Calculation of Production Back Allocation Using Machine Learning Algorithms

Abstract

The petroleum industry is reliant on precise and efficient back allocation, a process that calculates individual well production rates from shared facilities or multi-well platforms. Especially in matured facilities and legacy assets, traditional measurement techniques often fail to provide the necessary accuracy due to a lack of pre-installed flow meters and individual measurement mechanisms. Furthermore, these methods frequently require additional interventions, a factor that could potentially defer production, incur significant costs, and require extensive supply chain management. Despite these challenges, back allocation remains an essential process for effective reservoir, well, and field production performance management, as well as for ensuring accurate revenue allocation throughout a field's economic life cycle. This study explores the application of machine learning (ML) as an advanced, data-driven approach to overcome the complexities of back allocation and streamline the process with increased accuracy and reduced interventions. Three ML models were implemented for this purpose, namely XGBoost, Random Forest, and LightGBM. These models were designed to predict individual well oil rates based on various parameters easily obtainable from wellhead locations, including wellhead pressure, temperature, and choke size. A meticulous preprocessing stage was performed to make sure the data was ideally suited for the ML models. Further, hyperparameter tuning was applied to enhance model accuracy and performance. Of the three models, XGBoost showed remarkable performance, producing high R2 scores of 0.97, 0.98, 0.96, and 0.96 for each well. These scores underscore the model's strong capability to predict individual well oil rates with high precision, highlighting the potential of ML in addressing complex problems in the oil and gas sector. The study's findings present a promising advancement in the application of ML, particularly XGBoost, for accurate back allocation in combined production systems. The model's superior performance and prediction accuracy pave the way for improved decision-making related to reservoir management, well diagnostics, and cost optimization. The utilization of ML for back allocation holds considerable promise for boosting operational efficiency and profitability in oil and gas production systems. Looking ahead, further research will seek to apply the model on a larger scale and test its efficiency across varied field conditions and scenarios. This investigation will help to further validate the substantial advantages of employing ML methodologies in the petroleum industry.