Detection of banana plants and their major diseases through aerial images and machine learning methods: A case study in DR Congo and Republic of Benin

Front-line remote sensing tools, coupled with machine learning (ML), have a significant role in crop monitoring and disease surveillance. Crop type classification and a disease early warning system are some of these remote sensing applications that provide precise, timely, and cost-effective informa...

Descripción completa

Detalles Bibliográficos
Autores principales: Gómez Selvaraj, Michael, Vergara, Alejandro, Montenegro, Frank, Alonso Ruiz, Henry, Safari, Nancy, Raymaekers, Dries, Ocimati, Walter, Ntamwira, Jules Bagula, Tits, Laurent, Omondi, Bonaventure Aman Oduor, Blomme, Guy
Formato: Journal Article
Lenguaje:Inglés
Publicado: Elsevier 2020
Materias:
Acceso en línea:https://hdl.handle.net/10568/110670
_version_ 1855537195531632640
author Gómez Selvaraj, Michael
Vergara, Alejandro
Montenegro, Frank
Alonso Ruiz, Henry
Safari, Nancy
Raymaekers, Dries
Ocimati, Walter
Ntamwira, Jules Bagula
Tits, Laurent
Omondi, Bonaventure Aman Oduor
Blomme, Guy
author_browse Alonso Ruiz, Henry
Blomme, Guy
Gómez Selvaraj, Michael
Montenegro, Frank
Ntamwira, Jules Bagula
Ocimati, Walter
Omondi, Bonaventure Aman Oduor
Raymaekers, Dries
Safari, Nancy
Tits, Laurent
Vergara, Alejandro
author_facet Gómez Selvaraj, Michael
Vergara, Alejandro
Montenegro, Frank
Alonso Ruiz, Henry
Safari, Nancy
Raymaekers, Dries
Ocimati, Walter
Ntamwira, Jules Bagula
Tits, Laurent
Omondi, Bonaventure Aman Oduor
Blomme, Guy
author_sort Gómez Selvaraj, Michael
collection Repository of Agricultural Research Outputs (CGSpace)
description Front-line remote sensing tools, coupled with machine learning (ML), have a significant role in crop monitoring and disease surveillance. Crop type classification and a disease early warning system are some of these remote sensing applications that provide precise, timely, and cost-effective information at different spatial, temporal, and spectral resolutions. To our knowledge, most disease surveillance systems focus on a single-sensor based solutions and lagging the integration of multiple information sources. Moreover, monitoring larger landscapes using unmanned aerial vehicles (UAV) are challenging, and, therefore combining high resolution satellite imagery data with advanced machine learning (ML) models through the use of mobile apps could help detect and classify banana plants and provide more information on its overall health status. In this study, we classified banana under mixed-complex African landscapes through pixel-based classifications and ML models derived from multi-level satellite images (Sentinel 2, PlanetScope and WorldView-2) and UAV (MicaSense RedEdge) platforms. Our pixel-based classification from random forest (RF) model using combined features of vegetation indices (VIs) and principal component analysis (PCA) showed up to 97% overall accuracy (OA) with less than 10% omission and commission errors (OE and CE) and Kappa coefficient of 0.96 in high resolution multispectral images. We used UAV-RGB aerial images from DR Congo and Republic of Benin fields to develop a mixed-model system combining object detection model (RetinaNet) and a custom classifier for simultaneous banana localization and disease classification. Their accuracies were tested using different performance metrics. Our UAV-RGB mixed-model revealed that the developed object detection and classification model successfully classified healthy and diseased plants with 99.4%, 92.8%, 93.3% and 90.8% accuracy for the four classes: banana bunchy top disease (BBTD), Xanthomonas Wilt of Banana (BXW), healthy banana cluster and individual banana plants, respectively. These approaches of aerial image-based ML models have high potential to provide a decision support system for major banana diseases in Africa
format Journal Article
id CGSpace110670
institution CGIAR Consortium
language Inglés
publishDate 2020
publishDateRange 2020
publishDateSort 2020
publisher Elsevier
publisherStr Elsevier
record_format dspace
spelling CGSpace1106702025-11-11T19:03:59Z Detection of banana plants and their major diseases through aerial images and machine learning methods: A case study in DR Congo and Republic of Benin Gómez Selvaraj, Michael Vergara, Alejandro Montenegro, Frank Alonso Ruiz, Henry Safari, Nancy Raymaekers, Dries Ocimati, Walter Ntamwira, Jules Bagula Tits, Laurent Omondi, Bonaventure Aman Oduor Blomme, Guy artificial intelligence machine learning remote sensing disease recognition satellite imagery disease surveillance classification bananas inteligencia artificial aprendizaje electrónico vigilancia de enfermedades imágenes por satélites Front-line remote sensing tools, coupled with machine learning (ML), have a significant role in crop monitoring and disease surveillance. Crop type classification and a disease early warning system are some of these remote sensing applications that provide precise, timely, and cost-effective information at different spatial, temporal, and spectral resolutions. To our knowledge, most disease surveillance systems focus on a single-sensor based solutions and lagging the integration of multiple information sources. Moreover, monitoring larger landscapes using unmanned aerial vehicles (UAV) are challenging, and, therefore combining high resolution satellite imagery data with advanced machine learning (ML) models through the use of mobile apps could help detect and classify banana plants and provide more information on its overall health status. In this study, we classified banana under mixed-complex African landscapes through pixel-based classifications and ML models derived from multi-level satellite images (Sentinel 2, PlanetScope and WorldView-2) and UAV (MicaSense RedEdge) platforms. Our pixel-based classification from random forest (RF) model using combined features of vegetation indices (VIs) and principal component analysis (PCA) showed up to 97% overall accuracy (OA) with less than 10% omission and commission errors (OE and CE) and Kappa coefficient of 0.96 in high resolution multispectral images. We used UAV-RGB aerial images from DR Congo and Republic of Benin fields to develop a mixed-model system combining object detection model (RetinaNet) and a custom classifier for simultaneous banana localization and disease classification. Their accuracies were tested using different performance metrics. Our UAV-RGB mixed-model revealed that the developed object detection and classification model successfully classified healthy and diseased plants with 99.4%, 92.8%, 93.3% and 90.8% accuracy for the four classes: banana bunchy top disease (BBTD), Xanthomonas Wilt of Banana (BXW), healthy banana cluster and individual banana plants, respectively. These approaches of aerial image-based ML models have high potential to provide a decision support system for major banana diseases in Africa 2020-11 2020-12-30T17:58:09Z 2020-12-30T17:58:09Z Journal Article https://hdl.handle.net/10568/110670 en Open Access application/pdf Elsevier Gomez Selvaraj, M.; Vergara, A.; Montenegro, F.; Alonso Ruiz, H.; Safari, N.; Raymaekers, D.; Ocimati, W.; Ntamwira, J.; Tits, L.; Omondi, A.B.; Blomme, G. (2020) Detection of banana plants and their major diseases through aerial images and machine learning methods: A case study in DR Congo and Republic of Benin. ISPRS Journal of Photogrammetry and Remote Sensing 169 p. 110-124. ISSN: 1872-8235.
spellingShingle artificial intelligence
machine learning
remote sensing
disease recognition
satellite imagery
disease surveillance
classification
bananas
inteligencia artificial
aprendizaje electrónico
vigilancia de enfermedades
imágenes por satélites
Gómez Selvaraj, Michael
Vergara, Alejandro
Montenegro, Frank
Alonso Ruiz, Henry
Safari, Nancy
Raymaekers, Dries
Ocimati, Walter
Ntamwira, Jules Bagula
Tits, Laurent
Omondi, Bonaventure Aman Oduor
Blomme, Guy
Detection of banana plants and their major diseases through aerial images and machine learning methods: A case study in DR Congo and Republic of Benin
title Detection of banana plants and their major diseases through aerial images and machine learning methods: A case study in DR Congo and Republic of Benin
title_full Detection of banana plants and their major diseases through aerial images and machine learning methods: A case study in DR Congo and Republic of Benin
title_fullStr Detection of banana plants and their major diseases through aerial images and machine learning methods: A case study in DR Congo and Republic of Benin
title_full_unstemmed Detection of banana plants and their major diseases through aerial images and machine learning methods: A case study in DR Congo and Republic of Benin
title_short Detection of banana plants and their major diseases through aerial images and machine learning methods: A case study in DR Congo and Republic of Benin
title_sort detection of banana plants and their major diseases through aerial images and machine learning methods a case study in dr congo and republic of benin
topic artificial intelligence
machine learning
remote sensing
disease recognition
satellite imagery
disease surveillance
classification
bananas
inteligencia artificial
aprendizaje electrónico
vigilancia de enfermedades
imágenes por satélites
url https://hdl.handle.net/10568/110670
work_keys_str_mv AT gomezselvarajmichael detectionofbananaplantsandtheirmajordiseasesthroughaerialimagesandmachinelearningmethodsacasestudyindrcongoandrepublicofbenin
AT vergaraalejandro detectionofbananaplantsandtheirmajordiseasesthroughaerialimagesandmachinelearningmethodsacasestudyindrcongoandrepublicofbenin
AT montenegrofrank detectionofbananaplantsandtheirmajordiseasesthroughaerialimagesandmachinelearningmethodsacasestudyindrcongoandrepublicofbenin
AT alonsoruizhenry detectionofbananaplantsandtheirmajordiseasesthroughaerialimagesandmachinelearningmethodsacasestudyindrcongoandrepublicofbenin
AT safarinancy detectionofbananaplantsandtheirmajordiseasesthroughaerialimagesandmachinelearningmethodsacasestudyindrcongoandrepublicofbenin
AT raymaekersdries detectionofbananaplantsandtheirmajordiseasesthroughaerialimagesandmachinelearningmethodsacasestudyindrcongoandrepublicofbenin
AT ocimatiwalter detectionofbananaplantsandtheirmajordiseasesthroughaerialimagesandmachinelearningmethodsacasestudyindrcongoandrepublicofbenin
AT ntamwirajulesbagula detectionofbananaplantsandtheirmajordiseasesthroughaerialimagesandmachinelearningmethodsacasestudyindrcongoandrepublicofbenin
AT titslaurent detectionofbananaplantsandtheirmajordiseasesthroughaerialimagesandmachinelearningmethodsacasestudyindrcongoandrepublicofbenin
AT omondibonaventureamanoduor detectionofbananaplantsandtheirmajordiseasesthroughaerialimagesandmachinelearningmethodsacasestudyindrcongoandrepublicofbenin
AT blommeguy detectionofbananaplantsandtheirmajordiseasesthroughaerialimagesandmachinelearningmethodsacasestudyindrcongoandrepublicofbenin