The rapid development of aquaculture in recent years has been likened to a ‘Blue Revolution’ (Costa-Pierce, 2002) that matches the ‘Grain Revolution’ of higher cereal yields from the 1950s onwards. The industry’s rapid growth and expansion globally, however, has caused concerns about negative environmental impacts, such as eutrophication of nearby waters and, habitat alteration. In Europe, the annual growth of aquaculture has declined to 1%, partly because of market factors, but also because the industry is subject to stringent regulations regarding sustainable development. These factors have led to a strong focus on the ecological development of aquaculture in marine systems, and the promotion of terms such as “ecological aquaculture” and “ecoaquaculture”. Coupled with the need for greater efficiencies and economies of scale to empower the sustainable growth of the industry, precision aquaculture focuses on exploiting modern technologies towards the eco-intensification of aquaculture farms.

Data generated on modern aquaculture farms extend across a wide variety of forms. In situ sensors sample large numbers of environmental variables such as temperature, current velocity, dissolved oxygen (DO), chlorophyll and salinity. Remotely-sensed environmental data can sample much larger spatial domains and can be at the bay-scale – from land-based sensors such as CODAR-type HF radar – or at the global scale from satellite-based monitoring systems. Informing on-farm operations also requires sampling of animal variables such as size, clustering behaviour, and movement, and this is typically done using underwater technologies such as video monitoring, hydroacoustic technology and aerial drone imagery. Further, there are large datasets of pertinent variables that are generated by numerical models such as weather or ocean circulation products. These datasets constitute huge data volumes with distinct characteristics. Integrating and extracting information from these disparate data sources are key to encapsulating the full dynamics of the farm environment and enabling effective management.

The overarching aims of precision aquaculture have been defined as (Føre et al., 2018): 1) improve accuracy, precision and repeatability in farming operations; 2) facilitate more autonomous and continuous biomass/animal monitoring; 3) provide more reliable decision support and; 4) reduce dependencies on manual labour and subjective assessments thus improving staff safety. Similar to precision livestock farming (Berckmans, 2006), precision fish farming has been decomposed into three conditions that must be fulfilled:

1. Continuous monitoring of animal variables (i.e. parameters related to the behavioural or physiological state of the fish),
2. a reliable model to predict how animal variables dynamically vary in response to external factors, and,
3. observations and predictions integrated into an online system for decision or control.

It’s worth noting that in addition to the livestock farming requirements, aquaculture also demands sensing of the ambient environment (e.g. water temperature, oxygen), a consideration that is less important in agriculture where animals can be housed. Achieving these objectives is dependent on the successful implementation of a range of innovative technologies related to sensors, computer vision and AI, enabled by a readily inter-connected edge, fog and cloud ecosystem. Central to this paradigm shift from human to autonomous management is an IoT platform to link information from different components, understand observed status against desired or model-predicted benchmark, and return insight from data in terms of actionable information, such as modified feeding protocol or defined health intervention or treatment.

Conceptually, the cultivation of fish in the ocean has parallels with terrestrial livestock farming. In practice, however, livestock farming is more amenable towards direct human and interaction contact than is possible in the marine-based counterpart. Modern fish farms are comprised of cages with up to 200,000 fish. As farms are typically composed of 10 – 20 cages, and multiple farms are often co-located in a bay, the total number of individual fish is enormous. This precludes the direct translation of concepts from livestock farming, and in practice, precision aquaculture is a marriage of approaches developed for both precision livestock and grain cultivation, i.e., fish are not managed as individuals as are cows, yet are obviously more complex in management than plants.

Alexandra discusses some of the factors that introduce complexity to aquaculture farms and how data can help farm managers to adapt and make an informed decision in the face of such complexity

REFERENCES:

Berckmans, D. (2006). Automatic on-line monitoring of animals by precision livestock farming. In R. Geers & F. Madec (Eds.), Livestock production and society (pp. 27–30). Wageningen Academic Publishers.

Costa-Pierce, B. A. (2002). Ecological aquaculture : the evolution of the blue revolution. John Wiley & Sons, 2008. https://books.google.ca/books/about/Ecological_Aquaculture.html?id=FFYNhAsks24C&source=kp_book_description&redir_esc=y

Føre, M., Frank, K., Svendsen, E., Alfredsen, J. A., Dempster, T., Eguiraun, H., Watson, W., Stahl, A., Sunde, L. M., Schellewald, C., Skøien, K. R., & Alver, M. O. (2018). Precision fish farming: A new framework to improve production in aquaculture. Biosystems Engineering, 173, 176–193. https://doi.org/10.1016/J.BIOSYSTEMSENG.2017.10.014