Precision agriculture and aquaculture offer a new way of creating a production system that is efficient and eco-friendly with the potential to increase food availability to wider communities across the globe. Digital technologies and applied computing play a crucial role to aid local farmers in better control of production losses. This paper addresses whether it is feasible to deploy a virtual digital replica of aquaculture farms to control essential water quality variables, including temperature, dissolved oxygen (DO), pH, turbidity and ammonia. Traditional IoT systems can offer monitoring capabilities. However, this emerging application requires real-time control-based actuation to intervene in the environment. Often, farmers have limited time to react to any anomalous event. The proposed Planetary Digital Twin employs AI-based control loops to monitor, simulate and optimize aquaculture processes and assets. Preliminary system validation results suggest the approach is feasible in communicating real-time sensor data to a mechanism to detect and control anomalies.
Oysters have the potential to be a part of more sustainable farming systems, such as multitrophic systems integrated into biofloc systems, due to their filtration activity, which enables them to act as organic consumers. However, the stress experienced by animals in a system with a high organic load can compromise their productive performance. The objective of this study was to evaluate the biological responses of Crassostrea gasar oysters when exposed to different concentrations of total suspended solids in biofloc systems. The oysters were exposed to four different concentrations of solids for 28 days. Hall effect sensors were installed on the outside of the shells to detect the movement of the oyster valves. Also, biochemical and histological analyses were conducted to assess the biological responses of the oysters to exposure to varying levels of solids. A difference in valve opening detected by the Hall sensors was observed from the second week of culture, indicating a relationship between shell closure and higher concentrations of suspended solids present in the system. In terms of biochemical analysis, a significant increase in lipid damage was observed in treatments with medium and high levels of total suspended solids compared with the control group. Conversely, no changes were observed in the gill structure of the oysters caused by the concentrations of suspended solids in the system when compared with the control. According to the analyses of gill activity and biochemistry, it is suggested that C. gasar should be cultured with total suspended solids at less than 200 mg/L. Oysters cultivated in a biofloc system keep their shells closed when subjected to high concentrations of total suspended solids; concentrations of total suspended solids below 200 mg/L do not induce oxidative stress, changes in behavior or histological alterations in C. gasar oysters cultivated in a biofloc system.
Fisheries and aquaculture industries notably contribute to animal-source protein production worldwide. Climate change is creating environmental conditions suitable for harmful algal blooms (HAB) on a global scale. Some phytoplankton species can also release toxins, which may cause large-scale marine mortality with knock-on effects on coastal economies. Reliable phytoplankton monitoring and early HAB detection are also essential in climate-resilient solutions for aquaculture applications. Currently, phytoplankton monitoring is primarily based on traditional microscopy. However, it is time-consuming and requires an experienced taxonomist. There is a need to expedite and automate phytoplankton monitoring to support aquaculture industries. Analytical instruments based on microscopy coupled with artificial intelligence (AI) models may be vital to monitoring applications. Digital plankton data sets are usually imbalanced and reflect natural environmental differences. The lack of data to represent minority species/genera prevents AI models from understanding some taxa completely. It compromises system reliability for HAB monitoring applications. The present study investigates state-of-the-art models for class imbalance problems tailored for HAB monitoring within multi-trophic aquaculture farms from Brazil, South Africa, and Scotland. A unified benchmark database covering publicly available microscopic image-based datasets supported phytoplankton modelling. AI deep collaborative models and threshold moving techniques provided the best results compared to standard architectures. It prevailed, especially for low-abundant yet toxic organisms.