Skip to main content
ARS Home » Southeast Area » Stoneville, Mississippi » Crop Production Systems Research » Research » Publications at this Location » Publication #348095

Title: Using hyperspectral data in precision farming applications

Author
item YAO, HAIBO - Mississippi State University
item Huang, Yanbo
item TANG, LIE - Iowa State University
item TIAN, LEI - University Of Illinois
item Bhatnagar, Deepak
item Cleveland, Thomas

Submitted to: CRC Press
Publication Type: Book / Chapter
Publication Acceptance Date: 8/13/2018
Publication Date: 12/11/2018
Citation: Yao, H., Huang, Y., Tang, L., Tian, L., Bhatnagar, D., Cleveland, T.E. 2018. Using hyperspectral data in precision farming applications. In: Thenkabail, P.S., Lyon, J.G., editors. Hyperspectral Remote Sensing of Vegetation. 1st Edition. Boca Raton, Florida: CRC Press. https://doi.org/10.1201/b11222.
DOI: https://doi.org/10.1201/b11222

Interpretive Summary:

Technical Abstract: Modern agriculture faces a huge challenge in providing food security and safety to the ever growing world population while at the same time trying to protect our environment and ecosystems on this planet. The development of precision agriculture provides the means to meet these challenges. Precision agriculture, or site-specific farming, aims at managing crops based on their specific needs. Remote sensing is an important part of a precision agriculture management system with hyperspectral imaging as a powerful remote sensing tool due to its superior wavelength information, including both spectra coverage and bandwidth. The image’s spatial, spectral, and temporal solutions are critical to precision agriculture applications. Hyperspectral data has been collected from many platforms including satellites, manned airplanes, ground vehicles, and unmanned aerial vehicles for implementation s in agriculture. When processing hyperspectral imagery, numerous vegetation indices have been developed for different purposes. Multivariate statistical analysis and pattern recognition procedures are also widely used. The chapter provides an overview of hyperspectral imaging in agriculture with specific topics discussed on soil property and fertility sensing, herbicide drift detection, weed mapping, crop nitrogen stress detection, crop yield estimation, insect/pest infestation identification, and the current trend in using unmanned aerial vehicles. It is expected that advances in hyperspectral sensor capability and computational power will continuously meet the needs in present agriculture, and with new applications being discovered in the future.