In the sun-drenched landscapes of Morocco, a groundbreaking study is harnessing the power of artificial intelligence to revolutionize green hydrogen production. Led by Hanane Ait Lahoussine Ouali of the African Sustainable Agriculture Research Institute (ASARI) at Mohammed VI Polytechnic University, the research employs artificial neural networks to optimize hydrogen production through electrolysis powered by concentrated solar energy.
The study, published in the journal “Clean Energy and Sustainable Technology,” focuses on a Dish/Stirling system, which concentrates solar power to drive electrolysis—a process that splits water into hydrogen and oxygen. By analyzing data from over twenty locations in Morocco, the research identifies Figuig and Bouarfa as the most promising sites for implementing this technology, with the potential to produce over 1462 tons of green hydrogen annually.
“Our findings demonstrate the significant potential of integrating artificial intelligence with renewable energy technologies,” said Ouali. “By leveraging machine learning, we can enhance the efficiency and predictability of green hydrogen production, making it a more viable and attractive option for the energy sector.”
The research employs a feed-forward back-propagation network (FFBPN) to evaluate the impact of various input parameters, including direct normal irradiation (DNI) at different geographical locations. The model was trained using different algorithms, with the Levenberg-Marquardt (LM) algorithm emerging as the most effective, showcasing the lowest errors and the highest R2 value during both training and testing.
“This study is a pioneering effort in applying machine learning to predict green hydrogen production from Dish/Stirling systems,” Ouali explained. “The results not only highlight the potential of specific locations but also underscore the importance of choosing the right training algorithm for accurate predictions.”
The commercial implications of this research are substantial. As the world shifts towards cleaner energy solutions, green hydrogen is gaining traction as a versatile and sustainable fuel. The ability to predict and optimize hydrogen production can significantly reduce costs and improve the viability of hydrogen as an energy source.
“By making green hydrogen production more predictable and efficient, we can accelerate its adoption in various industries, from transportation to energy storage,” Ouali noted. “This research lays the groundwork for future developments in the field, paving the way for a more sustainable energy future.”
As the energy sector continues to evolve, the integration of artificial intelligence with renewable energy technologies is expected to play a crucial role. This research not only highlights the potential of specific locations for hydrogen production but also demonstrates the power of machine learning in driving innovation and efficiency in the energy sector. With the findings published in “Clean Energy and Sustainable Technology,” the study sets a new benchmark for future research and commercial applications in green hydrogen production.