There is a growing demand for clean-label products. This study aimed to obtain a food-grade coloring ingredient for meat products based on the formation of Zn-protoporphyrin from porcine livers, thus contributing to the development of nitrite-free products. First, the effects of sodium disulfite and acetic, ascorbic, and lactic acids on the formation of Zn-protoporphyrin and the total microbial count were studied. The combination of ascorbic and acetic acids resulted in a higher Zn-protoporphyrin content than acetic acid alone, and microbial levels were maintained (ca. 3 log CFU/mL). Second, a response surface methodology was used to maximize Zn-protoporphyrin while maintaining microbiological food standards. To that end, the effects of pH (4.2–5.4), incubation time (3–30 h), and temperature (25–50 °C) were studied. The selected conditions for Zn-protoporphyrin formation involved anaerobic incubation at pH 4.8 and 45 °C for 24 h. The safety was validated through challenge testing for relevant pathogens (Listeria monocytogenes, Salmonella spp., and Clostridium perfringens). A significant reduction (>6 log units) was observed in the selected conditions for L. monocytogenes and Salmonella, whereas C. perfringens spores remained at the inoculated levels. The optimized procedure is proven to be microbiologically safe, and may improve the color of nitrite-free meat products.

Current approaches to chemical map generation from hyperspectral images are based on models such as partial least squares (PLS) regression, generating pixel‐wise predictions that do not consider spatial context and suffer from a high degree of noise. This study proposes an end‐to‐end deep learning approach using a modified version of U‐Net and a custom loss function to directly obtain chemical maps from hyperspectral images, skipping all intermediate steps required for traditional pixel‐wise analysis. The U‐Net is compared with the traditional PLS regression on a real dataset of pork belly samples with associated mean fat reference values. The U‐Net obtains a test set root mean squared error that is 7% lower than that of PLS regression on the task of mean fat prediction. At the same time, U‐Net generates fine detail chemical maps where 99.91% of the variance is spatially correlated. Conversely, only 2.37% of the variance in the PLS‐generated chemical maps is spatially correlated, indicating that each pixel‐wise prediction is largely independent of neighboring pixels. Additionally, while the PLS‐generated chemical maps contain predictions far beyond the physically possible range of 0%–100%, U‐Net learns to stay inside this range. Thus, the findings of this study indicate that U‐Net is superior to PLS for chemical map generation.