|
Getting your Trinity Audio player ready...
|
The intersection of sustainability and artificial intelligence (AI) is poised to revolutionise how humans approach clean energy exploration and utilisation. The ongoing efforts to leverage AI in the search for natural hydrogen reservoirs represent a significant stride towards achieving a sustainable energy landscape.
As the world grapples with the urgent need to transition from fossil fuels to renewable energy sources, the role of AI becomes increasingly pivotal. The ability of deep learning models to analyse vast amounts of data, coupled with satellite imagery, enables scientists to identify subtle surface expressions indicative of subsurface hydrogen reservoirs. This application of AI accelerates the discovery process and enhances the precision and efficiency of locating potential clean energy sources.
In the U.S., scientists are leveraging AI to locate subsurface reservoirs of naturally occurring free hydrogen, paving the way for a cleaner and more sustainable energy future. As the global transition from fossil fuels gains acceleration, researchers have developed a deep learning model capable of scanning the Earth’s surface to identify potential hydrogen-rich sites.
The research focuses on identifying ovoids or semicircular depressions (SCDs) associated with natural or “gold hydrogen” deposits. These depressions, often concealed by agriculture or vegetation, have been discovered worldwide, including in the U.S., Mali, Namibia, Brazil, France, and Russia. Recent findings indicate that these circular patterns are more abundant than previously thought.
To uncover these nearly invisible SCDs, postdoctoral scholars Sam Herreid and Saurabh Kaushik from the Byrd Polar and Climate Research Centre at Ohio State University combined their AI model with global satellite imagery data. Their algorithm was trained using known SCD locations, and remote sensing data was employed to analyse the distinctive features of these sites.
The researchers discovered that AI could map out surface expressions of potential subsurface hydrogen reservoirs globally. By establishing a baseline for further investigations, this innovative approach opens new avenues for exploring hydrogen-associated sites.
Interest in hydrogen as a clean and efficient energy source has surged, especially as governments invest in cleaner alternatives worldwide. Hydrogen is an attractive energy source due to its minimal environmental impact—burning hydrogen produces only water. Hydrogen can be stored and transported, unlike other renewable sources, making it a versatile option for various industries.
Joachim Moortgat, the principal investigator of the project and an associate professor of earth sciences at Ohio State, emphasised hydrogen’s potential. “Hydrogen, in general, is a very attractive energy source,” he said. “If you burn it, its only by-product is water, and unlike wind or solar energy, hydrogen can be stored and transported, so there are all kinds of industries trying hard to make the switch.”
However, the challenge lies in locating hydrogen reservoirs, which may occur in geologies and locations different from traditional oil or gas deposits. The AI tools developed in this project provide a comprehensive mapping of potential SCDs, significantly aiding the exploration process.
Despite the promising advancements, researchers acknowledge challenges in distinguishing hydrogen deposits from other circular-looking land features, such as lakes or crop circles. As countries worldwide intensify their search for hydrogen sources, the urgency to develop reliable exploration tools becomes paramount.
Abroad, Europe is actively exploring ways to harness gold hydrogen stores. At the same time, in the U.S., legislation such as the Inflation Reduction Act includes provisions to expand the clean energy production industry. Although the field is rapidly evolving, it will take several more years before natural hydrogen reservoirs become a reliable source of clean energy.
Herreid, one of the researchers, expressed his optimism for contributing to climate crisis mitigation through these efforts. “This work feels like it is contributing to mitigating the climate crisis,” he said.
As the industry progresses, the focus shifts to deepening the understanding of hydrogen systems. Moortgat highlighted the importance of discovering more SCDs and investigating their formation processes. “Once we discover a lot more, we will be in a better position to use AI tools to find similar ones worldwide,” he explained.
