Insights into the Application of Machine Learning in Reservoir Engineering: Current Developments and Future Trends

Abstract

In the past few decades, the machine learning (or data-driven) approach has been broadly adopted as an alternative to scientific discovery, resulting in many opportunities and challenges. In the oil and gas sector, subsurface reservoirs are heterogeneous porous media involving a large number of complex phenomena, making their characterization and dynamic prediction a real challenge. This study provides a comprehensive overview of recent research that has employed machine learning in three key areas: reservoir characterization, production forecasting, and well test interpretation. The results show that machine learning can automate and accelerate many reservoirs engineering tasks with acceptable level of accuracy, resulting in more efficient and cost-effective decisions. Although machine learning presents promising results at this stage, there are still several crucial challenges that need to be addressed, such as data quality and data scarcity, the lack of physics nature of machine learning algorithms, and joint modelling of multiple data sources/formats. The significance of this research is that it demonstrates the potential of machine learning to revolutionize the oil and gas sector by providing more accurate and efficient solutions for challenging problems.

Advanced Machine Learning application for Permeability Prediction for (M) Formation in an Iraqi Oil Field

“…This group includes the "Training" set with 75% (91 data samples) and the "Testing set with 25% (31 data samples). The matching of permeability predictions from both algorithms with core permeability in the studied wells is shown in Figures (11) and (12). This figure shows that the random forest algorithm is more accurate and matches the core data better than the multiple linear regression algorithm.…”

“…Reservoir characterization: Machine learning algorithms can analyze vast amounts of data, such as seismic data, well logs, and production history, to identify patterns and relationships. This helps in understanding reservoir properties, predicting reservoir behavior, and optimizing production strategies [11].…”

“…Production optimization: Machine learning can be used to develop predictive models that optimize production rates, manage equipment maintenance schedules, and identify potential production issues. These models can leverage real-time data and historical information to improve production efficiency [11][12].…”

An Unsupervised Anomaly Detection Based on Self-Organizing Map for the Oil and Gas Sector

“…The study by Wang et al [31] provides a comprehensive overview of machine learning applications in the oil and gas sector. The research shows that different machine learning techniques can improve industrial plant efficiency.…”

Recent Advances in Carbon Dioxide Sequestration in Deep Unmineable Coal Seams Using CO2-ECBM Technology: Experimental Studies, Simulation, and Field Applications

“…Machine learning (ML) has been employed in various sectors, such as oil and gas and the environmental sector. Different ML like artificial neural networks (ANN), group methods of data handling (GMDH), adaptive neuro-fuzzy inference systems (ANFIS), function networks (FN), support vector machines (SVM), Gaussian process regression (GPR), random forest (RF), regression tree ensembles, deep neural networks, convolution neural networks (CNN), long short-term memory (LSTM) network, etc., can be used to predict certain parameters from easily available data without incurring additional costs. − Due to the fact that the capacity of coal to sequestrate CO 2 depends on the wettability of the formation, which is measured by contact angle (CA), ref predicted the CA of coal formation toward CO 2 wetness, implying that CO 2 sorption capacity increases as the CA angle increases. The ML techniques used were ANN and ANFIS.…”