Partial least squares and machine learning for the prediction of intramuscular fat content of lamb loin

Stephanie M Fowler; David Wheeler; Stephen Morris; Suzanne I Mortimer; David L Hopkins

doi:10.1016/j.meatsci.2021.108505

Partial least squares and machine learning for the prediction of intramuscular fat content of lamb loin

Meat Sci. 2021 Jul:177:108505. doi: 10.1016/j.meatsci.2021.108505. Epub 2021 Mar 19.

Authors

Stephanie M Fowler¹, David Wheeler², Stephen Morris³, Suzanne I Mortimer⁴, David L Hopkins⁵

Affiliations

¹ NSW Department of Primary Industries, Centre for Red Meat and Sheep Development, Cowra, NSW 2794, Australia. Electronic address: steph.fowler@dpi.nsw.gov.au.
² NSW Department of Primary Industries, Orange Agricultural Institute, Orange, NSW 2800, Australia.
³ NSW Department of Primary Industries, Wollongbar Primary Industries Institute, Wollongbar, NSW 2477, Australia.
⁴ NSW Department of Primary Industries, Livestock Industries Centre, Armidale, NSW 2351, Australia.
⁵ NSW Department of Primary Industries, Centre for Red Meat and Sheep Development, Cowra, NSW 2794, Australia.

PMID: 33773186
DOI: 10.1016/j.meatsci.2021.108505

Abstract

Given the paucity of lamb carcase grading tools, there is a distinct need for the development of rapid, non-destructive grading tools for Australian lamb carcases, particularly fat content given its importance to meat and eating quality. The aim of the current study was to determine the potential for Near Infrared (NIR) spectroscopy to predict IMF using Partial Least Squares (PLS) and machine learning analysis methods. As such, 299 lamb loins were measured using a NIR fibre optic device, a sample was excised for Soxhlet determination of IMF content and prediction models were created using either PLS or machine learning analyses methods. IMF prediction model outcomes were similar between analysis methods with an R² = 0.6 and RMSE = 0.84 and R² = 0.65 and RMSE = 0.72, respectively. This study highlighted that spectra from one slaughter varied greatly from the two succeeding slaughters and wavelengths selected between studies are not consistent.

Keywords: Carcases assessment; Chemometrics; Meat processing; Near infra-red spectroscopy; Sheep meat.

MeSH terms

Adipose Tissue*
Animals
Australia
Least-Squares Analysis
Machine Learning
Muscle, Skeletal / chemistry*
Red Meat / analysis*
Red Meat / standards
Sheep, Domestic
Spectroscopy, Near-Infrared / methods
Spectroscopy, Near-Infrared / veterinary