Scaling up microalgae cultivation is key to commercial viability. Over the past two decades, the market value of microalgae has expanded exponentially, driven by their applications in the pharmaceutical, nutraceutical, cosmetic, and animal feed industries. High-value compounds such as omega-3 fatty acids, proteins, and pigments are in strong demand. However, supply remains constrained by suboptimal cultivation practices and high harvesting costs. Despite decades of progress in process modeling, control, and optimization, industrial adoption is still limited by dynamic cultivation conditions influenced by weather variability, biological adaptation, and integration challenges. Technical barriers, including limited data accuracy, modest control performance, and the fragility of low-cost devices, further restrict optimization efforts. In response, we examined recent advances in control, optimization, and automated machine learning applied to microalgae cultivation. We propose an automated architecture built on a closed-loop supervisory layer that embeds machine learning within the control loop, enabling real-time monitoring, prediction, and adaptive actuation. This approach aligns with real-time optimization and distributed control system practices, integrating system identification, controller optimization, fault diagnosis and tolerance, and perception to achieve autonomous, uncertainty-aware operation.
Sangregorio-Soto et al. (Thu,) studied this question.