Identifying New Behind Casing Opportunities Using Machine Learning

Abstract

This paper discusses the adoption of Machine Learning (ML) approach to identify new Behind Casing Opportunities (BCO) in two brown fields (B and S) offshore East Malaysia. A multi-stage field-based ML models were developed based on selected wells and consequently used to predict reservoir characteristics in completed wells. The predicted results indicated new upside BCO for add perforation candidate. Raw and interpreted data from B and S fields were analyzed and processed for model training and evaluation. For the case of identifying new opportunity, a specific model development strategy and train dataset selection was employed. The trained ML models evaluated to select the optimal models to predict lithologies, porosity, permeability and water saturations which are then been compared against the actual interpretation. Eventually, the identified upside potentials are validated by Subject Matter Experts (SME) before being proposed as add perforation candidate. It was observed that the models’ performances vary between the two fields due to unique geological complexity as well as the varying quality of raw and interpreted data from each field. Field B which is more geologically complex performs less compared to Field S. In conclusion, this study provides and insight on the advantages and limitations of machine learning to identify new upside BCO in completed wells. The novelty in this work is in the specific model development strategy to identify new upside BCO potentials. This work may be beneficial and essential especially in enhancing resource monetization in brown fields which face challenges in terms of high idle well percentage, low recovery, and declining production.