article · Smart Agricultural Technology
Global food security faces several threats, including the increasing global population, which is putting pressure on an already overutilized agricultural industry. The production of food crops such as wheat, corn, rice, and potatoes is itself hindered by many abiotic and biotic factors, including pests and diseases. Traditionally, plant disease detection has been sought through field scouting, which relies on visual symptoms. These are not always accurate, and oversights often lead to secondary epidemic outbreaks. To overcome such limitations, hyperspectral imaging and spectroscopy have emerged as non-invasive technologies for early detection of plant diseases. They have the potential to identify subtle physiological changes in plants before visual symptoms. Globally, these approaches have been widely used for plant disease detection, but very few hyperspectral-based plant disease detection studies have been reported in Canada. This review critically synthesizes the application of hyperspectral techniques in agriculture, with a focus on potato diseases in both the global and Canadian contexts. Most of the studies using these approaches were conducted under controlled conditions. Like with many other methods, translation of lab-based models to real farmer fields faces reduced performance because of environmental variability, complex backgrounds, and sensor and illumination differences, including confounding responses between biotic and abiotic stresses. This review aims (i) to highlight the key limitations to the deployment of hyperspectral imaging for large-scale disease detection, i.e., the workflow differences from image acquisition to model establishment under laboratory and field conditions, and (ii) to provide a perspective bridging the gap between experimental research and real-world application of hyperspectral techniques. This is meant to lay the foundation for the development and implementation of earlier and more accurate plant disease detection tools.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.atech.2026.102500
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.