Energy

This chapter supports UN SDGs 7 (Affordable and Clean Energy) and 13 (Climate Action) by advancing the understanding and utilization of geothermal resources to promote sustainable and clean energy solutions, contributing to climate change mitigation efforts.

This chapter aligns with SDGs 7, 11, and 10, by offering a case study on renewable energy and rural electrification in Ecuador, in the context of socioeconomic challenges and climate change, whilst also drawing on other examples from developing countries elsewhere.

This chapter explores the integration of artificial intelligence (AI) in biohydrogen production, a promising renewable energy technology. Biohydrogen is regarded as a potential renewable bioenergy resource. There are many processes through which it can be produced, for example, thermochemical and biological processes like pyrolysis, electrolysis, dark fermentation, and photo-fermentation. It is more economically viable when it is produced from waste materials such as waste biomass via microbial fermentation or light-driven chemical reactions. In the last decade, AI or intelligent systems have revolutionized scientific research. Prospectively, classical AI, machine learning (ML), and deep learning algorithms can be applied to optimize biohydrogen production processes. These techniques including reinforcement learning, artificial neural networks, and genetic algorithms can help optimize crucial influential parameters affecting biohydrogen production efficiency and yield. Random forest and support vector machine are two specific ML algorithms that can improve process monitoring, yield prediction, and address challenges for biohydrogen production by managing complex data, accurately predicting outcomes with improved scalability for industrial production processes. The chapter also highlights AI applications in biohydrogen production employing various AI tools like jellyfish optimizer and adaptive neuro-fuzzy inference system that optimize operational conditions in microbial electrolysis cells, enhancing hydrogen yield from wastewater. However, there are many challenges to implement AI-based systems in practice at large that include data limitations, real-world variability, scalability, and supportive technology to AI. Moreover, intelligent systems’ limited adaptability, to date proven credibility and human oversight importance were also discussed with associated ethical concerns. It also needs continuous monitoring and improvement for economically viable and sustainable production processes. Emerging technological trends in biohydrogen production focus on autonomous AI-based production systems, predictive modeling, appropriate management of supply chain, and sustainability valuation. Future AI developments aim to make biohydrogen production more cost-effective, efficient, and scalable.

Humanity is in the midst of a switch of energy sources to power the world, moving to renewables while phasing out fossil fuels. Yet, this process requires many decades and a set of temporary mitigation measures for processes that are required to continue. In this chapter, we explore decarbonization strategies like carbon capture and storage/utilization (CCS/CCU), their role in the current energy picture, and the roadmaps toward net-zero emissions operations in the medium term. Analyzing the strengths and weaknesses of methods like pre- and postcombustion, as well as oxy-fuel combustion and membrane separation, provides us with a framework for action and a list of best practices to implement these techniques across different contexts. Applications vary in their levels of maturity, and some of them have suffered setbacks, yet we are only at the beginning stages of a promising path to achieving net-zero emissions across many different sectors. In this sense, the success of CCS/CCU projects is also dependent on the participation of other actors such as citizens, policymakers, governments, and international organizations. Because of this, the right regulatory frameworks need to be provided, and a joint effort that spans different disciplines is required for decarbonization efforts to come to fruition. A global transformation is, in the end, a challenge that can only be tackled by the best minds coming together and developing synergistic associations.