Innovative machine learning techniques could help detect leaks during underground carbon dioxide (CO2) sequestration, helping reduce their environmental and economic impacts.
Academics from various universities have formed an international research partnership to implement artificial intelligence (AI) and machine learning to detect the leaks in pipelines and well string.
They will also employ a novel “digital twin” for leak detection during single phase – crude oil or gas – and multi-phase flow during the transportation and injection of carbon dioxide into the underground storage site.
This involved creating a virtual representation of a pipeline which is updated in real time via a network of sensors mounted and installed in the real gas pipelines.
The team will use Computational Fluid Dynamics (CFD), whereby AI simulates the flow of liquids and gases and hope to be able to accurately predict the likelihood and location of leaks in both the single phase and multi-phase flows.
These techniques are expected to more accurately predict the location, size, number and orientation of both small chronic and larger leaks and ultimately take action by AI without requiring human interference.
Academics from Teesside University’s School of Computing, Engineering & Digital Technologies are working with researchers at Texas A&M University at Qatar (TAMUQ), Qatar University, Texas A&M University (US), Birch Scientific (US) and Rock-Oil Consulting from Canada for the project.
Dr Sina Rezaei Gomari, Senior Lecturer in Energy & Environmental Engineering said: “Teesside University is committed to research which utilises novel and disruptive technologies, processes and business models to forge a smarter, greener industrial economy.
“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.
“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, without the need for remotely operated vehicles or aircraft to scan the pipeline which can be both time-consuming and costly.
“We will be working with alongside leading oil and gas companies to ensure that this research can have real industrial applications.”
