Metaheuristic optimization of hybrid silicon nitride grating couplers
Bibliographic record
Abstract
Grating couplers are essential building blocks to form low-loss photonic chip interfaces. Optical coupling between submicrometric waveguides and standard optical fibers remains a practical hurdle, because of geometrical, material, and modal mismatches. Grating couplers on low-index contrast platforms like silicon nitride (Si₃N₄) suffer from low directionality and poor fiber-to-grating field overlap, thus overall efficiency is limited. To address this, Si₃N₄ couplers with high-index overlays are appealing solution to improve coupling performance, yet with cost-effective fabrication. However, adding extra layers increases the design complexity, resulting in unintuitive operation and time-consuming manual device optimization. To overcome this, machine learning (ML) optimization emerges as an attractive lever to design integrated photonic devices. In this work, we present a comparative study of three metaheuristic optimization techniques - particle swarm optimization (PSO), gray wolf optimization (GWO), and genetic algorithm (GA) – to enhance the coupling performance in hybrid α-Si/SiN grating couplers. The devices are studied for transverse electric (TE) polarization at telecom waveband, centered around 1550 nm wavelength. Employing metaheuristic optimization with Ansys Lumerical finite difference time domain (FDTD) solver, we obtained sub-decibel fiber-chip coupling loss (<1 dB). Proposed strategy presents an effective design approach to develop low-loss and scalable grating couplers on hybrid Si₃N₄ platform for telecom 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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| 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".