Waveguides bending are basic and important structures for high integration optics and circuits allowing to change the wave propagation direction [1]. Due to the abrupt change of the propagation direction of light over the discontinuity region reflection and radiation is expected to occurs and complex numerical techniques, such as the finite element method, should be used for the modeling of such structure while at the same time it requires knowledge of advanced electromagnetic theory and high computational effort and resources. On the other hand, complex neural networks architectures and machine learning algorithms have been used for the modeling of optical fiber couplers [2] and optical fibers and tapers [3]. The main advantages of machine learning based models are their simplicity, the reduced computational effort and time and also their application for synthesis problems. In this work, a machine learning algorithm has been implemented for the modeling of waveguides bending based on Silicon on Silica with a resonator at the bending. The refractive indexes are n1 = 3.476 and n2 =1.444. and the cavity size is defined by the coordinates of five coordinate points. The data set for the training and validation of the proposed model has been obtained by an efficient frequency domain finite element method [4]. Regression higher than 0.98 has been obtained for the efficiency computation. The obtained model is simple, it is less time-consuming and it requires less computational-effort than conventional numerical techniques used for the analysis of this kind of problems. As a conclusion waveguides bending can be analyzed by using machine learning algorithms. Additionally, a machine learning model can be easily adapted for the analysis of several other photonic and plasmonic devices.
The present work deals with the implementation of machine learning algorithms for the analysis of the coupling efficiency of tapers for silicon photonics applications operating in the C band. The analyzed tapers are used for coupling a continuous waveguide with a periodical subwavelength waveguide and they are composed by several segments with variable lengths. The training, testing, and validating data sets have been numerically obtained by an efficient frequency domain finite element method which solves the wave equation and determines the spatial distribution of the electromagnetic fields and the coupling efficiency for each taper configuration. An excellent agreement has been observed for the coupling efficiency calculation using the machine learning algorithms when compared with the one obtained by using the finite element method.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.