UAV-Based Disease Detection in Palm Groves of <i>Phoenix canariensis</i> Using Machine Learning and Multispectral Imagery
Climate change and the appearance of pests and pathogens are leading to the disappearance of palm groves of <i>Phoenix canariensis</i> in the Canary Islands. Traditional pathology diagnostic techniques are resource-demanding and poorly reproducible, and it is necessary to develop new mon...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/14/3584 |
| _version_ | 1797587570905841664 |
|---|---|
| author | Enrique Casas Manuel Arbelo José A. Moreno-Ruiz Pedro A. Hernández-Leal José A. Reyes-Carlos |
| author_facet | Enrique Casas Manuel Arbelo José A. Moreno-Ruiz Pedro A. Hernández-Leal José A. Reyes-Carlos |
| author_sort | Enrique Casas |
| collection | DOAJ |
| description | Climate change and the appearance of pests and pathogens are leading to the disappearance of palm groves of <i>Phoenix canariensis</i> in the Canary Islands. Traditional pathology diagnostic techniques are resource-demanding and poorly reproducible, and it is necessary to develop new monitoring methodologies. This study presents a tool to identify individuals infected by <i>Serenomyces phoenicis</i> and <i>Phoenicococcus marlatti</i> using UAV-derived multispectral images and machine learning. In the first step, image segmentation and classification techniques allowed us to calculate a relative prevalence of affected leaves at an individual scale for each palm tree, so that we could finally use this information with labelled in situ data to build a probabilistic classification model to detect infected specimens. Both the pixel classification performance and the model’s fitness were evaluated using different metrics such as omission and commission errors, accuracy, precision, recall, and F1-score. It is worth noting the accuracy of more than 0.96 obtained for the pixel classification of the affected and healthy leaves, and the good detection ability of the probabilistic classification model, which reached an accuracy of 0.87 for infected palm trees. The proposed methodology is presented as an efficient tool for identifying infected palm specimens, using spectral information, reducing the need for fieldwork and facilitating phytosanitary treatment. |
| first_indexed | 2024-03-11T00:40:46Z |
| format | Article |
| id | doaj.art-2b792d2e6e7f4b4eadb682613f9aca0e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T00:40:46Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2b792d2e6e7f4b4eadb682613f9aca0e2023-11-18T21:12:51ZengMDPI AGRemote Sensing2072-42922023-07-011514358410.3390/rs15143584UAV-Based Disease Detection in Palm Groves of <i>Phoenix canariensis</i> Using Machine Learning and Multispectral ImageryEnrique Casas0Manuel Arbelo1José A. Moreno-Ruiz2Pedro A. Hernández-Leal3José A. Reyes-Carlos4Departamento de Física, Universidad de La Laguna, 38200 San Cristóbal de La Laguna, SpainDepartamento de Física, Universidad de La Laguna, 38200 San Cristóbal de La Laguna, SpainDepartamento de Informática, Universidad de Almería, 04120 Almería, SpainDepartamento de Física, Universidad de La Laguna, 38200 San Cristóbal de La Laguna, SpainSección de Sanidad Vegetal, Dirección General de Agricultura, Consejería de Agricultura, Ganadería y Pesca, 47014 Santa Cruz de Tenerife, SpainClimate change and the appearance of pests and pathogens are leading to the disappearance of palm groves of <i>Phoenix canariensis</i> in the Canary Islands. Traditional pathology diagnostic techniques are resource-demanding and poorly reproducible, and it is necessary to develop new monitoring methodologies. This study presents a tool to identify individuals infected by <i>Serenomyces phoenicis</i> and <i>Phoenicococcus marlatti</i> using UAV-derived multispectral images and machine learning. In the first step, image segmentation and classification techniques allowed us to calculate a relative prevalence of affected leaves at an individual scale for each palm tree, so that we could finally use this information with labelled in situ data to build a probabilistic classification model to detect infected specimens. Both the pixel classification performance and the model’s fitness were evaluated using different metrics such as omission and commission errors, accuracy, precision, recall, and F1-score. It is worth noting the accuracy of more than 0.96 obtained for the pixel classification of the affected and healthy leaves, and the good detection ability of the probabilistic classification model, which reached an accuracy of 0.87 for infected palm trees. The proposed methodology is presented as an efficient tool for identifying infected palm specimens, using spectral information, reducing the need for fieldwork and facilitating phytosanitary treatment.https://www.mdpi.com/2072-4292/15/14/3584probabilistic classification modellingsupport vector machinerandom forestspectral separability analysisstructure insensitive pigment indexNDVI |
| spellingShingle | Enrique Casas Manuel Arbelo José A. Moreno-Ruiz Pedro A. Hernández-Leal José A. Reyes-Carlos UAV-Based Disease Detection in Palm Groves of <i>Phoenix canariensis</i> Using Machine Learning and Multispectral Imagery Remote Sensing probabilistic classification modelling support vector machine random forest spectral separability analysis structure insensitive pigment index NDVI |
| title | UAV-Based Disease Detection in Palm Groves of <i>Phoenix canariensis</i> Using Machine Learning and Multispectral Imagery |
| title_full | UAV-Based Disease Detection in Palm Groves of <i>Phoenix canariensis</i> Using Machine Learning and Multispectral Imagery |
| title_fullStr | UAV-Based Disease Detection in Palm Groves of <i>Phoenix canariensis</i> Using Machine Learning and Multispectral Imagery |
| title_full_unstemmed | UAV-Based Disease Detection in Palm Groves of <i>Phoenix canariensis</i> Using Machine Learning and Multispectral Imagery |
| title_short | UAV-Based Disease Detection in Palm Groves of <i>Phoenix canariensis</i> Using Machine Learning and Multispectral Imagery |
| title_sort | uav based disease detection in palm groves of i phoenix canariensis i using machine learning and multispectral imagery |
| topic | probabilistic classification modelling support vector machine random forest spectral separability analysis structure insensitive pigment index NDVI |
| url | https://www.mdpi.com/2072-4292/15/14/3584 |
| work_keys_str_mv | AT enriquecasas uavbaseddiseasedetectioninpalmgrovesofiphoenixcanariensisiusingmachinelearningandmultispectralimagery AT manuelarbelo uavbaseddiseasedetectioninpalmgrovesofiphoenixcanariensisiusingmachinelearningandmultispectralimagery AT joseamorenoruiz uavbaseddiseasedetectioninpalmgrovesofiphoenixcanariensisiusingmachinelearningandmultispectralimagery AT pedroahernandezleal uavbaseddiseasedetectioninpalmgrovesofiphoenixcanariensisiusingmachinelearningandmultispectralimagery AT joseareyescarlos uavbaseddiseasedetectioninpalmgrovesofiphoenixcanariensisiusingmachinelearningandmultispectralimagery |