Oral
Abstract
Research summary supplied by the authors
The leather industry faces critical sustainability challenges, including inefficient detection of microbial spoilage in raw hides and inadequate supply chain traceability. Currently, no rapid spoilage detection techniques suitable for industrial practices exist, resulting in increased chemical use and waste. Furthermore, traceability systems for processed leather products often lack accuracy, leading to misrepresentation and eroding consumer trust. This study addresses these issues with spectroscopic techniques. A linescan hyperspectral imaging system working in a spectral range of 550 nm to 1700 nm was utilized as a rapid and non-destructive technique for predicting the aerobic plate counts on raw hide samples during storage. Our models successfully predicted the staling states characterised by bacterial loads on hide samples with low prediction errors. Real -time grading based on microbial load offers potential for optimising raw hide selection for production pathways, reducing chemical consumption and preventing material waste. Additionally, visible -near infrared spectroscopy coupled with machine learning successfully traced wet -blue leather impregnated with chemical tracers. The classification models demonstrated over 97% accuracy in differentiating treated and untreated samples, ensuring reliable verification of origin and authenticity throughout the supply chain. These results demonstrate the potential of spectroscopic technologies to enhance leather production sustainability by minimising waste, optimising resources, and ensuring supply chain transparency. This approach fosters environmentally responsible practices and aligns leather production with global sustainability goals.