A research team has developed a wheat powdery mildew index (WPMI) that enables accurate detection and monitoring of a major fungal disease in winter wheat using unmanned aerial vehicle (UAV) hyperspectral imagery, according to a study published in the Journal of Remote Sensing on April 10, 2026. The index provides a practical tool for identifying infected areas and tracking disease spread or recovery across multiple spatial scales, from leaf to field level.
Wheat powdery mildew (WPM) is a destructive fungal disease that damages leaf tissues, weakens plant growth, and can cause severe yield losses or crop failure. Current field diagnosis relies heavily on expert visual inspection, which is labor-intensive, subjective, and difficult to scale. Although hyperspectral remote sensing has shown promise, many existing vegetation indices (VIs) were developed for general pigment or stress monitoring rather than specific disease detection. Machine learning methods also require large, high-quality training datasets. The study addressed the need for rapid, field-scale monitoring of WPM in smallholder farms, where disease spread can be spatially uneven.
The researchers developed two forms of WPMI: WPMIG = (R760 − R554)/(R661 + R554) and WPMIR = (R760 − R661)/(R661 + R554). These indices use disease-sensitive bands in the green, red, and near-infrared (NIR) regions. Compared with traditional VIs, WPMI more consistently distinguished healthy and infected wheat and better quantified disease index (DI) across leaf, ground canopy, and UAV canopy scales. WPMIG showed particularly strong performance and was selected for UAV-based hot-spot analysis to reveal potential infection and recovery areas.
The team collected three years of data from greenhouse and field experiments (2022–2024), including 1,260 leaf spectra and 804 canopy spectra. At the leaf scale, WPMI achieved the highest overall classification accuracy, reaching 85% and 86% for WPMIG and WPMIR, respectively, in 2022 greenhouse experiments. In field conditions, the indices achieved 80–81% accuracy. For disease severity estimation, WPMIG reached R² values of 0.55 to 0.93 at the ground scale and 0.48 to 0.90 at the UAV scale. UAV-derived WPMIG maps, combined with Getis–Ord Gᵢ* hot-spot analysis, identified clusters of likely infection and tracked spatiotemporal changes over three growing seasons.
The researchers noted that a disease-specific spectral index can move crop disease monitoring beyond simple image comparison. By linking UAV hyperspectral imagery with spatial analysis, the method can help reveal where WPM is emerging, expanding, or declining, offering a basis for earlier warning and more targeted disease management. The approach may help farmers identify disease hot spots before severe outbreaks occur, reduce unnecessary pesticide use, and improve field-level decision-making.
With further validation across regions, wheat varieties, sensors, and disease conditions, WPMI-based UAV monitoring could support precision plant protection and early warning systems for wheat production. More broadly, this strategy provides a framework for developing disease-specific remote sensing indices for other crop–pathogen systems, contributing to smarter and more resilient agricultural monitoring. The study was supported by multiple funding sources, including the National Key Research and Development Program and the National Natural Science Fund. The full study is available at https://spj.science.org/doi/10.34133/remotesensing.0955.
