XG-Attention-WGAN PIC: Utilizing XGboost-Attention-WGAN for Photonics Integrated Circuit Design
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916990038310912 |
|---|---|
| author | Hasani, Mahmood Shircharandabi, Atena Rabiei, Masiha Motaharifar, Mobin Ghasemi, Mehrdad Banad, Yaser Mike Sharif, Sarah |
| author_facet | Hasani, Mahmood Shircharandabi, Atena Rabiei, Masiha Motaharifar, Mobin Ghasemi, Mehrdad Banad, Yaser Mike Sharif, Sarah |
| contents | Photonic Integrated Circuits (PICs) are fundamental for optical computing, communication, quantum information processing, and precision sensing. However, traditional numerical simulations for designing PIC components are computationally intensive and struggle with high-dimensional parameter spaces. This paper introduces XG-Attention-WGAN PIC, a novel framework that synergistically combines Wasserstein Generative Adversarial Networks (WGANs) with eXtreme Gradient Boosting (XGBoost) to enhance parameter prediction and inverse design in PICs. We utilize Finite-Difference Time-Domain simulations to generate high-fidelity training data, which is augmented by WGAN-generated synthetic data, yielding a root mean squared error (RMSE) of 0.26089. When integrated with XGBoost, this error is reduced to 0.008. The integration of a 64-head self-attention mechanism within the WGAN generator significantly improves data quality and model efficiency over 1000 training epochs. Demonstrated on microring resonators, our approach not only achieves superior prediction accuracy and design optimization but also autonomously discovers a novel, experimentally realizable geometry with enhanced Q-factor performance. The proposed framework provides a scalable, data-driven strategy for developing high-performance PIC components, with promising implications for quantum computing and advanced optical systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03651 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | XG-Attention-WGAN PIC: Utilizing XGboost-Attention-WGAN for Photonics Integrated Circuit Design Hasani, Mahmood Shircharandabi, Atena Rabiei, Masiha Motaharifar, Mobin Ghasemi, Mehrdad Banad, Yaser Mike Sharif, Sarah Optics Pattern Formation and Solitons Photonic Integrated Circuits (PICs) are fundamental for optical computing, communication, quantum information processing, and precision sensing. However, traditional numerical simulations for designing PIC components are computationally intensive and struggle with high-dimensional parameter spaces. This paper introduces XG-Attention-WGAN PIC, a novel framework that synergistically combines Wasserstein Generative Adversarial Networks (WGANs) with eXtreme Gradient Boosting (XGBoost) to enhance parameter prediction and inverse design in PICs. We utilize Finite-Difference Time-Domain simulations to generate high-fidelity training data, which is augmented by WGAN-generated synthetic data, yielding a root mean squared error (RMSE) of 0.26089. When integrated with XGBoost, this error is reduced to 0.008. The integration of a 64-head self-attention mechanism within the WGAN generator significantly improves data quality and model efficiency over 1000 training epochs. Demonstrated on microring resonators, our approach not only achieves superior prediction accuracy and design optimization but also autonomously discovers a novel, experimentally realizable geometry with enhanced Q-factor performance. The proposed framework provides a scalable, data-driven strategy for developing high-performance PIC components, with promising implications for quantum computing and advanced optical systems. |
| title | XG-Attention-WGAN PIC: Utilizing XGboost-Attention-WGAN for Photonics Integrated Circuit Design |
| topic | Optics Pattern Formation and Solitons |
| url | https://arxiv.org/abs/2510.03651 |