Antarctic krill (Euphausia superba) represents a promising sustainable protein source for human consumption. While a portion of the catch undergoes immediate onboard processing, the majority is preserved as frozen raw material, with storage duration significantly impacting product quality and safety. This study established a novel approach for rapid quality assessment through storage time prediction. Traditional chemical quality indicators of krill during a 12-month storage were first monitored and the correlation between the quality and storage time was verified. Coupled with four different regression machine learning algorithms, near-infrared spectroscopy (NIRS) was applied to develop models. Following optimal spectral preprocessing selection and hyperparameters optimization, the light gradient boosting machine (LightGBM) model yielded the best storage time prediction performance, with the R² of the test set being 0.9882 and the errors RMSE, MAE, and MAPE being 0.3724, 0.2018, and 0.0431, respectively. Subsequent model interpretation results revealed a strong correspondence between model-related NIR features and chemical indicators associated with quality changes during krill frozen storage, which further justified the model’s predictive capability. The results proved that NIR spectroscopy combined with LightGBM could be used as a rapid and effective technique for the quality evaluation of frozen Antarctic krill, offering substantial potential for industrial implementation.

Acid-solubilized (ASC) and pepsin-solubilized collagen (PSC) extracted at 4 °C (ASC-4 and PSC-4), 12 °C (ASC-12 and PSC-12), and 20 °C (ASC-20 and PSC-20) from the skin of farmed pufferfish (Takifugu obscurus) was characterized by SDS-polyacrylamide gel electrophoresis (SDS-PAGE), Fourier-transform infrared spectroscopy (FTIR), and fibril-forming tests. The results indicate that extraction at 12 °C can effectively improve the extraction efficiency of natural collagen compared with extraction at 4 °C. However, extraction at 20 °C results in a decrease in molecular integrity, thus, inducing the resultant collagen to degrade or even lose fibril-forming ability. Transmission electron microscope (TEM) images revealed that ASC-4, PSC-4, ASC-12, and PSC-12 can assemble into fibrils with D-periodicities, and ASC-20 associated into molecular aggregates alongside partial D-banded fibrils, while no well-defined fibrils were observed in PSC-20. Scanning electron microscope (SEM) analysis confirmed the well-defined fibril morphologies of ASC-4, PSC-4, ASC-12, and PSC-12 with imino acid contents between 190.0 and 197.8 residues/1000 residues. The denaturation temperature of ASC-4, PSC-4, ASC-12 and PSC-12 was 30.0, 27.6, 25.9 and 22.7 °C, respectively. This study indicates that ASC and PSC extracted at 4 °C and 12 °C could be alternatives to terrestrial collagens for industrial applications.