Machine learning prediction of hydrochar properties using ash-based biomass classification with optimized models and interpretability analysis
Bibliographic record
Abstract
The growing demand for sustainable energy solutions has intensified research on biomass valorization into carbon rich hydrochar via hydrothermal carbonization (HTC). However, optimizing hydrochar fuel properties (Fuel Ratio, H/C, O/C) remains challenging due to the complex interplay of feedstock composition and process conditions. This study presents a machine learning (ML) driven approach to predict hydrochar properties by categorizing biomass into low, medium and high ash content groups. An integrated framework combining different ML models and metaheuristic optimization techniques was developed to establish robust predictive capabilities. The results show that the GPR model achieved a testing R 2 > 0.72 and RMSE < 0.1365 across all ash categories. Feature selection highlighted temperature, time, and biomass composition (Carbon, Oxygen, Volatile Matter, Fixed Carbon) as important predictors, demonstrating the effectiveness of ML with hyperparameter optimization for accurate hydrochar properties prediction. Partial dependence plots further explained nonlinear relationships between inputs and outputs. A user-friendly Graphical User Interface was developed, enabling real-time hydrochar properties prediction, closely aligning with experimental data. This work demonstrates that ML models, coupled with optimization techniques, can effectively guide HTC process optimization for tailored hydrochar production, bridging the gap between data-driven insights and practical applications in renewable energy.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".