Page Banner

United States Department of Agriculture

Agricultural Research Service

Research Project: USING REMOTE SENSING AND GIS FOR DETECTING AND MAPPING INVASIVE WEEDS IN RIPARIAN AND WETLAND ECOSYSTEMS Title: Yield estimation from hyperspectral imagery using Spectral Angle Mapper (SAM)

Authors
item Yang, Chenghai
item Everitt, James
item Bradford, Joe

Submitted to: Transactions of the ASABE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: March 13, 2008
Publication Date: July 30, 2008
Citation: Yang, C., Everitt, J.H., Bradford, J.M. 2008. Yield estimation from hyperspectral imagery using Spectral Angle Mapper (SAM). Transactions of the ASABE. 51(2):729-737.

Interpretive Summary: Hyperspectral imagery contains nearly continuous spectral data and has the potential for better differentiation and estimation of biophysical attributes of interest. This study applied the spectral angle mapper technique to airborne hyperspectral imagery for estimating grain sorghum yield variability. Results show that grain yield was significantly related to spectral angle values and that spectral angle images derived from the hyperspectral imagery had better correlations with yield than majority of the normalized difference vegetation indices derived from the imagery. This technique provides a useful tool to convert a hyperspectral image to a single layer image to characterize relative yield variability without using actual yield data.

Technical Abstract: Vegetation indices (VIs) derived from remotely sensed imagery are commonly used to estimate crop yields. Spectral angle mapper (SAM) provides an alternative approach to quantifying the spectral differences among all pixels in imagery and therefore has the potential for mapping yield variability. The objective of this study was to apply the SAM technique to airborne hyperspectral imagery for mapping yield variability. Airborne hyperspectral imagery was acquired from two grain sorghum fields in south Texas and yield data were collected using a grain yield monitor. SAM images were generated from the hyperspectral images based on six reference spectra extracted directly from the hyperspectral images and four reflectance spectra measured on ground. Statistical analysis showed that the 10 SAM images for each field produced similar correlation coefficients with yield. For comparison, all 5151 possible narrow band normalized difference vegetation indices (NDVIs) were derived from the 102-band images and related to yield. Results showed that the SAM images based on the soil reference spectra provided higher correlation coefficients with yield than 75% and 92% of the 5151 narrow band NDVIs for fields 1 and 2, respectively. Like a NDVI image, a SAM image can be easily generated from a hyperspectral image to characterize the spatial variability in yield. However, due to the large number of NDVIs that can be derived from a hyperspectral image, a SAM image based on a single reference spectrum can be a better representation of yield variability if actual yield data are not available for the identification of the best NDVI. The results from this study indicate that the SAM technique can be used alone or in conjunction with other VIs for yield estimation from hyperspectral imagery.

Last Modified: 12/21/2014
Footer Content Back to Top of Page