Discovering Energy Consumption Patterns with Unsupervised Machine Learning for Canadian In Situ Oil Sands Operations

Canada’s in situ oil sands can help meet the global demand. Because of energy-intensive extraction processes, operations also play a critical role meeting carbon budget. The steam ratio (SOR) is an indicator used to measure energy efficiency and assess greenhouse gas (GHG) emissions industry. A low SOR indicates process that more efficient less intensive. In this study, we applied machine learning methods for data-driven discovery public database?, Petrinex?, containing operating data from 2015 2019 extracted over 35 million records 20 operations. Two unsupervised methods, including clustering association rules, showed cyclic stimulation (CSS) recovery method was than steam-assisted gravity drainage (SAGD) method. Chi-square tests statistically significant between CSS high (p <0.005). rules suggested occurrence non-condensable (NCG) co-injection produced SOR. on two identified relationship < 0.005). Association indicated there no production regions SORs. For future development, decision-makers should consider SAGD as preferred because it Existing projects development explore possibility NCG with reduce consumption consequently GHG processes.