A new partnership will explore the potential role that artificial intelligence (AI) could play in the world of industrial-scale carbon capture.
Leading Indian carbon dioxide (CO2) technologies firm GAS LAB Asia (GAS LAB) will join forces with AI-driven carbon capture solutions developer Carbonetics Carbon Capture (Carbonetics) as part of a ‘world-first’ alliance in AI-driven commercial carbon capture projects.
The partnership extends to a research agreement through GAS LAB’s DST-recognised Dr. S. S. Aggarwal Research Center, dedicated to delivering innovations that substantially lower the lifecycle cost of CO2 capture.
According to the deal, Carbonetics will bring its generative AI design technology to the partnership, aiming to reduce both capital and operational costs.
AI-assisted CO2 capture aids in the optimisation of CO2 capture and storage from industrial processes and power generation plants.
AI algorithms can help to optimise factors including temperature, pressure, flow rates and chemical reactions, improving the efficiency and effectiveness of CO2 capture processes.
Its contribution will include business models such as carbon capture as a service (CCaaS), co-ownership and O&M services.
“Our AI technology perfectly complements GAS LAB’s experience,” said Yash Agarwal, Co-Founder of Carbonetics. “This partnership is a major step towards the Net Zero journey for hard-to-abate sectors.”
For the past 60 years, GAS LAB has developed a range of technologies in CO2 separation, recovery and application across industries such as alcobev and desalination.
“This partnership merges GAS LAB’s robust market presence and research focus with Carbonetics’ groundbreaking AI technology, setting a new standard in carbon capture solutions and addressing climate challenges directly,” said Jayanti Goela, CEO of GAS LAB.
For companies such as Halliburton, AI has become a game changer when it comes to estimating carbon storage capacity volume using seismic data.
Due to sparse seismic datasets, the traditional technique for mapping and estimating the quantity of carbon storage ability is neither adequate nor accurate, says the company.
Having developed a data-driven machine learning solution, Halliburton created a Relative Storage Index through deep learning-based ML algorithm.
RSI is a ML predicted value which can be customised to define suitable ranges for different geological setups. This helps provide a better understanding of the strength and weaknesses of subsurface storage.
Recent case studies have indicated that carbon capture supported by data-driven ML solutions can be up to ten times faster than applying conventional modelling techniques.
source: gasworld.com