Scaling Field and Experimental Data Using Machine Learning Approaches to Evaluate Oilwell Cement Degradation, Stability and Integrity for CCUS Applications

Abstract

Abstract Carbon Capture, Utilization and Storage (CCUS) processes are increasingly being utilized as a viable solution for carbon removal and meet the goal of net-zero carbon emissions by 2050. Captured carbon dioxide (CO2) is stored deep underground – typically in depleted oil or gas (O&G) wells - utilizing technologies and methods currently employed by the energy industry. However, there are certain ongoing well integrity challenges that would need to be addressed – especially those relating to the cement layer. Cement present in wells used for CCUS applications – including old or abandoned wells - need to ensure zonal isolation, be resistant to deterioration, corrosion, or gas migration, as well as be suited for adverse downhole conditions. Oilwell cement present in existing or abandoned O&G assets have been exposed to a wide range of downhole conditions throughout their lifecycle. It is generally very difficult to determine the mechanical properties and physical condition of the cement downhole and a decline in these properties is expected over time. Experimental evaluations have shown that temperature plays a role in the setting and maturity of the cement, and in CCUS wells, corrosive factors are a major concern due to the acidic environment produced at the CO2 injection zone. These can significantly affect cement mechanical properties such as the Uniaxial Compressive Strength (UCS). Evaluations have shown Temperature or Acoustic Logs can be used to determine downhole properties which can then be correlated to the behavior of cements and the change in their mechanical properties over time using machine learning algorithms. Laboratory evaluations showed varying mechanical properties for oilwell cement at different temperatures and degradation over time. Overall, Class G cements developed the highest stress failure resistance, followed by Class H cements. Higher temperatures accelerated the setting time of all cement samples due to rapid dehydration. However, this in turn reduced the peak UCS developed, indicating a lower stress failure criterion. UCS also showed a direct relationship to acoustic data which can be utilized to evaluate mature and abandoned wells for their integrity. When modeled using supervised machine learning algorithms, field temperature data and acoustic data can reliably predict the mechanical properties of cements over time. An artificial neural network model, and two tree based models were developed, which showed good correlation in predicting compressive strength of downhole cements. Properly understanding the behavior of oilwell cement and the evolution of their mechanical properties is critical to ensure safe storage. Data driven algorithms which can correlate the dynamic mechanical properties of cement to the temperature gradient and acoustic logs can help reliability predict the integrity of the cement layer over time especially for CCUS applications.