About This Project

Despite their miniscule size, microalgae are capable of sustainably producing biofuels, pharmaceuticals, an other compounds. As a result, microalgae are increasingly gaining attention as a viable resource for our needs. However, the cultivation of microalgae requires high-cost photobioreactors in order to facilitate high biomass yield. I hypothesize that my photobioreactor design can achieve microalgae growth comparable to conventional systems while reducing equipment costs.

Ask the Scientists

What is the context of this research?

As a high school student, I’ve experiences firsthand how difficult cultivating microalgae for research without expensive photobioreactors is. This challenge is not unique to me; many independent phycologists and small labs face the same financial barrier, limiting critical research in fields such as biofuels, food, and pharmaceuticals.

This project addresses the algal biotechnology sector, a relatively new but rapidly growing industry with major potential across the sciences. However, current photobioreactors still face major bottlenecks, namely high upfront and maintenance costs, as well as the lack of adaptive real time culture monitoring. By building on research from the AI and biology communities, we aim to unify these fields into a more efficient system for cultivating microalgae. With support, scientists and researchers could gain access to affordable and effective algae cultivation tools.

What is the significance of this project?

Microalgae are very important microorganisms for scientific research, namely because they are relevant ecologically and in industrial purposes. Without the proper tools required to assess and cultivate microalgae, research in this field can stagnate. Other AI/ML systems exist but lack the sophisticated morphology detection systems that Algaephyte offers.

What are the goals of the project?

The goal of this project is to develop an automated photobioreactor capable of taking the inputs optical density, ph, cellular characteristics, temperature, light wavelength/intensity, and convert those inputs using a hybrid machine learning digital twin approach to optimize algal growth. I aim to achieve a higher biomass yield than another study; I conservatively will aim for 0.3 grams of biomass per litre per day of Arthospira Platesis.

The second goal is to develop a built-in cell screening software integrated with Algaephyte to discover potentially viable strains of microalgae that may have applications in research or industry.