Skip to main content
ARS Home » Pacific West Area » Maricopa, Arizona » U.S. Arid Land Agricultural Research Center » Water Management and Conservation Research » Research » Publications at this Location » Publication #316280

Research Project: Enhancing Water Conservation and Crop Productivity in Irrigated Agriculture

Location: Water Management and Conservation Research

Title: Lesquerella seed yield estimation using color image segmentation to track flowering dynamics under water and nitrogen limitation

Author
item Thorp, Kelly
item WANG, G - Bridgestone Americas Tire Operations
item BADARUDDIN, M - University Of Arizona
item Bronson, Kevin

Submitted to: Industrial Crops and Products
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/11/2016
Publication Date: 4/4/2016
Publication URL: http://handle.nal.usda.gov/10113/62287
Citation: Thorp, K.R., Wang, G., Badaruddin, M., Bronson, K.F. 2016. Lesquerella seed yield estimation using color image segmentation to track flowering dynamics under water and nitrogen limitation. Industrial Crops and Products. 86:186-195.

Interpretive Summary: Lesquerella seed oil may be used as a biorenewable petroleum substitute in the production of many industrial products, including cosmetics, coatings, plastics, and greases. It also has application as a biorenewable diesel fuel additive. Several issues related to crop management and plant breeding must be resolved before the crop can be produced commercially. In this study, we investigated a digital imaging approach to track the dynamics of flowering in lesquerella under different levels of irrigation and fertilizer management. We demonstrated that digital images were useful to detect changing flowering patterns and that flowering patterns were highly correlated with lesquerella seed yield. Information about lesquerella flowering can aid breeders in the selection of optimum varieties and can aid producers with irrigation management and harvest decisions. The results of this study advance the science of digital image processing for applications in agricultural crop management. Results will benefit plant breeders, growers, and others aiming to develop lesquerella into a commercially viable oilseed crop for production of biorenewable products.

Technical Abstract: Seed oil from lesquerella (Physaria fendleri (Gray) O'Kane & Al-Shehbaz) can potentially supplement castor oil as a non-petroleum-based chemical feedstock in the production of many industrial products. However, before lesquerella will become commercially viable, further efforts are needed to address crop management challenges and to improve lesquerella varieties. Because lesquerella develops vibrant yellow flowers on top of the canopy, the objective of this study was to investigate a digital image analysis approach to 1) assess differences in lesquerella flowering due to water and nitrogen limitation and 2) to estimate lesquerella seed yield. During the winters of 2011-2012 and 2012-2013, field experiments tested lesquerella responses to two irrigation levels and six nitrogen fertilization levels at Maricopa, Arizona. Biomass was sampled within a 30 cm by 30 cm area twice per month, and lesquerella flowers were manually counted. Twice per week, digital images were collected with a commercial digital camera at a nadir view angle approximately 2 m above the canopy. To obtain the percentage of yellow flowers in each image, an analysis routine included 1) an image transformation to the hue, saturation, and intensity (HSI) color space and 2) a Monte Carlo approach to address uncertainty in HSI parameters used for image segmentation. The imposed irrigation and fertilization treatments led to differences in both flower count and flower cover (p<0.05). However, the digital imaging approach permitted more frequent measurements, which revealed fine temporal changes in flowering patterns that could be explained by management and climate factors. Due in part to the larger sampling area for the digital imaging approach, lesquerella seed yield was better estimated using flower cover percentage (r2 <= 0.84) as compared to manual flower counts (r2 <= 0.56). Overall, the digital imaging approach provided useful information to monitor lesquerella flowering dynamics, which was affected by water and nitrogen limitation and highly correlated with lesquerella seed yield.