Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Environmental Microbial & Food Safety Laboratory » Research » Publications at this Location » Publication #372927

Research Project: Sensing Technologies for the Detection and Characterization of Microbial, Chemical, and Biological Contaminants in Foods

Location: Environmental Microbial & Food Safety Laboratory

Title: Determination of the viability of retinispora (Hinoki cypress) seeds using shortwave infrared hyperspectral imaging spectroscopy

item MUKASA, PEREZ - Chungnam National University
item WAHKOLI, COLLINS - Chungnam National University
item MOHAMMAD, AKBAR - Chungnam National University
item PARK, EUNSOO - Chungnam National University
item LEE, JAYOUNG - Chungnam National University
item SUH, HYUN - Chungnam National University
item MO, CHANGYEUN - Kangwon National University
item LEE, HOONSOO - Chungbuk National University
item BAEK, INSUCK - Orise Fellow
item Kim, Moon
item CHO, BYOUNG-KWAN - Chungnam National University

Submitted to: Journal of Near Infrared Spectroscopy
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 11/28/2019
Publication Date: 1/21/2020
Citation: Mukasa, P., Wahkoli, C., Mohammad, A., Park, E., Lee, J., Suh, H., Mo, C., Lee, H., Baek, I., Kim, M.S., Cho, B. 2020. Determination of the viability of retinispora (Hinoki cypress) seeds using shortwave infrared hyperspectral imaging spectroscopy. Journal of Near Infrared Spectroscopy.

Interpretive Summary: Seed viability is a critical seed quality factor and is crucial pre-sowing information for production and management in farming and forestry. Because traditional methods of determining seed viability are sample-destructive (as well as labor-intensive and time-consuming), non-destructive methods to determine viability are needed to effectively predict yields and establish seed warranties. This research investigated the use of shortwave infrared hyperspectral imaging to determine the viability of Hinoki cypress tree seeds. Hyperspectral images were acquired for 400 seeds, followed by germination tests to confirm seed viability (approx. 31.5% viable). Spectral image data analysis was conducted to find key wavelengths to use for differentiating viable and nonviable seeds, based on their association with chemical differences in the seeds that may be related to germination ability. The key wavelengths were used in to develop viability classification models that demonstrated 92-94% prediction accuracy when applied to the raw seed image data. These results show that shortwave infrared hyperspectral imaging may be useful in developing online seed sorting systems that seed companies and nurseries can use to ensure high quality seeds and improve production yields for food production and forestry.

Technical Abstract: Hyperspectral imaging with multivariate data analysis methods has recently been applied to develop a nondestructive technique to determine the seed viability of artificially aged vegetable and cereal seeds. In this study, we investigated the potential of using shortwave infrared hyperspectral imaging to determine the viability of naturally aged seeds. Hyperspectral images of 400 Hinoki cypress tree seeds were acquired, and germination tests were conducted for viability confirmation, which indicated 31.5% of the viable seeds. Partial least square discriminant analysis models with 179 variables in the wavelength region of 1000–1800 nm were developed with a maximum model accuracy of 98.4% and 93.8% in both the calibration and validation sets, respectively. The partial least square discriminant analysis beta coefficient revealed key wavelengths for differentiating viable from nonviable seeds, determined based on the differences in the chemical compositions of the seeds (including their lipid and fatty acid contents) which may control the germination ability of the seeds. The most effective wavelengths were selected using two model-based variable selection methods (i.e., the variable importance of projection [15 variables], and the successive projections algorithm [8 variables]) to develop the model. The successive projections algorithm wavelength selection method was used to develop a viability model, and its application to the raw data resulted in a prediction accuracy of 94.7% in the calibration set and 92.2% in the validation set. Our results demonstrate the potential of shortwave infrared hyperspectral imaging spectroscopy as a powerful nondestructive method to determine the viability of Hinoki cypress seeds. This method could be applied to develop an online seed sorting system for seed companies and nurseries.