Review Article

Hyperspectral Remote Sensing in Precision Agriculture: Comprehensive Review of Applications and Emerging Technologies

Satyam Shah

School of Geography, Geology and the Environment, University of Leicester, University Road, LE1 7RH, Leicester, United Kingdom

*Corresponding author e-mail: satyamshah444@gmail.com

(Received: 18/02/2026; Revised: 18/05/2026; Accepted: 15/06/2026; Published: 20/06/2026)

ABSTRACT

Hyperspectral remote sensing has emerged as a transformative technology for precision agriculture, enabling detailed characterisation of crop properties, stress conditions, and soil attributes across diverse agricultural landscapes. Unlike conventional multispectral sensors, hyperspectral imaging systems acquire data in hundreds of narrow contiguous spectral bands, facilitating detection of subtle biochemical and biophysical features associated with crop health, nutrient status, and disease. This review systematically synthesises the literature on hyperspectral remote sensing applications in precision agriculture published between 2018 and 2025. The methodology involved comprehensive database searches across Scopus, Web of Science, and Google Scholar, with inclusion criteria focusing on peer-reviewed articles addressing hyperspectral platforms, crop classification, biochemical parameter retrieval, stress detection, yield estimation, soil assessment, and machine learning approaches. Results indicate that satellite missions, including PRISMA, EnMAP, and EMIT, now provide operational spaceborne hyperspectral data for agricultural monitoring at regional scales, complemented by airborne and unmanned aerial vehicle platforms for field-scale applications. Deep learning architectures, including convolutional neural networks and transformer models, have substantially improved classification and retrieval accuracy, with reported accuracies of 90-97% for crop classification tasks. Pre-symptomatic disease detection achieves 85-93% accuracy with detection lead times of 5-10 days. Key challenges include atmospheric correction uncertainties, limited temporal revisit for current satellite missions, and integration with farm management systems. Future missions, including NASA’s Surface Biology and Geology and ESA’s CHIME will expand global hyperspectral data availability, while advances in artificial intelligence promise automated, scalable analysis workflows for operational precision agriculture.

Keywords: hyperspectral remote sensing, precision agriculture, crop monitoring, disease detection, machine learning

[Fulltext PDF]