Wells with compromised integrity can cause groundwater/soil contamination and increased carbon emissions. Given that there are more than 3.7 million abandoned wells in existence, preventative and remedial operations will need to be prioritized based on the current and future state of well integrity. Well integrity risk assessment, therefore, plays a critical role in managing abandoned wells. This paper presents a generalized workflow for risk assessment that can be applied to abandoned wells in any region.
This study introduces a data-based workflow to project wells onto a risk contour map with a leaking risk gradient as an indicator. The methodology calls for utilizing various feature-rich datasets obtained from multiple sources. Two datasets were used in this study for the purpose of demonstration, including a publicly available dataset consisting of 2342 wells and a newly collected dataset containing detailed information on 1047 wells in the San Juan Basin in the State of New Mexico. The inputs considered for the risk assessment model based on machine learning (ML) included well longitude, latitude, total injected or produced fluid throughout the well's lifetime, distance to induced seismic activity, well lifespan (age), TVD, surface casing bottom depth, production casing bottom depth, completion length, oil price, sacks of cement used to cement the surface casing, abandonment date, cement thickness, and target geologic reservoir formation. Five ML models (artificial neural network, support vector machine, random forest classifier, extreme gradient boosting classifier, and logistic regression) were trained, with the artificial neural network classifier showing the best performance with an initial 75% accuracy. This artificial neural network model was re-trained for regression, which allowed manual threshold setting. This increased the prediction accuracy to 85%. A leaking risk contour map with risk gradient indicators was created by applying the artificial neural network regression model.
This approach provides an essential tool for guidance on wells with compromised well integrity that need to be permanently abandoned or re-abandoned, and wells with sufficient long-term well integrity such that they can be considered for re-use and re-purposing as wastewater / CO2 / hydrogen storage wells, geothermal wells, gravitational energy battery wells, etc. This issue is particularly important given the large asset retirement obligations (ARO) faced by oil and gas operators, presenting major capital expenditures with little-to-no return on investment (ROI) if all wells are to be abandoned. Considerable ARO reduction may be achieved if wells with sufficient integrity can be re-purposed.
Reducing uncertainties associated with well integrity and generating a risk contour map provides valuable insight for asset management of wells to be either abandoned or repurposed and empowers decision-makers to prioritize resources efficiently. This paper provides an easily reproducible data-based approach for identifying wells with different well integrity risk profiles. This paper also highlights features that should almost always be considered in any well-integrity study.
