Hybrid Machine Learning and Genetic Algorithm Approach for Catalyst and Process Optimization in Fischer–Tropsch Synthesis Toward Sustainable Fuel Production
Bibliographic record
Abstract
Abstract This study presents a data‐driven approach for predicting the relationships between catalyst design, process conditions, and product selectivity in Fischer–Tropsch synthesis (FTS). A dataset of 400 entries was compiled from peer‐reviewed literature, incorporating 24 input variables covering catalyst composition (including base metals, supports, and promoters), physical properties (including BET surface area and pore diameter), and key reaction conditions (including temperature, pressure, TOS, GHSV, and the gas ratio). The five target responses included CO conversion and selectivity for CO 2 , CH 4 , C 2 –C 4 hydrocarbons, and C 5 –C 12 hydrocarbons. Random forest (RF) regression models were developed for each target variable (i.e., conversions and selectivity). High accuracy was consistently achieved in the model training; the training R 2 values ranged from 0.95 to 0.98, with the RMSEC falling between 1.7 and 5.3, which is in line with or an improvement over previously reported results. The performance of the models was evaluated using k‐fold cross‐validation, yielding robust R 2 values ranging from 0.75 to 0.91, with RMSEV values between 3 and 7 for all predicted FTS responses. These results are superior to those reported in the literature, especially regarding CO conversion and C 5 –C 12 product selectivity.To extend beyond prediction and provide actionable insights toward sustainable fuel production, a genetic algorithm (GA) was combined with the RF models to optimize the catalyst composition and process conditions. Using this RF–GA approach, an optimal catalyst was identified. This led to a notable C 5 –C 12 selectivity of 90.75%, one of the highest reported values.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| 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".