Optimizing hydrogen-rich gas production by steam gasification with integrated CaO-based adsorbent materials for CO2 capture: Machine learning approach
Bibliographic record
Abstract
The sorption-enhanced steam gasification of biomass with an integrated carbon dioxide (CO 2 ) capture is a promising process for hydrogen production. By using machine learning (ML) approaches to reduce the amount of CO 2 , this study aimed for prediction and optimization of gaseous products with a higher concentration of hydrogen. ML schemes are applied to hydrogen-rich syngas produced through calcium oxide-based adsorbent. Four predictive techniques are applied on the intrinsic constituents of biomass, adsorbents properties, steam gasification ratio, and temperature to predict the concentrations of hydrogen and CO 2 . The accuracies of ML models demonstrated high feasibility of ML to predict the hydrogen and CO 2 with R-squared (R 2 ) of 0.92; and 6.77 to 7.44 vol% of root-mean-square error (RMSE), respectively. Support vector machine (SVM) is optimized by tuning training data size and radial basis kernel ( rbf ) function. Also, the single and multi-objective(s) genetic algorithm approaches optimized the value of hydrogen concentration by Max f max ( H 2 ) by ∼84 and 88 vol%, respectively. Sensitivity analysis showed the fixed carbon/volatile matter, oxygen content, adsorbent/steam to biomass ratios, and gasification temperature in the range of 7–20 vol% of mean absolute percentage error (MAPE) on hydrogen content. The optimized input sets for the ML modelling procedure improved the hydrogen concentration by within 5 vol%. The results indicate a high proficiency of the ML models in accurate prediction of hydrogen gas in the gasification process. • Sorption-enhanced steam gasification of biomass evaluated by ML models. • ML models KNN, SVM, RF, and DT are used to predict hydrogen and CO 2 concentrations. • SVM and RF exhibited 0.91 to 0.92 of R 2 ; and 6.77 to 7.44 vol% of RMSEs. • Sensitivity analysis and genetic algorithm maximize hydrogen concentration by CO 2 reduction.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 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 teacher head, 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".