Ernesto Hernandez
Bioinspired Engineering Research Group (BIERG), School of Engineering, Technology and Design, Canterbury Christ Church University, Canterbury, Kent CT1 1QU, UK.
Sustainable development is a global priority, vital for ensuring world security. In the oil era, disruptive technologies are crucial for creating efficient and effective solutions to climate change, resource scarcity and environmental degradation. In this quest, the integration of bioinspired solutions and computing power keeps gaining attention. This integration supports the circular economy, where the bioeconomy plays a pivotal role. The bioeconomy is valued at four trillion USD and is a key component of the national bioeconomy strategy of fifty nations. Consequently, there is a focus on promoting sustainable bioinspired solutions through advanced bioprocessing and biocatalysis. However, on a planetary scale, these aspirations represent a complex challenge, hindered by many factors, including technological and infrastructural gaps. Addressing these complexities requires a systems thinking approach to find effective and efficient solutions. For decades, modelling and simulation have been proven technologies for solving complex problems, enabling progress across many aspects ranging from weather prediction, chemical synthesis, transportation, manufacturing and agriculture. Recently, the integration of stochastic models through artificial intelligence (AI) has enhanced predictions and tasks carried out by humans. AI is regarded as a disruptive technology, pushing the boundaries of biotechnology. In bioprocess engineering, AI has enhanced process optimisation, predictive maintenance, real-time monitoring, automation and data-driven decision-making. In biocatalysis, AI contributes to a more sustainable chemistry through discovery, design and engineering of biocatalytic pathways, enzymes or whole cells performance. However, its industrial application is under development. The challenges of AI in bioprocessing include the harmonisation of standards, skilled expertise, unclear black-box approach, complexities of cellular vs. industrial scales, technology integration, AI-assisted detection and lacking multi-objective optimisation in industrial applications. In biocatalysis, AI related challenges include the scarcity of structured data, large search spaces, burdensome process design, inaccurate quantitative predictions and the inefficiency of experimental validation. The integration of successful innovations in computing such as AI are transforming biotechnology for better trade-offs between sustainability, human development and resource management. This could accelerate decarbonisation, foster a cleaner circular economy and help achieve sustainable development goals.