Performance-Based Material Screening of Low-Temperature Direct Ammonia Fuel Cells Using Artificial Neural Networks
Bibliographic record
Abstract
This study employs artificial neural networks (ANNs) to optimize material screening and design parameters for low-temperature direct ammonia fuel cells (DAFCs). Using 241 experimental data sets from prior studies, the ANN is trained on 22 categorical and numerical parameters, including catalyst types, membrane thickness, anode loading, and operating conditions, to predict cell current density with high accuracy. The box-whisker analysis identifies the anode catalyst type, cathode catalyst, and anode support material as key determinants of power density, with the anode catalyst type exerting the greatest influence. The ANN, featuring six hidden layers with ReLU activation and trained via the Adam algorithm, achieves mean absolute percentage errors (MAPEs) of 5.75% and 9.30% for training and testing data sets, respectively, and further demonstrates robust generalization with an average training MAPE of 5.81% ± 1.34% and validation MAPE of 8.60% ± 2.10% across 5-fold cross-validation. The ANN accurately reproduces polarization and power density curves for two DAFC configurations (MAPEs of 7.62% and 8.13%). Sensitivity analyses reveal that thinner membranes enhance performance by reducing ohmic resistance, though gains diminish below 18 μm due to interfacial limitations, while an optimal anode loading of 2 mg/cm 2 maximizes power density at 255 mW/cm 2 . By capturing complex, nonlinear parameter interactions, the ANN surpasses traditional experimental approaches, reducing experimental overhead and accelerating DAFC optimization for sustainable energy applications.
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 | 0.000 |
| 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 | 0.000 | 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".