Hyperspectral Remote Sensing of Vegetation and Agricultural Crops uri icon


  • There are now over 40 years of research in hyperspectral remote sensing (orimaging spectroscopy) of vegetation and agricultural crops (Thenkabail etal., 2011a). Even though much of the early research in hyperspectral remotesensing was overwhelmingly focused on minerals, now there is substantialliterature in characterization, monitoring, modeling, and mapping of vegetationand agricultural crops using ground-based, platform-mounted, airborne,Unmanned Aerial Vehicle (UAV) mounted, and spaceborne hyperspectralremote sensing (Swatantran et al., 2011; Atzberger, 2013; Middleton et al., 2013;Schlemmer et al., 2013; Thenkabail et al., 2013; Udelhoven et al., 2013; Zhanget al., 2013). The state-of-the-art in hyperspectral remote sensing of vegetationand agriculture shows significant enhancement over conventional remotesensing, leading to improved and targeted modeling and mapping of specificagricultural characteristics such as: (a) biophysical and biochemical quantities(Galv√£o, 2011; Clark and Roberts, 2012), (b) crop type\species (Thenkabailet al., 2013), (c) management and stress factors such as nitrogen deficiency,moisture deficiency, or drought conditions (Delalieux et al., 2009; Gitelson,2013; Slonecker et al., 2013), and (d) water use and water productivities(Thenkabail et al., 2013). At the same time, overcoming Hughes? phenomenonor curse of dimensionality of data and data redundancy (Plaza et al., 2009)is of great importance to make rapid advances in a much wider utilization ofhyperspectral data. This is because, for a specific application, a large numberof hyperspectral bands are redundant (Thenkabail et al., 2013). Selecting therelevant bands will require the use of data mining techniques (Burger andGowen, 2011) to focus on utilizing the optimal or best ones to maximize theefficiency of data use and reduce unnecessary computing

publication date

  • 2014