Rethinking Human–Machine Communication in Aquaculture Monitoring

The disruption brought by artificial intelligence models capable of understanding and generating natural conversations, such as ChatGPT, marks a turning point in the way aquaculture professionals are likely to interact with technology in the coming years. Until now, devices used for monitoring and controlling water quality, feeding, or net inspections have required technicians to adapt to complex interfaces, undergo specialised training, and in many cases carry out manual adjustments. The arrival of systems able to interpret everyday language opens the door to a new era of communication between humans and machines.

Aquaculture relies on a wide range of monitoring devices: sensors that track oxygen levels, pH, and temperature; automated feeders; cameras for behavioural observation; and control systems that integrate this data. Until now, technicians have had to operate each device through technical dashboards or parameter settings, a process that can slow down response times and demand constant attention.

By applying the concept behind language-driven artificial intelligence, these systems could evolve into intelligent assistants rather than passive tools. Instead of entering numeric values into software, a farm manager might simply say: “increase feeding in cage four by 10% during the afternoon cycle,” or “alert me if dissolved oxygen drops below six milligrams per litre.” The device would translate those instructions into precise operational commands, adjusting its performance automatically while keeping the operator informed.

This shift changes the role of technicians. Rather than focusing on how to operate a machine, they can focus on what they need the machine to achieve. Communication becomes more intuitive, lowering the barrier to technology adoption and enabling smaller farms, often without specialised IT staff, to benefit from advanced digital solutions. At the same time, language-driven systems could improve decision-making by offering recommendations or asking clarifying questions when conditions are ambiguous.

The next steps for the sector involve embedding these capabilities across the technological ecosystem of aquaculture. From water quality probes that can explain trends in plain language, to feeding systems that adjust strategies based on both data and operators’ instructions, the potential is vast. With this approach, machines do not simply collect data or execute commands; they participate in a dialogue with the farmer, creating a more responsive and adaptive production environment.

As aquaculture continues to grow, so too does the need for precision, efficiency, and transparency. By rethinking human–machine communication, the industry has an opportunity to transform monitoring and control from a technical challenge into a natural extension of farm management. The experience of this kind of AI-assisted communication system shows that the future of aquaculture technology may not only depend on what machines can do underwater, but also on how easily humans can talk to them.