Skip to main content
ARS Home » Northeast Area » Kearneysville, West Virginia » Appalachian Fruit Research Laboratory » Innovative Fruit Production, Improvement, and Protection » Research » Publications at this Location » Publication #265489
Title: Hyperspectral image analysis for water stress detection of apple trees

Author
item KIM, YUNSEOP - Purdue University
item Glenn, David
item PARK, JOHNNY - Purdue University
item NGUGI, HENRY - Pennsylvania State University
item LEHMAN, BRIAN - Pennsylvania State University

Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 4/22/2011
Publication Date: 7/1/2011
Citation: Kim, Y.J., Glenn, D.M., Park, J., Ngugi, H.K., Lehman, B.L. 2011. Hyperspectral image analysis for water stress detection of apple trees. Computers and Electronics in Agriculture. 77:155-160.

Interpretive Summary: Plant water stress significantly reduces plant productivity. Mapping of plant stress in the field would allow growers to recognize and correct the problem before critical thresholds of water stress are exceeded and so maximize productivity. Five different levels of water stress were created in young ‘Gala’ apple trees in a greenhouse. The trees were periodically monitored with a hyperspectral camera that measured reflectance in the visible and near-infrared range, a spectral vegetation sensor, and a digital color camera. Various spectral indices were calculated and correlated to water stress levels. The experimental results indicated that intelligent optical sensors could deliver decision support for water stress detection and management.

Technical Abstract: Plant stress significantly reduces plant productivity. Automated on-the-go mapping of plant stress would allow for a timely intervention and mitigation of the problem before critical thresholds are exceeded, thereby maximizing productivity. The spectral signature of plant leaves was analyzed by a hyperspectral camera to identify the onset and intensity of plant water stress. Five different levels of water treatment were created in young apple trees (cv. 'Buckeye Gala') in a greenhouse. The trees were periodically monitored with a hyperspectral camera along with an active-illuminated spectral vegetation sensor and a digital color camera. Individual spectral images over a 400 - 1000 nm wavelength range were extracted at a specific wavelength to estimate reflectance and generate spectral profiles for the five different water treatment levels. Various spectral indices were calculated and correlated to stress levels. The highest correlation was found with Red Edge NDVI at 705 nm and 750 nm in narrowband indices and NDVI at 680 nm and 800 nm in broadband indices. The experimental results indicated that intelligent optical sensors could deliver decision support for plant stress detection and management.