Microalgae, such as Chlorella vulgaris and Scenedesmus obliquus, are highly efficient at capturing carbon dioxide through photosynthesis, converting it into valuable biomass. This biomass can be further processed into carbon materials with applications in various fields, including water treatment. The reinforcement learning (RL) method was used to dynamically optimize environmental conditions for microalgae growth, improving the efficiency of biodiesel production. The contributions of this study include demonstrating the effectiveness of RL in optimizing biological systems, highlighting the potential of microalgae-derived materials in various industrial applications, and showcasing the integration of renewable energy technologies to enhance sustainability. The study demonstrated that Chlorella vulgaris and Scenedesmus obliquus, cultivated under controlled conditions, significantly improved absorption rates by 50% and 80%, respectively, showcasing their potential in residential heating systems. Post-cultivation, the extracted lipids were effectively utilized for biodiesel production. The RL models achieved high predictive accuracy, with R2 values of 0.98 for temperature and 0.95 for oxygen levels, confirming their effectiveness in system regulation. The development of activated carbon from microalgae biomass also highlighted its utility in removing heavy metals and dyes from water, proving its efficacy and stability, thus enhancing the sustainability of environmental management. This study underscores the successful integration of advanced machine learning with biological processes to optimize microalgae cultivation and develop practical byproducts for ecological applications.

Optimizing microalgal biomass conversion into carbon materials and their application in water treatment: a machine learning approach
    Abstract
        Graphical abstract
    1 Introduction
    2 Methodology
        2.1 Microalgae cultures and sludge collection
        2.2 Microalgal biomass harvesting and drying
        2.3 Machine learning optimization
        2.4 Data collection
        2.5 Methods
            2.5.1 Microalgae cultures and sludge collection
            2.5.2 Machine learning approach and tests
        2.6 Validity and reliability of data
    3 Results and discussion
        3.1 Study framework
        3.2 Optimization and performance evaluation
        3.3 Experimental tests
            3.3.1 Temperature variation over hydraulic retention time test
            3.3.2 Dissolved oxygen concentration monitoring
        3.4 Sensitivity analysis for input parameters
        3.5 Properties of carbon materials for water treatment applications
        3.6 Machine learning performance
    4 Conclusions
    Acknowledgement 
    References

• Arwa Al‑Huqail(Department of Biology, College of Science, Princess Nourah bint Abdulrahman University, P.O.Box 84428, 11671 Riyadh, Saudi Arabia)
• Khidhair Jasim Mohammed(Air Conditioning and Refrigeration Techniques Engineering Department, College of Engineering and Technologies, Al-Mustaqbal University, Babylon 51001, Iraq)
• Meldi Suhatril(Department of Civil Engineering, Faculty of Engineering, Universiti Malaya, 50603 Kuala Lumpur, Malaysia)
• Hamad Almujibah(Department of Civil Engineering, College of Engineering, Taif University, P.O. Box 11099, 21974 Taif City , Saudi Arabia)
• Sana Toghroli(Department of Biomaterials, Saveetha Dental College and Hospital, Saveetha Institute of Medical and Technical Sciences, Chennai 600077, India, UTE University, Faculty of Architecture and Urbanism, Architecture Department, TCEMC Investigation group, Calle Rumipamba S/N and Bourgeois, Quito, Ecuador)
• Sultan Saleh Alnahdi(Civil Engineering Department, College of Engineering, University of Business and Technology, Jeddah, Saudi Arabia)
• Joffin Jose Ponnore(Department of Mechanical Engineering, College of Engineering in Al‑Kharj, Prince Sattam Bin Abdulaziz University, Al‑Kharj 11942, Saudi Arabia)