Spatial Variability of Aroma Profiles of Cocoa Trees Obtained through Computer Vision and Machine Learning Modelling: A Cover Photography and High Spatial Remote Sensing Application
Cocoa is an important commodity crop, not only to produce chocolate, one of the most complex products from the sensory perspective, but one that commonly grows in developing countries close to the tropics. This paper presents novel techniques applied using cover photography and a novel computer appl...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/14/3054 |
_version_ | 1811263593858990080 |
---|---|
author | Sigfredo Fuentes Gabriela Chacon Damir D. Torrico Andrea Zarate Claudia Gonzalez Viejo |
author_facet | Sigfredo Fuentes Gabriela Chacon Damir D. Torrico Andrea Zarate Claudia Gonzalez Viejo |
author_sort | Sigfredo Fuentes |
collection | DOAJ |
description | Cocoa is an important commodity crop, not only to produce chocolate, one of the most complex products from the sensory perspective, but one that commonly grows in developing countries close to the tropics. This paper presents novel techniques applied using cover photography and a novel computer application (VitiCanopy) to assess the canopy architecture of cocoa trees in a commercial plantation in Queensland, Australia. From the cocoa trees monitored, pod samples were collected, fermented, dried, and ground to obtain the aroma profile per tree using gas chromatography. The canopy architecture data were used as inputs in an artificial neural network (ANN) algorithm, with the aroma profile, considering six main aromas, as targets. The ANN model rendered high accuracy (correlation coefficient (R) = 0.82; mean squared error (MSE) = 0.09) with no overfitting. The model was then applied to an aerial image of the whole cocoa field studied to produce canopy vigor, and aroma profile maps up to the tree-by-tree scale. The tool developed could significantly aid the canopy management practices in cocoa trees, which have a direct effect on cocoa quality. |
first_indexed | 2024-04-12T19:48:10Z |
format | Article |
id | doaj.art-f0fa52ca6f4f4cde800cfcb8aa4d974e |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-12T19:48:10Z |
publishDate | 2019-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-f0fa52ca6f4f4cde800cfcb8aa4d974e2022-12-22T03:18:55ZengMDPI AGSensors1424-82202019-07-011914305410.3390/s19143054s19143054Spatial Variability of Aroma Profiles of Cocoa Trees Obtained through Computer Vision and Machine Learning Modelling: A Cover Photography and High Spatial Remote Sensing ApplicationSigfredo Fuentes0Gabriela Chacon1Damir D. Torrico2Andrea Zarate3Claudia Gonzalez Viejo4School of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Melbourne, VIC 3010, AustraliaSchool of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Melbourne, VIC 3010, AustraliaSchool of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Melbourne, VIC 3010, AustraliaSchool of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Melbourne, VIC 3010, AustraliaSchool of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, University of Melbourne, Melbourne, VIC 3010, AustraliaCocoa is an important commodity crop, not only to produce chocolate, one of the most complex products from the sensory perspective, but one that commonly grows in developing countries close to the tropics. This paper presents novel techniques applied using cover photography and a novel computer application (VitiCanopy) to assess the canopy architecture of cocoa trees in a commercial plantation in Queensland, Australia. From the cocoa trees monitored, pod samples were collected, fermented, dried, and ground to obtain the aroma profile per tree using gas chromatography. The canopy architecture data were used as inputs in an artificial neural network (ANN) algorithm, with the aroma profile, considering six main aromas, as targets. The ANN model rendered high accuracy (correlation coefficient (R) = 0.82; mean squared error (MSE) = 0.09) with no overfitting. The model was then applied to an aerial image of the whole cocoa field studied to produce canopy vigor, and aroma profile maps up to the tree-by-tree scale. The tool developed could significantly aid the canopy management practices in cocoa trees, which have a direct effect on cocoa quality.https://www.mdpi.com/1424-8220/19/14/3054leaf area indexcocoa beansvolatile compoundsartificial neural networksVitiCanopy app |
spellingShingle | Sigfredo Fuentes Gabriela Chacon Damir D. Torrico Andrea Zarate Claudia Gonzalez Viejo Spatial Variability of Aroma Profiles of Cocoa Trees Obtained through Computer Vision and Machine Learning Modelling: A Cover Photography and High Spatial Remote Sensing Application Sensors leaf area index cocoa beans volatile compounds artificial neural networks VitiCanopy app |
title | Spatial Variability of Aroma Profiles of Cocoa Trees Obtained through Computer Vision and Machine Learning Modelling: A Cover Photography and High Spatial Remote Sensing Application |
title_full | Spatial Variability of Aroma Profiles of Cocoa Trees Obtained through Computer Vision and Machine Learning Modelling: A Cover Photography and High Spatial Remote Sensing Application |
title_fullStr | Spatial Variability of Aroma Profiles of Cocoa Trees Obtained through Computer Vision and Machine Learning Modelling: A Cover Photography and High Spatial Remote Sensing Application |
title_full_unstemmed | Spatial Variability of Aroma Profiles of Cocoa Trees Obtained through Computer Vision and Machine Learning Modelling: A Cover Photography and High Spatial Remote Sensing Application |
title_short | Spatial Variability of Aroma Profiles of Cocoa Trees Obtained through Computer Vision and Machine Learning Modelling: A Cover Photography and High Spatial Remote Sensing Application |
title_sort | spatial variability of aroma profiles of cocoa trees obtained through computer vision and machine learning modelling a cover photography and high spatial remote sensing application |
topic | leaf area index cocoa beans volatile compounds artificial neural networks VitiCanopy app |
url | https://www.mdpi.com/1424-8220/19/14/3054 |
work_keys_str_mv | AT sigfredofuentes spatialvariabilityofaromaprofilesofcocoatreesobtainedthroughcomputervisionandmachinelearningmodellingacoverphotographyandhighspatialremotesensingapplication AT gabrielachacon spatialvariabilityofaromaprofilesofcocoatreesobtainedthroughcomputervisionandmachinelearningmodellingacoverphotographyandhighspatialremotesensingapplication AT damirdtorrico spatialvariabilityofaromaprofilesofcocoatreesobtainedthroughcomputervisionandmachinelearningmodellingacoverphotographyandhighspatialremotesensingapplication AT andreazarate spatialvariabilityofaromaprofilesofcocoatreesobtainedthroughcomputervisionandmachinelearningmodellingacoverphotographyandhighspatialremotesensingapplication AT claudiagonzalezviejo spatialvariabilityofaromaprofilesofcocoatreesobtainedthroughcomputervisionandmachinelearningmodellingacoverphotographyandhighspatialremotesensingapplication |