Research by Teesside University in collaboration with international partners aims to investigate the potential of machine learning and AI to detect leakage during carbon sequestration in underground storage.
Led by Associate Professor Aziz Rahman from Texas A&M University at Qatar by Qatar Foundation Priority Research, the $530,000 project could help mitigate risks associated with carbon leakage in pipelines and well string.
A study by Frontiers Energy Research indicates that CO2 leakage could decrease the share of fossil-based carbon capture and storage (CCS) by as much as 35% if properly controlled and price-evaluated.
CO2 leakage could lead to as much as 25 gigatonnes of carbon of additional emissions during this century at a leakage rate of 0.1% annually.
AI can be employed using Computational Fluid Dynamics to help predict how likely leakage is single-phase (crude oil or gas) and multiphase flow (multiple materials), as well as its location. The research will use machine learning together with a digital twin – a virtual object that emulates a physical object – to detect leaks during carbon transport and injection underground.
The project will create a virtual popline updated in real-time with the help of sensors installed in the actual pipelines.
“It is well-documented just how devastating leaks from pipelines can be if they aren’t spotted and acted upon in a timely and efficient manner,” said Dr. Sina Rezaei-Gomari from Teesside University. “This research will look at how state-of-the-art computational techniques including machine learning and digital twinning can be applied to accurately predict where faults are occurring.”
The digital twinning method helps scientists perform simulations to predict the way a a process or a product would perform.
Companies using CCS can implement AI to prevent leaks while removing the need for human interference, thus saving both time and resources.