| Download | - View final version: Deep learning-based prediction of fabrication-process-induced structural variations in nanophotonic devices (PDF, 5.5 MiB)
- View supplementary information: Deep learning-based prediction of fabrication-process-induced structural variations in nanophotonic devices (PDF, 394 KiB)
|
|---|
| DOI | Resolve DOI: https://doi.org/10.1021/acsphotonics.1c01973 |
|---|
| Author | Search for: Gostimirovic, DusanORCID identifier: https://orcid.org/0000-0001-9323-4452; Search for: Xu, Dan-Xia1; Search for: Liboiron-Ladouceur, Odile; Search for: Grinberg, Yuri2 |
|---|
| Affiliation | - National Research Council of Canada. Advanced Electronics and Photonics
- National Research Council of Canada. Digital Technologies
|
|---|
| Funder | Search for: National Research Council of Canada |
|---|
| Format | Text, Article |
|---|
| Subject | silicon photonics; integrated photonics; machine learning; deep convolutional neural networks; fabrication process variations; topological optimization |
|---|
| Abstract | The performance of integrated silicon photonic devices is sensitive to small structural variations that arise from imperfections in the nanofabrication process. This sensitivity is exacerbated for next-generation devices that require fine feature sizes to push the limits of performance. In this work, we present a deep convolutional neural network model to predict fabrication variations in planar silicon photonic devices and verify their manufacturing feasibility prior to prototyping. Our model is trained on a modest set of scanning electron microscope images of structures that experience dimensional inaccuracies stemming from combined contributions from proximity effects in lithography and loading effects in dry etching. Our model quickly and accurately predicts over/under-etching, corner rounding, filling of narrow channels and holes, and washing away of small features in a photonic device. With this, the expected performance of a device can be predicted through an extra simulation and any necessary design corrections can be made prior to fabrication. |
|---|
| Publication date | 2022-07-20 |
|---|
| Publisher | American Chemical Society (ACS) |
|---|
| Licence | |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | bec52cb3-e5ca-4587-adb8-c3721a324915 |
|---|
| Record created | 2022-07-28 |
|---|
| Record modified | 2023-03-16 |
|---|
