Early prediction of Spirulina platensis biomass yield for biofuel production using machine learning

• Published in: Clean technologies and environmental policy 2022-09, Vol.24 (7), p.2283-2293
• Main Authors: Ching, Phoebe Mae Lim, Mayol, Andres Philip, Juan, Jayne Lois G. San, So, Richard H. Y., Sy, Charlle L., Mandia, Emelina, Ubando, Aristotle T., Culaba, Alvin B.
• Format: Article
• Language: English
• Subjects: Biodiesel fuels; Biofuels; Biomass; Biomass energy production; Case studies; Commercialization; Cultivation; Cyanobacteria; Earth and Environmental Science; Environment; Environmental aspects; Environmental Economics; Environmental Engineering/Biotechnology; Environmental factors; Environmental policy; Industrial and Production Engineering; Industrial Chemistry/Chemical Engineering; Learning algorithms; Machine learning; Mathematical models; Nutrient concentrations; Optical density; Optimization; Original Paper; Parameter identification; pH control; pH effects; Prediction models; Predictions; Process parameters; Production; Spirulina platensis; Sustainable Development
• ISSN: 1618-954X; 1618-9558
• DOI: 10.1007/s10098-022-02321-1

Despite many advantages of third-generation biofuels, there are still numerous opportunities to improve their production efficiency and streamline their commercialization. The unpredictability of cultivating biomass is a major challenge to consistent, efficient production. In particular, the cultivation of Spirulina platensis biomass for biofuel production is affected by various environmental factors such as light, temperature, pH and the nutrient concentration of water. Since controlling these factors is energy intensive, a biomass prediction model would be helpful in anticipating biomass production and in indicating necessary adjustments to the process to improve yield. In this case, earlier is clearly better. This study developed a machine learning-based early prediction model, which identifies the earliest time during cultivation that the process parameters such as optical density and pH can accurately be used to predict biomass yield. In the case study, the early prediction model predicted the final biomass yield (on the 23rd day) by the 8th day of cultivation using ridge regression. Furthermore, an application of this model in pH control led to a 54.1% average improvement in biomass yield. This model may be used to monitor cultivation batches allowing problems (i.e. low yield) to be identified early. It can also be applied in process simulation and optimization to improve biomass yield. In summary, mathematical modelling can make the unpredictable biomass process more predictable and improve production efficiency. Graphical abstract