Decision support systems for digital twins in aquaculture: A systematic literature review

Aquaculture is rapidly adopting digital technologies (IoT, AI/ML, cyber–physical systems) to improve operational efficiency, environmental performance, and risk management. Within this transformation, Decision Support Systems (DSS) operationalize data into actionable recommendations, while Digital Twins (DT) extend these capabilities by maintaining a synchronized virtual representation of farm processes for scenario testing, forecasting, and optimization. This PRISMA-guided systematic review synthesizes 80 peer-reviewed studies (2010–2025) addressing DSS and DT in aquaculture, assessing application domains, enabling technologies, validation practices, and technology readiness. Results show strong growth since 2023 and concentration in water quality, feeding, and health monitoring. While AI-based disease detection and water-quality forecasting frequently report high accuracy in controlled evaluations, only a small fraction of studies report sustained on-farm deployment, indicating a persistent gap between prototype performance and commercial adoption. Compared with recent DT-focused perspective papers (e.g., Fore et al., (2024)), this review contributes a systematic, evidence-based assessment of maturity and field transfer by integrating DSS and DT literature, mapping validation approaches, and consolidating socio-economic and data-quality constraints. We identify priority gaps in (i) data standardization and quality assurance, (ii) model generalization across farms and seasons, (iii) continuous calibration and DT validation in highly variable biological systems, and (iv) cost–benefit evidence and adoption pathways. The review provides a decision-oriented benchmark to guide the development of robust, scalable, and trustworthy DSS/DT solutions for sustainable and climate-resilient aquaculture. • Synthesizes 80 studies (2010–2025) on aquaculture DSS and DT, emphasizing readiness, validation, and adoption. • Identifies the research-to-farm and the dominant technical as well as socio-economic barriers. • Proposes future directions for robust DT/DSS.