SCAPS Empowered Machine Learning Modelling of Perovskite Solar Cells: Predictive Design of Active Layer and Hole Transport Materials
Bibliographic record
Abstract
Over the last decade, perovskite-based materials have manifested boundless power in boosting solar cells' power conversion efficiency. Despite the extraordinary achievements of simulation surveys in reaching high efficiencies, there is a yawning gap between experimental and simulation results. To harmonize them, acquiring a deep understanding of results, selecting the proper hole transport layer (HTL) and active layer (AL), and employing proper optimization methods in simulation, have remained a great challenge. In this survey, we employed SCAPS-1D and machine learning to study the characteristics of different HTLs (Spiro, CIS, and CsSnI3) and perovskite layers (FAPbI3, MAPbI3, and CsPbI3), including thickness, doping density, and defect density. CsSnI3 as the HTL possesses a negligible lattice-mismatch with perovskite, reducing the dangling bonds as recombination sites, high hole velocity, and low cost than commonly-used Spiro-OMeTAD. According to the SCAPS results, HTL based on CsSnI3 with a thickness of 220 nm, a defect density of 5×1017 cm-3, and a doping density of 5×1019 cm-3 yields the highest performance of about 23.90 %. Moreover, FAPbI3 as AL is not only more stable than MAPbI3, but also it has a more fascinating direct bandgap energy of 1.51 eV, than CsPbI3 and MAPbI3, capable of achieving the highest power conversion efficiency (>24 %) at a thickness of 530 nm and defect density of 1014 cm-3. Machine learning tools also affirm the extracted results with ~75% accuracy on the performance matrices of solar cells. This type of solar cell structure would shed light on the new generation of solar cells.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| 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".