Detection of chlorophyll and leaf area index dynamics from sub-weekly hyperspectral imagery
KAUST DepartmentBiological and Environmental Sciences and Engineering (BESE) Division
Environmental Science and Engineering Program
Water Desalination and Reuse Research Center (WDRC)
Permanent link to this recordhttp://hdl.handle.net/10754/621234
MetadataShow full item record
AbstractTemporally rich hyperspectral time-series can provide unique time critical information on within-field variations in vegetation health and distribution needed by farmers to effectively optimize crop production. In this study, a dense timeseries of images were acquired from the Earth Observing-1 (EO-1) Hyperion sensor over an intensive farming area in the center of Saudi Arabia. After correction for atmospheric effects, optimal links between carefully selected explanatory hyperspectral vegetation indices and target vegetation characteristics were established using a machine learning approach. A dataset of in-situ measured leaf chlorophyll (Chll) and leaf area index (LAI), collected during five intensive field campaigns over a variety of crop types, were used to train the rule-based predictive models. The ability of the narrow-band hyperspectral reflectance information to robustly assess and discriminate dynamics in foliar biochemistry and biomass through empirical relationships were investigated. This also involved evaluations of the generalization and reproducibility of the predictions beyond the conditions of the training dataset. The very high temporal resolution of the satellite retrievals constituted a specifically intriguing feature that facilitated detection of total canopy Chl and LAI dynamics down to sub-weekly intervals. The study advocates the benefits associated with the availability of optimum spectral and temporal resolution spaceborne observations for agricultural management purposes.
CitationHouborg R, McCabe MF, Angel Y, Middleton EM (2016) Detection of chlorophyll and leaf area index dynamics from sub-weekly hyperspectral imagery. Remote Sensing for Agriculture, Ecosystems, and Hydrology XVIII. Available: http://dx.doi.org/10.1117/12.2241345.
SponsorsResearch reported in this publication was supported by the King Abdullah University of Science and Technology (KAUST). We greatly appreciate the logistical, equipment and scientific support offered to our team by Mr Jack King, Mr Alan King and employees of the Tawdeehiya Farm in Al Kharj, Saudi Arabia, without whom this research would not have been possible.
PublisherSPIE-Intl Soc Optical Eng
Conference/Event nameRemote Sensing for Agriculture, Ecosystems, and Hydrology XVIII