Geographic-scale coffee cherry counting with smartphones and deep learning

Deep learning and computer vision, using remote sensing and drones, are 2 promising nondestructive methods for plant monitoring and phenotyping. However, their applications are infeasible for many crop systems under tree canopies, such as coffee crops, making it challenging...

Descripción completa

Detalles Bibliográficos
Autores principales: Rivera Palacio, Juan Camilo, Bunn, Christian, Rahn, Eric, Little-Savage, Daisy, Schimidt, Paul, Ryo, Masahiro
Formato: Journal Article
Lenguaje:Inglés
Publicado: Elsevier 2024
Materias:
Acceso en línea:https://hdl.handle.net/10568/141476
_version_ 1855527260642082816
author Rivera Palacio, Juan Camilo
Bunn, Christian
Rahn, Eric
Little-Savage, Daisy
Schimidt, Paul
Ryo, Masahiro
author_browse Bunn, Christian
Little-Savage, Daisy
Rahn, Eric
Rivera Palacio, Juan Camilo
Ryo, Masahiro
Schimidt, Paul
author_facet Rivera Palacio, Juan Camilo
Bunn, Christian
Rahn, Eric
Little-Savage, Daisy
Schimidt, Paul
Ryo, Masahiro
author_sort Rivera Palacio, Juan Camilo
collection Repository of Agricultural Research Outputs (CGSpace)
description Deep learning and computer vision, using remote sensing and drones, are 2 promising nondestructive methods for plant monitoring and phenotyping. However, their applications are infeasible for many crop systems under tree canopies, such as coffee crops, making it challenging to perform plant monitoring and phenotyping at a large spatial scale at a low cost. This study aims to develop a geographic-scale monitoring method for coffee cherry counting, supported by an artificial intelligence (AI)-powered citizen science approach. The approach uses basic smartphones to take a few pictures of coffee trees; 2,968 trees were investigated with 8,904 pictures in Junín and Piura (Peru), Cauca, and Quindío (Colombia) in 2022, with the help of nearly 1,000 smallholder coffee farmers. Then, we trained and validated YOLO (You Only Look Once) v8 for detecting cherries in the dataset in Peru. An average number of cherries per picture was multiplied by the number of branches to estimate the total number of cherries per tree. The model's performance in Peru showed an R2 of 0.59. When the model was tested in Colombia, where different varieties are grown in different biogeoclimatic conditions, the model showed an R2 of 0.71. The overall performance in both countries reached an R2 of 0.72. The results suggest that the method can be applied to much broader scales and is transferable to other varieties, countries, and regions. To our knowledge, this is the first AI-powered method for counting coffee cherries and has the potential for a geographic-scale, multiyear, photo-based phenotypic monitoring for coffee crops in low-income countries worldwide.
format Journal Article
id CGSpace141476
institution CGIAR Consortium
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1414762025-12-08T09:54:28Z Geographic-scale coffee cherry counting with smartphones and deep learning Rivera Palacio, Juan Camilo Bunn, Christian Rahn, Eric Little-Savage, Daisy Schimidt, Paul Ryo, Masahiro coffee artificial intelligence crop modelling phenotyping crop monitoring monitoring systems cherries Deep learning and computer vision, using remote sensing and drones, are 2 promising nondestructive methods for plant monitoring and phenotyping. However, their applications are infeasible for many crop systems under tree canopies, such as coffee crops, making it challenging to perform plant monitoring and phenotyping at a large spatial scale at a low cost. This study aims to develop a geographic-scale monitoring method for coffee cherry counting, supported by an artificial intelligence (AI)-powered citizen science approach. The approach uses basic smartphones to take a few pictures of coffee trees; 2,968 trees were investigated with 8,904 pictures in Junín and Piura (Peru), Cauca, and Quindío (Colombia) in 2022, with the help of nearly 1,000 smallholder coffee farmers. Then, we trained and validated YOLO (You Only Look Once) v8 for detecting cherries in the dataset in Peru. An average number of cherries per picture was multiplied by the number of branches to estimate the total number of cherries per tree. The model's performance in Peru showed an R2 of 0.59. When the model was tested in Colombia, where different varieties are grown in different biogeoclimatic conditions, the model showed an R2 of 0.71. The overall performance in both countries reached an R2 of 0.72. The results suggest that the method can be applied to much broader scales and is transferable to other varieties, countries, and regions. To our knowledge, this is the first AI-powered method for counting coffee cherries and has the potential for a geographic-scale, multiyear, photo-based phenotypic monitoring for coffee crops in low-income countries worldwide. 2024 2024-04-16T09:38:29Z 2024-04-16T09:38:29Z Journal Article https://hdl.handle.net/10568/141476 en Open Access application/pdf Elsevier Rivera Palacio, J.C.; Bunn, C.; Rahn, E.; Little-Savage, D.; Schimidt, P.; Ryo, M. (2024) Geographic-scale coffee cherry counting with smartphones and deep learning. Plant Phenomics 6: 0165. ISSN: 2643-6515
spellingShingle coffee
artificial intelligence
crop modelling
phenotyping
crop monitoring
monitoring systems
cherries
Rivera Palacio, Juan Camilo
Bunn, Christian
Rahn, Eric
Little-Savage, Daisy
Schimidt, Paul
Ryo, Masahiro
Geographic-scale coffee cherry counting with smartphones and deep learning
title Geographic-scale coffee cherry counting with smartphones and deep learning
title_full Geographic-scale coffee cherry counting with smartphones and deep learning
title_fullStr Geographic-scale coffee cherry counting with smartphones and deep learning
title_full_unstemmed Geographic-scale coffee cherry counting with smartphones and deep learning
title_short Geographic-scale coffee cherry counting with smartphones and deep learning
title_sort geographic scale coffee cherry counting with smartphones and deep learning
topic coffee
artificial intelligence
crop modelling
phenotyping
crop monitoring
monitoring systems
cherries
url https://hdl.handle.net/10568/141476
work_keys_str_mv AT riverapalaciojuancamilo geographicscalecoffeecherrycountingwithsmartphonesanddeeplearning
AT bunnchristian geographicscalecoffeecherrycountingwithsmartphonesanddeeplearning
AT rahneric geographicscalecoffeecherrycountingwithsmartphonesanddeeplearning
AT littlesavagedaisy geographicscalecoffeecherrycountingwithsmartphonesanddeeplearning
AT schimidtpaul geographicscalecoffeecherrycountingwithsmartphonesanddeeplearning
AT ryomasahiro geographicscalecoffeecherrycountingwithsmartphonesanddeeplearning