Advances in Agriculture and Agricultural Sciences

ISSN 2756-326X

Advances in Agriculture and Agricultural Sciences | Vol. 12, No. 9, September 2026 | pp. 301–308

DOI: 10.46882/2026.AAAS.120904

Research Article

Title: Hyperspectral Canopy Imaging Coupled with Random Forest Algorithms Enables Pre-Symptomatic Detection of Stripe Rust in Winter Wheat

Names of Authors: Al-Mansoor, T. R.¹, Moreau, C. D.², and Gomez, E. F.³

Authors’ Affiliations: ¹Department of Agricultural Engineering, King Saud University, Riyadh, Saudi Arabia. ²UMR Agronomy, INRAE AgroParisTech, Palaiseau, France. ³Department of Crop Sciences, National University of La Plata, La Plata, Argentina.

Abstract: Yellow stripe rust (Puccinia striiformis f. sp. tritici) causes severe yield losses in winter wheat when fungicide applications are delayed until visible foliar pustules appear. Unmanned aerial vehicles equipped with visible-near-infrared hyperspectral sensors monitored inoculated and control wheat plots across four growth stages. Spectral reflectance indices were processed using Random Forest and Support Vector Machine classifiers to identify early physiological stress prior to visual symptom expression. The Random Forest model achieved 91.8% classification accuracy five days before visual lesion emergence, driven primarily by shifts in the red-edge (705–740 nm) and water-absorption bands. Targeted fungicide spraying guided by early hyperspectral maps reduced total chemical volume by 44.0% while preserving grain yield parity with prophylactic broadcast spraying. Aerial hyperspectral analytics support precision disease management and lower agrochemical inputs in cereal production.

Keywords: Precision agriculture; Hyperspectral remote sensing; Puccinia striiformis; Machine learning; Disease early detection; Winter wheat.

Manuscript Timeline: Received July 25, 2026; Revised August 30, 2026; Accepted September 09, 2026; Published September 16, 2026.

Citation: Al-Mansoor, T. R., Moreau, C. D., and Gomez, E. F. (2026). Hyperspectral Canopy Imaging Coupled with Random Forest Algorithms Enables Pre-Symptomatic Detection of Stripe Rust in Winter Wheat. Advances in Agriculture and Agricultural Sciences, 12(9), pp. 301–308.