Summary
This study investigates the application of near-infrared spectroscopy as a non-destructive method for measuring eggshell strength, a key quality parameter in poultry production. Machine learning models, supplemented by explainable artificial intelligence techniques, were employed to interpret spectral data and identify the chemical or structural features most predictive of shell integrity. The work contributes to the development of rapid, inline quality assessment tools that could reduce reliance on destructive testing in egg grading and production monitoring.
UK applicability
The findings are broadly applicable to UK commercial egg production, where eggshell quality is a significant concern for both welfare and marketability. UK producers and grading facilities could potentially adopt NIR-based systems to improve non-destructive quality control, and the approach aligns with wider industry interest in precision livestock farming technologies.
Key measures
Eggshell breaking strength (N or kgf); NIR spectral data; model prediction accuracy (e.g. R², RMSE, RMSEP); feature importance scores from XAI methods
Outcomes reported
The study evaluated the accuracy of near-infrared (NIR) spectroscopy combined with explainable artificial intelligence (XAI) methods to predict eggshell strength non-destructively. It likely reported predictive model performance metrics and identified the spectral wavelengths most influential in determining shell integrity.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.