Performance Benchmarking of Machine Learning Models for Terahertz Metamaterial Absorber Prediction

This study presents a polarization-insensitive ultrabroadband terahertz metamaterial absorber based on vanadium dioxide$(\text{VO}_{2})$and evaluates machine learning methods for predicting its absorption performance. The structure consists of a$\text{VO}_{2}$metasurface, a$\text{MF}_{2}$dielectric spacer, and a gold ground plane. It achieves more than 90% absorption between 5.72 and 11.11 THz, covering a bandwidth of 5.38 THz with an average absorptance of 98.15%. A dataset of 9,018 samples was generated from full-wave simulations by varying patch width, dielectric thickness, and frequency. Six regression models were trained: Linear Regression, Support Vector Regression, Decision Tree, Random Forest, XGBoost, and Bagging. Performance was measured using adjusted$\mathrm{R}^{2}$, MAE, MSE, and RMSE. Ensemble models achieved the best results, with Bagging reaching an adjusted$\mathbf{R}^{2}$of 0.9985 and RMSE of 0.0146. The workflow offers a faster alternative to exhaustive simulations and can be applied to other metamaterial designs, enabling efficient evaluation and optimization.