Aquaculture Journal

Accurate prediction of shrimp body weight is critical for optimizing harvest timing, feed management, and stocking density decisions in intensive aquaculture. While prior studies emphasize environmental factors, operational management variables—particularly harvesting metrics—remain understudied. This study quantified the predictive importance of harvesting-related variables using 5 years of industrial-scale operational data from 12 ponds (5479 cleaned records, 34.94% retention rate). We trained seven machine learning models and applied three independent feature importance methods: consensus importance ranking, SHAP explainability analysis, and Pearson correlations. Main findings: Operational variables (days of culture: 2.833 SHAP, stocking density: 1.871, cumulative feed: 1.510) ranked substantially above environmental variables (temperature: 0.123, pH: 0.065, dissolved oxygen: 0.077). Partial harvest frequency showed bimodal clustering, indicating two distinct viable operational strategies. The Weighted Ensemble model achieved the highest performance (R² = 0.829, RMSE = 4.23 g, MAE = 3.12 g). Model stability analysis via 10-fold GroupKFold cross-validation showed that the Artificial Neural Network (ANN) exhibited the tightest confidence bounds (0.708 g width, 27.7% coefficient of variation), indicating exceptional consistency. This is the first study to systematically analyze the importance of harvesting variables using SHAP explainability, revealing that operational management decisions may yield greater returns than marginal environmental control investments. Our findings suggest that operational optimization may be more impactful than environmental fine-tuning in well-managed systems.

This study introduced a new small-scale semi-mechanized planting method for Kappaphycus alvarezii (Doty) and compared its efficiency to traditional methods. A semi-mechanized sewing (S-MS) device was designed to speed up the planting process using affordable materials. To validate the S-MS model, three different cultivation systems (S-MS method, tie-tie, and tube-net systems) using two color morphotypes of K. alvarezii were implemented, each in triplicate. The experiment spanned 40 days. Water quality and technical indicators were monitored, and data on material consumption and productivity were analyzed. The exclusive S-MS mechanism was successfully completed. The S-MS significantly reduced rope usage by 4.3 times per each propagule sewn to the main cable and planting time (S-MS = 1 min 12 s per meter) compared to the traditional method (tie-tie = 1 min 48 s per meter). Final biomass varied among treatments (p < 0.05), with the S-MS method showing a higher final biomass (15.26 ± 0.88 kg) with olive green K. alvarezii. The average daily growth rates (6.38%) were higher for the S-MS method with olive green K. alvarezii. The S-MS technique offers cost and time savings for seaweed farmers, making it a viable alternative to traditional methods, showed comparable productivity to tie-tie but superior efficiency and resource economy.

The management of fouling through exposure of mussels to air has become risky due to rising temperatures, as it can negatively impact product quality and farm productivity. Since the early 2000s, during air exposure, mussel farmers of the Mar Piccolo have been using high-density polyethylene (HDPE) cloths to cover mussels and prevent their overheating, thus contributing to marine litter from husbandry practices. In this context the aim of the present study was to evaluate whether the use of alternative types of air exposure facilities (wooden, without and with hemp cloth vs. galvanized iron, without and with HDPE cloth) can impact mussel condition index (CI). Since the most damaged mussels during exposure to air are those in contact with galvanized iron structures, for each facility, it was evaluated if there were differences between the mussels in contact with galvanized iron/wood racks and those near the sea surface. Overall, the results showed that the CI of mussels cleaned on wooden racks, ranging from 11.4 ± 2.7 to 12.5 ± 2.7, did not differ significantly from that of mussels before air exposure (CI = 13.1 ± 2.3), except for those near the sea surface without cover (CI = 9.6 ± 2.6). In contrast, a significant decrease in CI was observed in mussels cleaned on galvanized iron racks, with the lowest values observed in covered mussels (CI = 8.2 ± 2.3).