2026/07/27 by Xin Jue, Yan Wang, Shide Zhang +4
paper · doi:10.1088/1361-6463/ae90ba
Abstract The emergence of deep neural networks (DNNs) has greatly alleviated the time-consuming and phase-discretization problems in conventional metasurface design processes. However, most DNN-assisted design methods are constrained by predefined target electromagnetic parameter formats, making retraining unavoidable when the design objective changes. To address this, we develop an objective-configurable inverse design framework and paired with thermally tunable metasurfaces for multi-channel terahertz wavefront manipulation. The designed metasurface combines anisotropic structural responses with thermally tunable VO 2 , providing four independent linear polarization (LP) channels through polarization and state multiplexing. The inverse design framework couples a residual convolutional neural network (Res-CNN) forward surrogate model with an estimation-of-distribution algorithm implemented via the cross-entropy method (EDA-CEM). By reusing the same surrogate model and reconfiguring only the design objective, different channel combinations and wavefront functions can be selectively activated, which allows on-demand multi-channel wavefront manipulation. As proof-of-concept demonstrations, four addressable LP channels are realized, and two additional circular polarization (CP) channels are further introduced through an adaptive phase allocation. With all four LP channels activated, four-channel letter hologram multiplexing is achieved on a single metasurface, with an average imaging efficiency of 71.6%. After extension to CP channels, six-channel wavefront manipulation is achieved with inter-channel crosstalk below 30%. By integrating thermally tunable metasurface, surrogate modeling, and probabilistic optimization, this work establishes a robust and scalable paradigm for next-generation reconfigurable multi-functional THz photonic devices.