Affiliation:
1. Nanyang Technological University
2. Institute of Microelectronics, Agency for Science, Technology and Research (A*STAR)
Abstract
In this study, a simplified transformer model is used to perform next-value prediction on light coupled out from silicon photonics gratings to free space. Finite-difference time-domain (FDTD) simulation is performed to simulate the electric field (E-field) in laser light coupled from gratings with pitches of 0.6, 0.8, 1.0, 1.2, 1.4 and 1.6 µm, to free-space. Only E-field distribution from 0.6 µm is used in model training, and the trained transformer model is used to predict the E-field from the rest of the gratings. Prediction of accuracy up to 92.5% is obtained. The time taken for model training is 1908.4 seconds, which is significantly shorter than the conventional three-dimensional FDTD simulation that takes up to several hours. To further reduce the training time, transformer models can be trained with stepped datasets, but with compromised prediction accuracies. In summary, we demonstrated that the transformer model can be used to perform next-value E-field prediction using minimal training data. The developed and trained transformer model can be integrated to the state-of-the-art FDTD software to further expedite the existing FDTD simulation.
Funder
Ministry of Education - Singapore
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献