Skip to main content
ARS Home » Pacific West Area » Pendleton, Oregon » Columbia Plateau Conservation Research Center » Research » Publications at this Location » Publication #317383
Title: Spectral considerations for modeling yield of canola

Author
item Sulik, John
item Long, Daniel

Submitted to: Remote Sensing of Environment
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/22/2016
Publication Date: 7/1/2016
Publication URL: https://handle.nal.usda.gov/10113/5246375
Citation: Sulik, J.J., Long, D.S. 2016. Spectral considerations for modeling yield of canola. Remote Sensing of Environment. 184:161-174.

Interpretive Summary: A spectral index for multispectral sensors is presented that correlates with yield variability for Brassica oilseed crops. Here we present a normalized difference yellowness index (NDYI) to model variability in within-field relative yield potential and overcome limitations of the normalized difference vegetation index (NDVI) during flowering. NDYI only requires wavebands in the visible region of the spectrum and can be applied to any satellite or aerial sensor that has blue and green channels. The derivation of the NDYI is based on the absorption feature of carotenoids present in the floral tissue of Brassica oilseeds such as canola. Empirical measurements and theoretical analyses suggest that NDYI is better correlated with final yield than other commonly used indices such as NDVI. Overall, NDYI is found to have a more linear relationship with final yield than NDVI, with NDVI saturating at high yield values. In addition, NDVI is confounded by variation in flowering whereas NDYI directly exploits variation in flowering. This highlights the benefit of using a spectral index that is sensitive to reproductive growth of vegetation instead of vegetative growth for crops with spectrally prominent reproductive canopy elements. Our results indicate that NDYI is a better indicator of yield potential than NDVI during mid-season development stages.

Technical Abstract: Conspicuous yellow flowers that are present in a Brassica oilseed crop such as canola require careful consideration when selecting a spectral index for yield estimation. This study evaluated spectral indices for multispectral sensors that correlate with the seed yield of Brassica oilseed crops. A small-plot experiment was conducted near Pendleton, Oregon in which spring canola was grown under varying water regimes and nitrogen treatments to create a wide range in oilseed yield. Plot measurements consisted of canopy reflectance at flowering using a hand-held spectroradiometer and seed yield at physiological maturity. Spectroradiometric measurements were converted to MODIS band equivalent reflectance. Selected indices were computed from spectra obtained with the radiometer and correlated with seed yield. A normalized difference yellowness index (NDYI), computed from the green and blue wavebands, overcame limitations of the normalized difference vegetation index (NDVI) during flowering and best modeled variability in relative yield potential. NDYI was more linear and correlated with county-wide oilseed yield data and MODIS satellite data from North Dakota (r2 = 0.72) than NDVI (r2 = 0.66). NDYI only requires wavebands in the visible region of the spectrum and can be applied to any satellite or aerial sensor that has blue and green channels. These findings highlight the benefit of using a spectral index that is sensitive to reproductive growth of vegetation instead of vegetative growth for crops with spectrally prominent reproductive canopy elements. Our results indicate that NDYI is a better indicator of yield potential than NDVI during mid-season development stages.