Abstract
Machine learning and optimization algorithms have been widely applied in the design and optimization for photonics devices. We briefly review recent progress of this field of research and show data-driven applications, including spectrum prediction, inverse design and performance optimization, for novel graphene metamaterials (GMs). The structure of the GMs is well-designed to achieve the wideband plasmon induced transparency (PIT) effect, which can be theoretically demonstrated by using the transfer matrix method. Some traditional machine learning algorithms, including k nearest neighbour, decision tree, random forest and artificial neural networks, are utilized to equivalently substitute the numerical simulation in the forward spectrum prediction and complete the inverse design for the GMs. The calculated results demonstrate that all algorithms are effective and the random forest has advantages in terms of accuracy and training speed. Moreover, evolutionary algorithms, including single-objective (genetic algorithm) and multi-objective optimization (NSGA-II), are used to achieve the steep transmission characteristics of PIT effect by synthetically taking many different performance metrics into consideration. The maximum difference between the transmission peaks and dips in the optimized transmission spectrum reaches 0.97. In comparison to previous works, we provide a guidance for intelligent design of photonics devices based on machine learning and evolutionary algorithms and a reference for the selection of machine learning algorithms for simple inverse design problems.
Highlights
It should be noted that the construction of integration level, the design and optimization processes for the theoretical models for complex graphene nanostructures photonic devices become computationally expensive and is generally difficult because the physical mechanisms are complex [3]
Time-domain (FDTD) and finite element method (FEM) [18- Once the data-driven model is constructed, when the physical parameters are inputted into the model, the electromagnetic responses can be calculated in a very short time based on the [34], deep neural networks were an effective model inference [20, 28], Typically, the inference time of the modelling method to construct the complex relationship model is significantly smaller than the calculation time of the between physical parameters and electromagnetic responses
If the the potential relationship between the addition, except for the supervised learning and unsupervised electromagnetic responses and physical parameters can be learning, reinforcement learning was used to build an constructed by using machine learning technique, the inverse autonomous system to solve the decision-making problems in design problems are solved by the data-driven methods. the optimization of photonic devices [51,52,53,54,55]
Summary
In order to overcome the defects of the ANNs, we use several classical regression algorithms to achieve the forward spectrum prediction and inverse design for the GMs. Similar to kNN classification, kNN regression calculates the distances between the targeted instance and each training instance and selects the most similar k data as candidate set to determine the results [91]. It had been proven that ANNs- training instances includes 4 structure parameters (μc1, μc2, based models could equivalently replace the electromagnetic μc3, μc4) and 200 transmittances evenly sampled from the simulation for some photonic structures and the inference transmission spectrum.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
