Artificial intelligence is increasingly applied to crab research, yet no prior review has mapped this work or its progress toward real-world use. This scoping review maps artificial intelligence applications in true crabs (Brachyura) across aquaculture, fisheries, ecology, and processing. Following the PRISMA extension for Scoping Reviews, five databases were searched for records published from 2016 to 14 June 2026, yielding 11,172 records, most from databases whose broad field coverage returned papers mentioning crabs or artificial intelligence only in passing. Of these, 88 peer-reviewed English-language primary studies applying artificial intelligence to brachyuran data and reporting at least one quantitative performance metric were included. Each study was charted for species, task domain, model architecture, dataset, performance, and deployment maturity (Technology Readiness Level). The literature is young and expanding rapidly, with nearly half published since 2025, and heavily concentrated, with China contributing most affiliations and three species accounting for more than two-thirds of studies. Twelve task domains were identified, dominated by quality assessment and sex classification. The field has converged on object detectors with attention modules, but accuracy is rarely comparable because datasets and protocols are proprietary. Most systems remain at laboratory validation. Reported accuracy has therefore advanced faster than demonstrated deployment.
Expanded polystyrene floats have been identified as a significant source of marine microplastic in oyster aquaculture, yet no certification criterion assesses the material that the certified alternatives shed. Gravimetric mass loss, normalised to a common exposed area of 7200 mm2, is reported under accredited accelerated weathering to KS F 2274 for eight float materials: expanded polystyrene at three densities, expanded polypropylene, three injection-moulded polymers, and a continuous-fibre basalt-reinforced thermoplastic composite. Specimens were dried to constant mass before weighing, so the quantity measured is a net change: an upper bound on particulate release, not a measure of it. Mass exceeded the initial value in all three stabilised expanded polypropylene specimens. At 3000 h the loss spanned a factor of 54, and every foamed material exceeded every non-foamed one, while tripling the density of expanded polystyrene reduced loss by only 25% (n = 3; p < 0.0001 across the foamed groups). For ten injection-moulded grades the accelerated ranking reproduced that of 2.5 years outdoors (Spearman ρ = 0.89), though the ratio varied from 0.4 to 6.3. A wear model indicates that the pure-polymer barrier providing water tightness contains 905–1180 g L−1 of polymer against 578 g L−1 for the laminate beneath, so the wearing layer, not the bulk material, may govern release in service.
Cricket meal is increasingly considered a sustainable alternative to fishmeal in aquaculture, although its performance depends on the effective use of nutritional and functional components. This review examines evidence on including cricket meal in aquafeeds and the factors that may limit or enhance its application. Species-dependent responses to fishmeal replacement are discussed in relation to polyunsaturated fatty acid imbalance and chitin content. Strategies to improve lipid functionality include defatting, enriching the cricket’s rearing substrate to promote ω-3 fatty acid bioaccumulation, microbial fatty acid biotransformation, and enzymatic interesterification. The review also evaluates chitin and chitosan as health-promoting compounds with prebiotic, immunomodulatory, antimicrobial, antioxidant, and water-quality-related functions. Finally, fermentation and enzymatic hydrolysis are considered as tools to improve nutrient bioavailability. Overall, the integrated utilization of cricket meal components may increase its nutritional value, functional performance, and suitability as an aquaculture feed ingredient.
The sustainable farming of pearl lobsters (Panulirus ornatus) demands strategic measures that account for institutional, economic, ecological, technological, and social factors. This study identifies the main strategic drivers of sustainable grow-out aquaculture and prioritizes development interventions in South Sulawesi, Indonesia. Data were obtained from 54 key informants representing government agencies, researchers, extension officers, exporters, collectors, aquaculture workers, and coastal communities through interviews, focus-group discussions, observations, and structured questionnaires. The Matrix of Cross-Impact Multiplications Applied to Classification (MICMAC) was used to identify structural drivers, while the Analytic Hierarchy Process (AHP) was used to establish relative development priorities. The direct MICMAC analysis identified Regulatory Framework as linkage variables, while Multi-Actor Coordination and Aquaculture Innovation occupied the linkage position. The AHP results (CR = 0.047) assigned the highest criterion weight to institutional factors (0.339), followed by economic (0.242), technological (0.154), ecological (0.154), and social (0.111) factors. The highest global priorities were Multi-Actor Coordination (0.176), Regulatory Framework (0.163), Production Cost (0.109), and Aquaculture Innovation (0.100). The integrated MICMAC–AHP framework indicates that governance capacity, coordination, and technological innovation are important leverage points for sustainable pearl lobster grow-out aquaculture in South Sulawesi.
Persistent markerless identification of visually similar fish is difficult when occlusion interrupts tracking. This study evaluates a hybrid spatial–visual pipeline combining YOLO26n detection, ByteTrack association and a Swin-T re-identification (Re-ID) model. Experiments were carried out using two Aalborg University (AAU) zebrafish recordings containing six known individuals. The detector and embedding model were retrained on consecutive temporal blocks separated by ten omitted frames; 426 frames were held out from retraining and checkpoint selection. A 400 px vertical mask simulated occlusion, and predictions were evaluated against ground-truth AAU Object IDs. The added association stage restored the prior identity in three of eighteen eligible episodes after full emergence (16.7%), compared with none for ByteTrack. All three successes bridged changed ByteTrack IDs, with successes in both recordings; one assignment was incorrect and fourteen episodes remained unresolved. Under a separate partial-reappearance definition, Re-ID recovered six of twenty-four episodes (25.0%), versus none for ByteTrack, with one incorrect identity, one different identifier for the same fish and sixteen unresolved episodes. These verified recoveries demonstrate that the added association stage can restore identities after tracker interruption. Limited assignment coverage and testing on previously seen individuals constrain conclusions about reliability and transfer to independent recordings.
