Hydrogen production from the steam gasification of hydrochar: A multi-output machine learning approach integrated with metaheuristic algorithms
Bibliographic record
Abstract
Steam gasification of hydrochar requires high-temperature reactors, making the process costly and time-consuming. This study proposes soft computing approaches as efficient alternatives for predicting multiple output (syngas concentration, H 2 /CO ratio and heating value based on hydrochar composition and steam gasification operating conditions. Four Machine learning (ML) models enhanced with metaheuristic optimization techniques (Genetic Algorithms (GA) and Particle Swarm Optimization (PSO)) were trained on experimental data to predict syngas composition, H 2 /CO and higher heating value. Among the models, Gaussian Process Regression (GPR-GA (Coefficient of Determination, R 2 = 0.83, root mean square error, RMSE = 4.19) and GPR-PSO (R 2 = 0.82, RMSE = 4.3)) showed superior performance for hydrogen concentration prediction accuracy. Two-way Partial dependence plots and SHAP show that Steam to biomass ratio (S/B) and higher heating value has a significant effect on hydrogen concentration. Moreover, the optimal steam to biomass ratio and temperature should be in the range of 2.5–3 and 750–850 °C for highest predicted hydrogen concentration. To facilitate practical applications, graphical user interface (GUI) was developed using the best-performing ML model. GUI allows users to predict syngas compositions in real time and eliminates the need for extensive experimentation, providing a user-friendly platform to optimize syngas production while ensuring efficiency and reliability. • ML models optimized for accurate syngas composition prediction and analysis. • H 2 concentration increases with carbon, steam-to-biomass ratio, and temperature. • GPR-GA and GPR-PSO models outperformed others in hydrogen prediction accuracy. • Developed a Graphical user interface for real-time syngas composition predictions.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".