On machine learning methods to estimate cannabidiolic acid content of Cannabis sativa L. from near-infrared hyperspectral imaging

Wayne S. Holmes; Melanie Po Leen Ooi; Sanush Abeysekera; Ye Chow Kuang; Ray Simpkin; Manu Caddie; Jessika Nowak; Serge Demidenko

doi:10.1109/I2MTC53148.2023.10175994

On machine learning methods to estimate cannabidiolic acid content of Cannabis sativa L. from near-infrared hyperspectral imaging

Wayne S. Holmes
, Melanie Po Leen Ooi
, Sanush Abeysekera
, Ye Chow Kuang
, Ray Simpkin
, Manu Caddie
, Jessika Nowak
, Serge Demidenko

UNITEC Institute of Technology
University of Waikato
Sunway University
Callaghan Innovation
Rua Bioscience Ltd.
Massey University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

This paper investigates the use of near-infrared hyperspectral imaging to estimate the cannabidiolic acid (CBDA) concentration of Cannabis sativa L. plant components such as buds and leaves. A total of 9 regression techniques were assessed with Gaussian Process Regression producing the best result. The least angle regression technique was the best performer of the interpretable models trialled. These models relate the measured pixel reflectance to cannabinoid content as determined by liquid chromatography-mass spectrometry. The regression models were applied to the complete hyperspectral image of the plant to produce CBDA estimation and distribution maps. The ultimate goal of this work is to develop a non-destructive method for Cannabis sativa L. assessment to improve both crop yield and the quality of the plant.

Original language	English
Title of host publication	I2MTC 2023 - 2023 IEEE International Instrumentation and Measurement Technology Conference
Subtitle of host publication	Rising Above Covid-19, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665453837
DOIs	https://doi.org/10.1109/I2MTC53148.2023.10175994
Publication status	Published - 2023
Externally published	Yes
Event	2023 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2023 - Kuala Lumpur, Malaysia Duration: 22 May 2023 → 25 May 2023

Publication series

Name	Conference Record - IEEE Instrumentation and Measurement Technology Conference
Volume	2023-May
ISSN (Print)	1091-5281

Conference

Conference	2023 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2023
Country/Territory	Malaysia
City	Kuala Lumpur
Period	22/05/23 → 25/05/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 2 Zero Hunger

Keywords

Cannabis sativa L
field spectroscopy
proximal imaging
spectral imaging
spectral reflectance

Access to Document

10.1109/I2MTC53148.2023.10175994

Cite this

Holmes, W. S., Ooi, M. P. L., Abeysekera, S., Kuang, Y. C., Simpkin, R., Caddie, M., Nowak, J., & Demidenko, S. (2023). On machine learning methods to estimate cannabidiolic acid content of Cannabis sativa L. from near-infrared hyperspectral imaging. In I2MTC 2023 - 2023 IEEE International Instrumentation and Measurement Technology Conference: Rising Above Covid-19, Proceedings (Conference Record - IEEE Instrumentation and Measurement Technology Conference; Vol. 2023-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/I2MTC53148.2023.10175994

Holmes, Wayne S. ; Ooi, Melanie Po Leen ; Abeysekera, Sanush et al. / On machine learning methods to estimate cannabidiolic acid content of Cannabis sativa L. from near-infrared hyperspectral imaging. I2MTC 2023 - 2023 IEEE International Instrumentation and Measurement Technology Conference: Rising Above Covid-19, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (Conference Record - IEEE Instrumentation and Measurement Technology Conference).

@inproceedings{3adb559c9dae41878414fb8fb679e74c,

title = "On machine learning methods to estimate cannabidiolic acid content of Cannabis sativa L. from near-infrared hyperspectral imaging",

abstract = "This paper investigates the use of near-infrared hyperspectral imaging to estimate the cannabidiolic acid (CBDA) concentration of Cannabis sativa L. plant components such as buds and leaves. A total of 9 regression techniques were assessed with Gaussian Process Regression producing the best result. The least angle regression technique was the best performer of the interpretable models trialled. These models relate the measured pixel reflectance to cannabinoid content as determined by liquid chromatography-mass spectrometry. The regression models were applied to the complete hyperspectral image of the plant to produce CBDA estimation and distribution maps. The ultimate goal of this work is to develop a non-destructive method for Cannabis sativa L. assessment to improve both crop yield and the quality of the plant.",

keywords = "Cannabis sativa L, field spectroscopy, proximal imaging, spectral imaging, spectral reflectance",

author = "Holmes, \{Wayne S.\} and Ooi, \{Melanie Po Leen\} and Sanush Abeysekera and Kuang, \{Ye Chow\} and Ray Simpkin and Manu Caddie and Jessika Nowak and Serge Demidenko",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2023 ; Conference date: 22-05-2023 Through 25-05-2023",

year = "2023",

doi = "10.1109/I2MTC53148.2023.10175994",

language = "English",

series = "Conference Record - IEEE Instrumentation and Measurement Technology Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "I2MTC 2023 - 2023 IEEE International Instrumentation and Measurement Technology Conference",

}

Holmes, WS, Ooi, MPL, Abeysekera, S, Kuang, YC, Simpkin, R, Caddie, M, Nowak, J & Demidenko, S 2023, On machine learning methods to estimate cannabidiolic acid content of Cannabis sativa L. from near-infrared hyperspectral imaging. in I2MTC 2023 - 2023 IEEE International Instrumentation and Measurement Technology Conference: Rising Above Covid-19, Proceedings. Conference Record - IEEE Instrumentation and Measurement Technology Conference, vol. 2023-May, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2023, Kuala Lumpur, Malaysia, 22/05/23. https://doi.org/10.1109/I2MTC53148.2023.10175994

On machine learning methods to estimate cannabidiolic acid content of Cannabis sativa L. from near-infrared hyperspectral imaging. / Holmes, Wayne S.; Ooi, Melanie Po Leen; Abeysekera, Sanush et al.
I2MTC 2023 - 2023 IEEE International Instrumentation and Measurement Technology Conference: Rising Above Covid-19, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (Conference Record - IEEE Instrumentation and Measurement Technology Conference; Vol. 2023-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - On machine learning methods to estimate cannabidiolic acid content of Cannabis sativa L. from near-infrared hyperspectral imaging

AU - Holmes, Wayne S.

AU - Ooi, Melanie Po Leen

AU - Abeysekera, Sanush

AU - Kuang, Ye Chow

AU - Simpkin, Ray

AU - Caddie, Manu

AU - Nowak, Jessika

AU - Demidenko, Serge

PY - 2023

Y1 - 2023

N2 - This paper investigates the use of near-infrared hyperspectral imaging to estimate the cannabidiolic acid (CBDA) concentration of Cannabis sativa L. plant components such as buds and leaves. A total of 9 regression techniques were assessed with Gaussian Process Regression producing the best result. The least angle regression technique was the best performer of the interpretable models trialled. These models relate the measured pixel reflectance to cannabinoid content as determined by liquid chromatography-mass spectrometry. The regression models were applied to the complete hyperspectral image of the plant to produce CBDA estimation and distribution maps. The ultimate goal of this work is to develop a non-destructive method for Cannabis sativa L. assessment to improve both crop yield and the quality of the plant.

AB - This paper investigates the use of near-infrared hyperspectral imaging to estimate the cannabidiolic acid (CBDA) concentration of Cannabis sativa L. plant components such as buds and leaves. A total of 9 regression techniques were assessed with Gaussian Process Regression producing the best result. The least angle regression technique was the best performer of the interpretable models trialled. These models relate the measured pixel reflectance to cannabinoid content as determined by liquid chromatography-mass spectrometry. The regression models were applied to the complete hyperspectral image of the plant to produce CBDA estimation and distribution maps. The ultimate goal of this work is to develop a non-destructive method for Cannabis sativa L. assessment to improve both crop yield and the quality of the plant.

KW - Cannabis sativa L

KW - field spectroscopy

KW - proximal imaging

KW - spectral imaging

KW - spectral reflectance

UR - https://www.scopus.com/pages/publications/85166374913

U2 - 10.1109/I2MTC53148.2023.10175994

DO - 10.1109/I2MTC53148.2023.10175994

M3 - Conference contribution

AN - SCOPUS:85166374913

T3 - Conference Record - IEEE Instrumentation and Measurement Technology Conference

BT - I2MTC 2023 - 2023 IEEE International Instrumentation and Measurement Technology Conference

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2023

Y2 - 22 May 2023 through 25 May 2023

ER -

Holmes WS, Ooi MPL, Abeysekera S, Kuang YC, Simpkin R, Caddie M et al. On machine learning methods to estimate cannabidiolic acid content of Cannabis sativa L. from near-infrared hyperspectral imaging. In I2MTC 2023 - 2023 IEEE International Instrumentation and Measurement Technology Conference: Rising Above Covid-19, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. (Conference Record - IEEE Instrumentation and Measurement Technology Conference). doi: 10.1109/I2MTC53148.2023.10175994

On machine learning methods to estimate cannabidiolic acid content of Cannabis sativa L. from near-infrared hyperspectral imaging

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this