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

Given the paucity of lamb carcase grading tools, there is a distinct need for the development of rapid, nondestructive 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.

Automated summary

The study aimed to predict intramuscular fat (IMF) using Near Infrared (NIR) spectroscopy with Partial Least Squares (PLS) and machine learning analysis methods. The outcomes of IMF prediction models were similar between the two analysis methods. Additionally, discrepancies in spectra and wavelengths selected across different slaughter events were highlighted in the study.