Predicting Corrosion Severity of Pipeline Steels in Supercritical CO2 Environments Using Supervised Machine Learning
Bibliographic record
Abstract
Abstract The importance of effective corrosion management in carbon capture, utilization, and storage (CCUS) networks has significantly increased. Captured CO2 is often transported in the supercritical state (s-CO2) and can contain impurities like H2O, O2, SOx, or NOx. While repurposing existing oil and gas pipelines for s-CO2 transport has been suggested, further testing and risk assessment is required to validate this strategy and its associated risks. Given the substantial amount of corrosion data available from recent corrosion studies, machine learning (ML) has emerged as a promising tool for corrosion prediction and management. This study aims to utilize supervised ML techniques to predict the corrosion severity of pipeline steels operating in s-CO2 systems. The selected algorithms, random forest (RF), K-nearest neighbor (KNN), and support vector machine (SVM) were trained on a comprehensive data set of X-series pipeline steels which includes corrosion rates, impurity levels, temperatures, pressures, and exposure times. Additional testing data set and error and accuracy scores were used to determine the most accurate algorithm. An additional experimental testing was performed to verify the predictions of the model. It was found that the RF model had the best accuracy of 65.3% out of the three tested models and KNN had the worst accuracy of 59.2%. In multiple impurity environments the RF model was able to accurately predict corrosion severity but overestimated corrosion severity in environments with short exposure times.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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".