Data Mining and Unsupervised Machine Learning in Canadian In Situ Oil Sands Database for Knowledge Discovery and Carbon Cost Analysis
Bibliographic record
Abstract
Alberta’s oil sands (bitumen) extraction critically affects Canada’s ability to meet its commitment to the Paris Climate Change Agreement. However, few studies have published the actual operation data for extraction operations (schemes), especially fuel consumption data. In this study, we applied data mining techniques to Petrinex – a publicly available data warehouse for the oil and gas industry in Canada and extracted actual operating data for 20 schemes from over 35 million monthly records for the period of 2015 to 2019. The average of fuel gas (mainly natural gas) use was 0.29 103m3/m3 bitumen. The schemes with Steam Assisted Gravity Drainage (SAGD) used 0.27 103m3 fuel to produce 1 m3 bitumen. The schemes with Cyclic Steam Stimulation (CSS) used 0.44 103m3 fuel to produce 1 m3 bitumen. The weighted average of emission intensity (EI) was 0.44 t CO2e/m3 undiluted bitumen (70 kg CO2e/bbl). The weighted average EI for SAGD was 0.39 t CO2e/m3 (62 kg CO2e/bbl), and the weighted average EI for CSS was 0.65 t CO2e/m3 (103 kg CO2e/bbl). We also used two unsupervised machine learning methods for knowledge discovery: clustering and association rule. The clustering implied that the CSS method was less efficient than the SAGD recovery method based on energy use and steam to oil ratio (SOR). The clustering also indicated that the production region did not affect interactions between steam and bitumen. The association rule suggested that the occurrence of gas co-injection implied the occurrence of low SOR, {Gas | Co-injection} {Low | SOR} (support:19%, confidence:93%, lift:1.9). Finally, we analyzed the carbon cost. Using the GHG emission limit set by Alberta carbon regulation, the average carbon cost accounted for 2% ($ t CO2e/ $ m3 undiluted bitumen) and $8/m3 (US $1.3/bbl) of undiluted bitumen price when the carbon price was CAD $30/t CO2e and undiluted bitumen price was $326/m3 (US $39/bbl).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.011 | 0.016 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".