This research presents designing a tunable trans-reflective color filter utilizing Barium Titanate (BTO) and optimizing its performance by applying an artificial intelligence (AI) based inverse design model. The AI-based color filter design process is efficient and minimizes design challenges. The AI model comprising two sub-blocks is trained using a dataset that correlates geometrical parameters, refractive index, and input voltage variations with desired color outputs to precisely control the color filter's performance. The first is the parametric optimization block (POB), which employs two deep neural networks (DNNs) in the forward and inverse directions to achieve the optimized geometry of the proposed meta-atoms. Once the optimal parameters are completed, the next block, i.e., voltage tuning block (VTB), is employed to map specific colors onto the refractive index and the applied voltage of the BTO layer. In this way, by changing the voltage of the BTO layer, we can leverage BTO's tunable optical properties, which allow for a broad range of vibrant and customizable colors. The optimized color filter demonstrates enhanced tunability and efficiency, opening up new possibilities for applications in displays and imaging devices.
Read full abstract