The project aims to develop models for predicting the growth rate of microalgal cells through the analysis of time-varying data. For this purpose, a suitable array of pilot photobioreactors (PBRs) will be used. The PBRs will be equipped with the sensors required to monitor and record the abiotic cultivation parameters and will be designed to operate independently while providing high-quality data in real time. The use of Internet of Things (IoT) and machine-learning (ML) technologies will enable the transfer, storage, and processing of important parameters, such as pH, temperature, and CO2, which is essential for photosynthesis, while cell growth will also be monitored. Multiple parallel experiments involving short-duration cultures will allow the system to be appropriately configured using different combinations of abiotic parameters. This will provide the training required under a range of conditions and enable computational investigation of how these parameters interact, with the aim of optimizing cultivation performance.

For this purpose, analyses provided by ML tools will be performed. These tools will be integrated through MLOps architecture, while remote access and the real-time deployment and monitoring of models will also be supported.

The project will result in specialized algorithms that optimize cultivation parameters, achieving the highest possible production with the lowest environmental impact. A web application will also enable users to monitor cultivation conditions in real time and intervene whenever necessary.