The virtual, digital counterpart of a physical object, referred as digital twin, derives from the Internet of Things (IoT), and involves real-time acquisition and processing of large data sets. A fully implemented system ultimately enables real-time and remote management, as well as the reproduction of real and forecasted scenarios. Under the emerging framework of Precision Fish Farming, which brings control-engineering principles to fish production, we set up digital twin prototypes for land-based finfish farms. The digital twin is aimed at supporting producers in optimizing feeding practices, oxygen supply and fish population management with respect to 1) fish growth performances; 2) fish welfare, and 3) environmental loads. It relies on integrated mathematical models which are fed with data from in-situ sensors and from external sources, and simulate several dynamic processes, allowing the estimation of key parameters describing the ambient environment and the fishes. A conceptual application targeted at rearing cycles of rainbow trout ( Oncorhynchus mykiss) in an operational in-land aquafarm in Italy is presented. The digital twin takes into account the disparate levels of automation and control that are found within this farm, and considerations are made on preferential directions for future developments. In spite of its potential, and not only in the aquaculture sector, the development of digital twins is still at its early stage. Furthermore, Precision Fish Farming applications in land-based systems as well as targeted at rainbow trout are novel developments.
A digital twin is set up for a rainbow trout ( Oncorhynchus mykiss) aquaculture farm located in northern Italy. The farm is equipped with large-scale basins, and are supplied by freshwater from the neighbouring Sarca river. Generally speaking, digital twins are virtual, digital representations which mirror and are connected to real objects, enabling real-time and remote management, as well as the reproduction of real or forecasted scenarios. This is a pioneer application aimed at supporting producers in optimizing feeding practices, oxygen supply and fish population management with respect to 1) fish growth performances; 2) fish welfare, and 3) environmental loads. The digital twin relies on sensors, Big Data, IoT (Internet of Things) and predictive mathematical models. In spite of its potential, and not only in the aquaculture sector, the development of digital twins is still at its early stage. Furthermore, Precision Fish Farming applications in land-based systems as well as targeted at rainbow trout are novel developments.

In fish farming, economic values (EV) of breeding goal traits are lacking, even though they are key parameters when defining selection objectives. The aim of this study was to develop a bioeconomic model to estimate EV of 2 traits representing production performances in fish farming: the thermal growth coefficient (TGC) and the feed conversion ratio (FCR). This approach was applied to a farm producing African catfish (Clarias gariepinus) in a recirculating aquaculture system (RAS). In the RAS, 2 factors could limit production level: the nitrogen treatment capacity of the biofilter or the fish density in rearing tanks at harvest. Profit calculation includes revenue from fish sales, cost of juveniles, cost of feed, cost of waste water treatment, and fixed costs. In the reference scenario, profit was modeled to zero. EV were calculated as the difference in profit per kilogram of fish between the current population mean for both traits (µt) and the next generation of selective breeding (µt+Δt) for either TGC or FCR. EV of TGC and FCR were calculated for three generations of hypothetical selection on either TGC or FCR (respectively 6.8% and 7.6% improvement per generation). The results show that changes in TGC and FCR can affect both the number of fish that can be stocked (number of batches per year and number of fish per batch) and the factor limiting production. The EV of TGC and FCR vary and depend on the limiting factors. When dissolved NH3-N is the limiting factor for both µt and µt+Δt, increasing TGC decreases the number of fish that can be stocked but increases the number of batches that can be grown. As a result, profit remains constant and EVTGC is zero. Increasing FCR, however, increases the number of fish stocked and the ratio of fish produced per kilogram of feed consumed (\"economic efficiency\"). The EVFCR is 0.14 €/kg of fish, and profit per kilogram of fish increases by about 10%. When density is the limiting factor for both µt and µt+Δt, the number of fish stocked per batch is fixed; therefore, extra profit is obtained by increasing either TGC, which increases the annual number of batches, or by decreasing FCR, which decreases annual feed consumption. EVTGC is 0.03 €/kg of fish and EVFCR is 0.05-0.06 €/kg of fish. These results emphasize the importance of calculating economic values in the right context to develop efficient future breeding programs in aquaculture.