Applying Machine Learning Methods to Air Emission Monitoring
Alberta’s Oil and Gas (O&G) sector plays a critical role in Canada meeting its commitment to the Paris Climate Change Agreement. However, few studies published the actual operation data for extraction operations (schemes), especially fuel consumption data to accurately project greenhouse gas (GHG) emissions for development and expansion of O&G projects. In this study, we propose to
1) develop a GHG quantification tool using data science techniques in an integrated development environment – Jupyter Notebook with Python programming language to support aggregated oil and gas operations for their regulatory reporting,
2) apply knowledge discovery in databases (KDD) process to in situ oil sands extraction to discover patterns of energy consumption, GHG emissions, and oil production using unsupervised machine learning techniques.
3) Analyze carbon costs to the oil and gas extraction.