Synthesis-feature-coupled machine learning approaches to predict the capacitance of biomass-derived carbon electrodes in supercapacitors
Bibliographic record
Abstract
Activated carbon (AC) materials are an established candidate for electrode components in supercapacitors, particularly electric double-layer capacitors. Multi-thermochemical syntheses of biomass-based precursors influence the AC-based electrode’s specific capacitance. This work aimed to predict the physicochemical characteristics and gravimetric capacitive performance of carbon-based electrode materials by machine learning (ML) techniques. The inherent constituents of biomass precursors, thermochemical synthesis, and electrochemical measurements at three-/ two-electrode systems were considered as input variables. The random forest model was applied with five nature-inspired optimization algorithms. These nature-inspired ML models achieved predictions with R2 of ~0.90 to 0.95, RMSEs of 2.808 to 5.34, and mean absolute error (MAE) of 2.01 to 4.00. Sensitivity analysis disclosed that chemical activation ratio and activation temperature significantly impact the model criteria accuracy. The ML modelling achieved the ideal AC electrode materials with specific surface areas of ~ 2821.70 m2g-1 and additionally estimated the capacitances of ~321.6 Fg-1 at 1 A g-1 in 6 M KOH with a three-electrode system. ML achieved hypothetical N/O co-doped activated carbons as promising candidates for discovering EDLC electrode materials.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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".