Advanced Machine learning models for inverse design and digital manufacturing of terahertz metasurfaces using femtosecond laser technology

Terahertz radiation is essential for applications such as optical imaging, data transportation, and material characterization. However, conventional electronic devices struggle to generate and modulate terahertz radiation effectively. Metasurfaces offer a promising solution by manipulating light at the subwavelength scale. This study introduces a novel approach for fabricating subwavelength optical gratings using femtosecond lasers to modulate terahertz reflection and transmission, achieving modulation rates ranging from 0.3 % to 99.9 % across wavelengths of 100 to 200 mu m. We developed and validated two machine learning-based forward prediction models with R2 values of 0.999 and 0.982, respectively, to predict the structure and optical properties of laser- fabricated gratings. Additionally, two inverse design models were constructed, enabling precise determination of optimal design structures and laser processing parameters for desired optical properties, with R2 values of 0.989 for two-structure models and 0.878 for three-structure models. The lower accuracy of the three-structure model reflects its inherent complexity. Experimental validation confirms the effectiveness of these neural network- based models in advancing the manufacturability and application of terahertz metasurfaces.