Detection of chlorophyll and leaf area index dynamics from sub-weekly hyperspectral imagery

Handle URI:
http://hdl.handle.net/10754/621234
Title:
Detection of chlorophyll and leaf area index dynamics from sub-weekly hyperspectral imagery
Authors:
Houborg, Rasmus; McCabe, Matthew ( 0000-0002-1279-5272 ) ; Angel, Yoseline; Middleton, Elizabeth M.
Abstract:
Temporally 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.
KAUST Department:
Biological and Environmental Sciences and Engineering (BESE) Division; Water Desalination and Reuse Research Center (WDRC)
Citation:
Houborg 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.
Publisher:
SPIE-Intl Soc Optical Eng
Journal:
Remote Sensing for Agriculture, Ecosystems, and Hydrology XVIII
Conference/Event name:
Remote Sensing for Agriculture, Ecosystems, and Hydrology XVIII
Issue Date:
25-Oct-2016
DOI:
10.1117/12.2241345
Type:
Conference Paper
Sponsors:
Research 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.
Additional Links:
http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=2577833
Appears in Collections:
Conference Papers; Water Desalination and Reuse Research Center (WDRC); Biological and Environmental Sciences and Engineering (BESE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorHouborg, Rasmusen
dc.contributor.authorMcCabe, Matthewen
dc.contributor.authorAngel, Yoselineen
dc.contributor.authorMiddleton, Elizabeth M.en
dc.date.accessioned2016-10-30T06:23:30Z-
dc.date.available2016-10-30T06:23:30Z-
dc.date.issued2016-10-25en
dc.identifier.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.en
dc.identifier.doi10.1117/12.2241345en
dc.identifier.urihttp://hdl.handle.net/10754/621234-
dc.description.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.en
dc.description.sponsorshipResearch 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.en
dc.publisherSPIE-Intl Soc Optical Engen
dc.relation.urlhttp://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=2577833en
dc.rightsCopyright 2016 Society of Photo Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.en
dc.subjectLAIen
dc.subjectTotal canopy chlorophyllen
dc.subjectCubisten
dc.subjectHyperionen
dc.subjectHyperspectralen
dc.subjectDrylanden
dc.subjectVegetation indicesen
dc.titleDetection of chlorophyll and leaf area index dynamics from sub-weekly hyperspectral imageryen
dc.typeConference Paperen
dc.contributor.departmentBiological and Environmental Sciences and Engineering (BESE) Divisionen
dc.contributor.departmentWater Desalination and Reuse Research Center (WDRC)en
dc.identifier.journalRemote Sensing for Agriculture, Ecosystems, and Hydrology XVIIIen
dc.conference.dateSeptember 26, 2016en
dc.conference.nameRemote Sensing for Agriculture, Ecosystems, and Hydrology XVIIIen
dc.conference.locationEdinburgh, United Kingdomen
dc.eprint.versionPublisher's Version/PDFen
dc.contributor.institutionNASA Goddard Space Flight Center (GSFC), Greenbelt, Maryland, U.S.Aen
kaust.authorHouborg, Rasmusen
kaust.authorMcCabe, Matthewen
kaust.authorAngel, Yoselineen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.