438592
author Bengoa Luoni, Sofía Ailin
Ricci, Riccardo
Corzo, Melanie Anahi
Hoxha, Genc
Melgani, Farid
Fernandez, Paula Del Carmen
author_browse Bengoa Luoni, Sofía Ailin
Corzo, Melanie Anahi
Fernandez, Paula Del Carmen
Hoxha, Genc
Melgani, Farid
Ricci, Riccardo
author_facet Bengoa Luoni, Sofía Ailin
Ricci, Riccardo
Corzo, Melanie Anahi
Hoxha, Genc
Melgani, Farid
Fernandez, Paula Del Carmen
author_sort Bengoa Luoni, Sofía Ailin
collection INTA Digital
description Leaf senescence is a complex trait which becomes crucial for grain filling because photoassimilates are translocated to the seeds. Therefore, a correct sync between leaf senescence and phenological stages is necessary to obtain increasing yields. In this study, we evaluated the performance of five deep machine-learning methods for the evaluation of the phenological stages of sunflowers using images taken with cell phones in the field. From the analysis, we found that the method based on the pre-trained network resnet50 outperformed the other methods, both in terms of accuracy and velocity. Finally, the model generated, Sunpheno, was used to evaluate the phenological stages of two contrasting lines, B481_6 and R453, during senescence. We observed clear differences in phenological stages, confirming the results obtained in previous studies. A database with 5000 images was generated and was classified by an expert. This is important to end the subjectivity involved in decision making regarding the progression of this trait in the field and could be correlated with performance and senescence parameters that are highly associated with yield increase.
format info:ar-repo/semantics/artículo
id INTA18739
institution Instituto Nacional de Tecnología Agropecuaria (INTA -Argentina)
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher MDPI
publisherStr MDPI
record_format dspace
spelling INTA187392024-08-01T10:31:47Z Sunpheno : a deep neural network for phenological classification of sunflower images Bengoa Luoni, Sofía Ailin Ricci, Riccardo Corzo, Melanie Anahi Hoxha, Genc Melgani, Farid Fernandez, Paula Del Carmen Phenology Senescence Sunflowers Machine Learning Fenología Avejentamiento Girasol Aprendizaje Automático Leaf senescence is a complex trait which becomes crucial for grain filling because photoassimilates are translocated to the seeds. Therefore, a correct sync between leaf senescence and phenological stages is necessary to obtain increasing yields. In this study, we evaluated the performance of five deep machine-learning methods for the evaluation of the phenological stages of sunflowers using images taken with cell phones in the field. From the analysis, we found that the method based on the pre-trained network resnet50 outperformed the other methods, both in terms of accuracy and velocity. Finally, the model generated, Sunpheno, was used to evaluate the phenological stages of two contrasting lines, B481_6 and R453, during senescence. We observed clear differences in phenological stages, confirming the results obtained in previous studies. A database with 5000 images was generated and was classified by an expert. This is important to end the subjectivity involved in decision making regarding the progression of this trait in the field and could be correlated with performance and senescence parameters that are highly associated with yield increase. Instituto de Biotecnología Fil: Bengoa Luoni, Sofia Ailin. Wageningen University & Research. Laboratory of Genetics; Países Bajos Fil: Ricci, Riccardo. University of Trento. Department of Information Engineering and Computer Science; Italia Fil: Corzo, Melanie Anahi. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Agrobiotecnología y Biología Molecular; Argentina Fil: Corzo, Melanie Anahi. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina Fil: Hoxha, Genc. Technische Universität Berlin. Faculty of Electrical Engineering and Computer Science; Alemania Fil: Melgani, Farid. University of Trento. Department of Information Engineering and Computer Science; Italia Fil: Fernandez, Paula Del Carmen. Instituto Nacional de Tecnología Agropecuaria (INTA). Instituto de Agrobiotecnología y Biología Molecular; Argentina Fil: Fernandez, Paula Del Carmen. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina 2024-08-01T10:18:50Z 2024-08-01T10:18:50Z 2024-07 info:ar-repo/semantics/artículo info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion http://hdl.handle.net/20.500.12123/18739 https://www.mdpi.com/2223-7747/13/14/1998 2223-7747 https://doi.org/10.3390/plants13141998 eng info:eu-repograntAgreement/INTA/PNBIO/1131022/AR./Genómica funcional y biología de sistemas. info:eu-repograntAgreement/INTA/PNBIO/1131043/AR./Bioinformática y Estadística Genómica. info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf MDPI Plants 13 (14) : 1998 (July 2024)
spellingShingle Phenology
Senescence
Sunflowers
Machine Learning
Fenología
Avejentamiento
Girasol
Aprendizaje Automático
Bengoa Luoni, Sofía Ailin
Ricci, Riccardo
Corzo, Melanie Anahi
Hoxha, Genc
Melgani, Farid
Fernandez, Paula Del Carmen
Sunpheno : a deep neural network for phenological classification of sunflower images
title Sunpheno : a deep neural network for phenological classification of sunflower images
title_full Sunpheno : a deep neural network for phenological classification of sunflower images
title_fullStr Sunpheno : a deep neural network for phenological classification of sunflower images
title_full_unstemmed Sunpheno : a deep neural network for phenological classification of sunflower images
title_short Sunpheno : a deep neural network for phenological classification of sunflower images
title_sort sunpheno a deep neural network for phenological classification of sunflower images
topic Phenology
Senescence
Sunflowers
Machine Learning
Fenología
Avejentamiento
Girasol
Aprendizaje Automático
url http://hdl.handle.net/20.500.12123/18739
https://www.mdpi.com/2223-7747/13/14/1998
https://doi.org/10.3390/plants13141998
work_keys_str_mv AT bengoaluonisofiaailin sunphenoadeepneuralnetworkforphenologicalclassificationofsunflowerimages
AT ricciriccardo sunphenoadeepneuralnetworkforphenologicalclassificationofsunflowerimages
AT corzomelanieanahi sunphenoadeepneuralnetworkforphenologicalclassificationofsunflowerimages
AT hoxhagenc sunphenoadeepneuralnetworkforphenologicalclassificationofsunflowerimages
AT melganifarid sunphenoadeepneuralnetworkforphenologicalclassificationofsunflowerimages
AT fernandezpauladelcarmen sunphenoadeepneuralnetworkforphenologicalclassificationofsunflowerimages