biostudies-literatureUnknown105(13)Ahmed MWNational Institute of Food and Agriculture<h4>Background</h4>Accurate, non-destructive quantification of egg yolk ratio holds considerable significance for the food industry, nutritional assessment and egg grading. Conventional approaches are limited by destructive testing and insufficient throughput for commercial applications. This study investigates the potential of visible-near-infrared (Vis-NIR; 374-1015 nm) hyperspectral imaging (HSI) combined with machine learning (ML) and explainable artificial intelligence (AI) techniques for rapid and non-destructive yolk ratio prediction. Multiple regression models, spectral preprocessing and feature selection techniques were comprehensively evaluated to develop robust and interpretable predictive solutions.<h4>Results</h4>Regression models including partial least squares regression (PLJournal of the science of food and agriculture7250-7259https://www.ebi.ac.uk/biostudies/studies/S-EPMC12439085biostudies-literatureNon-destructive quantification of egg yolk ratio using visible-near-infrared hyperspectral imaging, machine learning and explainable AI.PMC12439085Ahmed MWKamruzzaman MEmmert JLfalseNon-destructive quantification of egg yolk ratio using visible-near-infrared hyperspectral imaging, machine learning and explainable AI.<h4>Background</h4>Accurate, non-destructive quantification of egg yolk ratio holds considerable significance for the food industry, nutritional assessment and egg grading. Conventional approaches are limited by destructive testing and insufficient throughput for commercial applications. This study investigates the potential of visible-near-infrared (Vis-NIR; 374-1015 nm) hyperspectral imaging (HSI) combined with machine learning (ML) and explainable artificial intelligence (AI) techniques for rapid and non-destructive yolk ratio prediction. Multiple regression models, spectral preprocessing and feature selection techniques were comprehensively evaluated to develop robust and interpretable predictive solutions.<h4>Results</h4>Regression models including partial least squares regression (PL2025-01-01T00:00:00Z2025 Oct2026-06-01T14:04:58.741Z2026-04-08T13:19:30.223ZS-EPMC124390854049755810.1002/jsfa.14431