Machine learning enhanced design and knowledge discovery for multi-junction photonic power converters
Bibliographic record
Abstract
Machine learning is proving to be a revolutionary tool across many disciplines, including optoelectronic device design. In this report, we compare classical and machine learning enhanced design optimization methodologies. We investigate, as an example case, the design of the complex structures of ten-junction InP lattice matched photonic power converters with In[Formula: see text]Ga[Formula: see text]As absorbers optimized for operation at 1550 nm. We find that the implicit pattern recognition capabilities of dimensionality reduction using principal component analysis accelerate design discovery, optimization, and the understanding of complex optical phenomena in the simulated devices. The dimensionality reduction approach offers over twenty times as many optimal designs with greater variability and with a 15% reduction in computational cost compared to a classical optimization method. Furthermore, we find that the representation of the reduced dimensionality subspace offers an intuitive interpretation of optical phenomena expected to occur in this design problem. This method is general and offers the potential for knowledge discovery, expanded design perspective, and optimization acceleration in conjunction with a significant reduction in computational expense in systems which can be numerically modeled.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| 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".