Simulation Calculation of Selective Reflective Films based on Metamaterials and Prediction of Color in Light Filter with Machine Learning

Xiangtian Gao1,2

Ming Yang1,2,Email

Aricson Pereira3

Sijie Guo4

Hang Zhang1,2,Email

1Institute of Engineering Thermophysics, Chinese Academy of Sciences, Beijing 100190, China.
2University of Chinese Academy of Sciences, Beijing 100049, China.
3Advanced Materials Division, Engineered Multifunctional Composites (EMC) Nanotech LLC, Knoxville, TN, 37922, United States of America.
4Department of Chemical and Biomolecular Engineering, University of Tennesee, Knoxville, TN 37996 United States of America.

Abstract

In this study, we constructed a three-layer cylindrical periodic structure based on metamaterials. This structure is obtained by coupling the periodic cylindrical structure and the MIM (metal/insulator/metal) three-layer structure. The finite difference time domain method is used to calculate the reflection curve of the structure, and then the color coordinates of the structure under the D65 light source are calculated. We obtain the relationship between the color presented by the structure and the variation of structural size parameters. Then the random forest algorithm is used for machine learning, and a more accurate learning model is obtained. The coefficient of determination R2 is above 0.98. This result ensures that the random forest algorithm can be used in the calculation of superstructure. The article presents a novel light filter design with tunable color properties and machine learning framework for accurate color predictions based on structural parameters.

Simulation Calculation of Selective Reflective Films based on Metamaterials and Prediction of Color in Light Filter with Machine Learning