Well Intervention Opportunity Management Using Artificial Intelligence and Machine Learning

Abstract

Abstract Operators face many challenges when selecting well-intervention candidates and evaluating a field’s potential because the process is highly time consuming, labor intensive, and susceptible to cognitive biases. An operator can lose up to USD 10 million/year because of ineffective well-intervention strategies in a single field. The objective of this study is to reduce such losses and standardize the well-intervention process by intelligently using the domain knowledge with artificial-intelligence (AI) and machine-learning (ML) techniques. The workflow developed in this study can automatically and autonomously analyze the surface-subsurface data to expeditiously recommend the top intervention candidates. The workflow leverages proven petroleum-engineering methods and customizable business logic to identify underperforming wells and then recommend workover techniques, post-workover production, success probability, and profitability. It uses production, petrophysics, reservoir, and economics data to run a series of AI/ML techniques. The data-analytics engine runs k-nearest neighbors to predict post-workover rates, followed by a decision tree to identify the remedies. Artificial neural network, random forest, and Monte-Carlo simulation are adapted to identify new perforation opportunities in existing wells. Analytic hierarchy process ranks the top intervention candidates based on post-workover rate, permeability, remaining reserves, and reservoir-production trends. Finally, Bayesian belief network calculates the probability of success. With this implementation, the manual benchmarking process of opportunity identification, which usually takes weeks to months, can now be completed within minutes. Once the opportunity is identified and reviewed, it gets registered in the opportunity tracker list for the final evaluation by the asset team. The results are displayed on web-based applications with customizable dashboards and can be integrated with any existing online/offline systems. Because the whole process is now automated and takes very little execution time, petroleum engineers can review the field’s performance on a daily basis. With more than 80% predictive accuracy and 90% time saving compared to the manual process, this workflow presents a step-change in the operator’s well-intervention management capacity. In this paper, the authors discuss the adaptations to the industry-standard AI/ML algorithms and the best practices to provide a faster, more accurate, and efficient well-intervention advisory system.