Science or science-fiction? Playing with ChatGPT to predict the future of the aquafeed industry

Technology continually reshapes our interactions with others and the broader society, with the environment, with the way we work and play, and possibly even the way we think. This continuous change seems to have recently accelerated by the widespread introduction of artificial intelligence (AI) tools. For those like us who are not AI experts, a simpler way to understand AI might be as a combination of algorithms and technologies that enable machines to mimic human-like cognitive functions, including problem-solving, learning from experience, and recognising patterns, all guided by human commands.¹ Advanced AI capabilities, including complex machine learning algorithms and specialised decision-making processes, are predominantly found in paid platforms, tailored for industrial and collaborative use. Whereas other AI tools are freely available to the public and most of them engage with users in natural language conversations, that is, chatbots. Examples of such open-source AIs include Gemini (Google-based), Meta.ai (developed by Meta and integrated with their social media platforms), and ChatGPT (OpenAI). While each platform offers distinct features and functionalities, ChatGPT has notably revolutionised how the general public perceives and utilises AI tools.² Since its release in November 2022, ChatGPT has been adopted for conversational interactions and widely used for knowledge searches, marking a significant shift in the accessibility and usability of AI for everyday users.

In the context of aquaculture, AI has the potential to help us drive the activity towards more sustainable practices.³ ChatGPT, for example, has surely been a source of information for many aquaculture students and farmers, and an additional tool for writing and researching for scientists. Most of us have probably used ChatGPT at least once for fun and curiosity, but possibly also to summarise information, provide definitions, interpret or translate a text, revise a code, or for searching an explanation on an unfamiliar concept related to aquaculture. These are general functionalities offered by ChatGPT, and other chatbots, and are mostly based on information available online. In this editorial of Reviews in Aquaculture, we wanted to go beyond the search for solely past information and, in a mix of scientific curiosity and trying to add extra fun in our daily research tasks, we asked ChatGPT to predict the future. We specifically explored its potential in predicting future trends in the aquafeed industry, inspired by the 6 out of 20 papers published in the current issue that directly focused on aquafeed or fish nutrition.^4-9 For that, we asked two questions on future prediction and research guidance, and limited the output to 250 words. Prompts and responses are presented below:

Q1. What will the aquafeed industry look like by the end of the century?

ChatGPT: “By the end of the century, the aquafeed industry is likely to have undergone significant transformations. With increasing demand for seafood due to population growth and dwindling wild fish stocks, aquaculture will have become a dominant source of seafood production. Aquafeed will evolve to be more sustainable and efficient, incorporating innovative ingredients such as algae, insects, and single-cell proteins to reduce reliance on traditional fishmeal and fish oil derived from wild-caught fish. Advancements in biotechnology may enable the production of feed tailored to specific species, improving growth rates and health outcomes while minimising environmental impacts. Precision feeding systems, driven by artificial intelligence and IoT technologies, will optimise feeding regimes, reducing waste and improving feed conversion ratios. Sustainability will be paramount, with aquafeed production striving for minimal environmental impact through the use of renewable energy sources, closed-loop systems, and efficient resource utilisation. Vertical integration and consolidation within the aquafeed industry may lead to the emergence of large multinational corporations dominating the market, driving standardisation and quality control. Furthermore, consumer preferences for ethically and sustainably sourced seafood will drive transparency and traceability throughout the aquaculture supply chain, influencing the formulation and marketing of aquafeed products. Overall, the aquafeed industry in 2100 will likely be characterised by innovation, sustainability, and technological integration to meet the growing global demand for seafood while safeguarding the health of the planet.”

Q2. As a researcher in aquaculture sustainability aiming to drive the aquafeed industry towards minimal environmental impact by the end of the century, I'm seeking guidance on the most impactful research topics to focus on. What are the top three key areas I should prioritise to ensure a sustainable future for aquafeed by 2100?

ChatGPT: “Alternative Protein Sources: Investigate and develop alternative protein sources such as insect meal, single-cell proteins, and algae to reduce dependency on traditional fishmeal and soy-based ingredients. Optimise production methods to ensure scalability, nutritional quality, and cost-effectiveness while minimising environmental footprint.

Circular Economy Approaches: Explore circular economy models within the aquafeed industry, including recycling and upcycling of by-products and waste streams from aquaculture and other industries. Research innovative technologies for converting organic waste into high-quality feed ingredients, thus reducing reliance on virgin resources and mitigating environmental pollution.

Nutritional Optimisation and Precision Feeding: Focus on fine-tuning aquafeed formulations through precision feeding techniques, leveraging advances in nutritional science and feed additives. Develop personalised feeding strategies tailored to specific species, life stages, and environmental conditions to optimise feed conversion efficiency, minimise nutrient loss, and reduce overall environmental impact.”

By analysing the first prediction, we felt that ChatGPT presented a future of innovation and sustainability, in an optimistic and somewhat idealised, if not utopian, sci-fi perspective, where technology-driven solutions will fix all the problems. While it highlights ambitious industry goals reflected in recent research, such predictions seem to be overlooking important factors that could affect feasibility. For instance, several studies have focused on innovative protein ingredients, and the trend of less usage of wild fish-based ingredients in the aquafeed industry is already taking place. However, the complexities of incorporating such new ingredients need to be highlighted, mainly for scaling up production, ensuring nutritional adequacy, understanding their rheological and organoleptic properties and interactions with other raw materials during feed manufacturing, and addressing potential ecological ramifications of large-scale cultivation or production of such materials. Additionally, the AI output reflected an assumption perpetuated in the scientific community that circular approaches always guarantee environmental sustainability, even though there is not enough scientific, nor quantitative, evidence to support that. Another critical concern is the emphasis on vertical integration, which might well become a reality and thus it will require further considerations as it might lead to monopolistic control and lack of diversity, hiding rather than promoting local socio-economic sustainability.

Reading then the recommended top three research topics, we were somewhat disappointed, as we were, possibly a bit naively, expecting truly innovative and out-of-the-box suggestions. But here, we could see very little imagination and no sci-fiction like suggestions, which is reassuring evidence that human imagination and creativity are likely yet not at risk of being replaced by a computer, at least for now. ChatGPT summarised three well-known, hot topics targeted by aquaculture nutrition researchers in recent years. Investigations on “Alternative protein sources,” “Circular economy approaches,” and “Nutritional optimisation and Precision feeding” are relevant and very much welcomed, as they indeed can contribute to improving the sustainability of aquafeed. Yet, ChatGPT seems to have lacked the fundamental understanding that advancing aquafeed sustainability primarily depends on the integration of ecological, social, and economic perspectives, to potentially develop context-specific solutions tailored to diverse environmental settings and stakeholder needs. One of the insights that we can gain from this exercise is that AI is a very useful tool, that is, and will increasingly be, utilised in science as well as in R&D. Not differently from the abacus, the calculator, the personal computer, and the writing and spreadsheet programs, it will make no sense not using it. It is also worth noting that the outputs of AI will always depend on the users and how the prompts are formulated, as seen in our exercise where we limited the output to a few words, potentially constraining the depth of the explanation. This constraint becomes evident when comparing the two predictions, as scalability was not mentioned in the first but addressed in the second. Thus, we feel like a caveat should be reported to all researchers who also happen to be ChatGPT enthusiasts: the possible misunderstanding and misuse of this tool, and for example, its utilisation for interpreting findings and conceptualising research, are unlikely to produce any impactful or novel research.

For this, we believe that reading scientific papers, written by experts who have intimate knowledge and direct expertise of the sector, is fundamental to expand our scientific reasonings, and ultimately to help moving current science and technologies towards a better future. Thus, we hope you will enjoy this new issue of Reviews in Aquaculture.