Digital framework for georeferenced multiplatform surveillance of banana wilt using human in the loop AI and YOLO foundation models

Abstract Bananas (Musa spp.) are a critical global food crop, providing a primary source of nutrition for millions of people. Traditional methods for disease monitoring and detection are often time-consuming, labor-intensive, and prone to inaccuracies. This study introduces an AI-powered multiplatfo...

Full description

Saved in:
Bibliographic Details
Main Authors: Juan Jose Mora, Guy Blomme, Nancy Safari, Sivalingam Elayabalan, Ramasamy Selvarajan, Michael Gomez Selvaraj
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-87588-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832571659406540800
author Juan Jose Mora
Guy Blomme
Nancy Safari
Sivalingam Elayabalan
Ramasamy Selvarajan
Michael Gomez Selvaraj
author_facet Juan Jose Mora
Guy Blomme
Nancy Safari
Sivalingam Elayabalan
Ramasamy Selvarajan
Michael Gomez Selvaraj
author_sort Juan Jose Mora
collection DOAJ
description Abstract Bananas (Musa spp.) are a critical global food crop, providing a primary source of nutrition for millions of people. Traditional methods for disease monitoring and detection are often time-consuming, labor-intensive, and prone to inaccuracies. This study introduces an AI-powered multiplatform georeferenced surveillance system designed to enhance the detection and management of banana wilt diseases. We developed and evaluated several deep learning foundation models, including YOLO-NAS, YOLOv8, YOLOv9, and Faster-RCNN to perform accurate disease detection on both platforms. Our results demonstrate the superior performance of YOLOv9 in detecting healthy, Fusarium Wilt and Xanthomonas Wilt diseased plants in aerial images, achieving high mAP@50, precision and recall metrics ranging from 55 to 86%. In terms of ground level images, we organized the dataset based on disease occurrence in Africa, Latin America, India, Asia and Australia. For this platform, YOLOv8 outperforms the rest and achieves mAP@50, precision and recall between 65 and 99% depending on the plant part and region. Additionally, we incorporated Explainable AI techniques, such as Gradient-weighted Class Activation Mapping, to enhance model transparency and trustworthiness. Human in the Loop Artificial Intelligence was also utilized to enhance the ground level model’s predictions.
format Article
id doaj-art-6ce7f478a2bc427fa5d3ba337973adc9
institution Kabale University
issn 2045-2322
language English
publishDate 2025-01-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-6ce7f478a2bc427fa5d3ba337973adc92025-02-02T12:24:18ZengNature PortfolioScientific Reports2045-23222025-01-0115113010.1038/s41598-025-87588-2Digital framework for georeferenced multiplatform surveillance of banana wilt using human in the loop AI and YOLO foundation modelsJuan Jose Mora0Guy Blomme1Nancy Safari2Sivalingam Elayabalan3Ramasamy Selvarajan4Michael Gomez Selvaraj5Alliance of Bioversity International and International Center for Tropical Agriculture (CIAT)Bioversity International, c/o ILRIBioversity InternationalImayam Institute of Agriculture and Technology (IIAT), Affiliated With Tamil Nadu Agricultural University (TNAU)ICAR-National Research Centre for BananaAlliance of Bioversity International and International Center for Tropical Agriculture (CIAT)Abstract Bananas (Musa spp.) are a critical global food crop, providing a primary source of nutrition for millions of people. Traditional methods for disease monitoring and detection are often time-consuming, labor-intensive, and prone to inaccuracies. This study introduces an AI-powered multiplatform georeferenced surveillance system designed to enhance the detection and management of banana wilt diseases. We developed and evaluated several deep learning foundation models, including YOLO-NAS, YOLOv8, YOLOv9, and Faster-RCNN to perform accurate disease detection on both platforms. Our results demonstrate the superior performance of YOLOv9 in detecting healthy, Fusarium Wilt and Xanthomonas Wilt diseased plants in aerial images, achieving high mAP@50, precision and recall metrics ranging from 55 to 86%. In terms of ground level images, we organized the dataset based on disease occurrence in Africa, Latin America, India, Asia and Australia. For this platform, YOLOv8 outperforms the rest and achieves mAP@50, precision and recall between 65 and 99% depending on the plant part and region. Additionally, we incorporated Explainable AI techniques, such as Gradient-weighted Class Activation Mapping, to enhance model transparency and trustworthiness. Human in the Loop Artificial Intelligence was also utilized to enhance the ground level model’s predictions.https://doi.org/10.1038/s41598-025-87588-2
spellingShingle Juan Jose Mora
Guy Blomme
Nancy Safari
Sivalingam Elayabalan
Ramasamy Selvarajan
Michael Gomez Selvaraj
Digital framework for georeferenced multiplatform surveillance of banana wilt using human in the loop AI and YOLO foundation models
Scientific Reports
title Digital framework for georeferenced multiplatform surveillance of banana wilt using human in the loop AI and YOLO foundation models
title_full Digital framework for georeferenced multiplatform surveillance of banana wilt using human in the loop AI and YOLO foundation models
title_fullStr Digital framework for georeferenced multiplatform surveillance of banana wilt using human in the loop AI and YOLO foundation models
title_full_unstemmed Digital framework for georeferenced multiplatform surveillance of banana wilt using human in the loop AI and YOLO foundation models
title_short Digital framework for georeferenced multiplatform surveillance of banana wilt using human in the loop AI and YOLO foundation models
title_sort digital framework for georeferenced multiplatform surveillance of banana wilt using human in the loop ai and yolo foundation models
url https://doi.org/10.1038/s41598-025-87588-2
work_keys_str_mv AT juanjosemora digitalframeworkforgeoreferencedmultiplatformsurveillanceofbananawiltusinghumanintheloopaiandyolofoundationmodels
AT guyblomme digitalframeworkforgeoreferencedmultiplatformsurveillanceofbananawiltusinghumanintheloopaiandyolofoundationmodels
AT nancysafari digitalframeworkforgeoreferencedmultiplatformsurveillanceofbananawiltusinghumanintheloopaiandyolofoundationmodels
AT sivalingamelayabalan digitalframeworkforgeoreferencedmultiplatformsurveillanceofbananawiltusinghumanintheloopaiandyolofoundationmodels
AT ramasamyselvarajan digitalframeworkforgeoreferencedmultiplatformsurveillanceofbananawiltusinghumanintheloopaiandyolofoundationmodels
AT michaelgomezselvaraj digitalframeworkforgeoreferencedmultiplatformsurveillanceofbananawiltusinghumanintheloopaiandyolofoundationmodels