Inverse Design of Multiband Absorbers Driven by Peak Features: TIMD-Based Local Feature Enhancement

Metasurfaces, due to their electromagnetic wave manipulation capabilities, provide a crucial technological approach for designing multi-band absorbers. Given the broad application potential of absorbers in various scenarios, their inverse design has increasingly become a research focus. Current deep learning–based inverse design methods for absorbers face two major challenges: the original absorption spectrum data sequences are excessively long, making effective feature extraction difficult and prone to dimensionality explosion. The Transformer for Reversed Metasurface Design (TRMD) method overcomes the sequence length limitation by introducing Multi-Head Self-Attention (MHSA) to effectively capture contextual dependencies in long sequences. However, the absorption peaks in the spectrum are jointly determined by the unit shape and material properties of the absorber, containing rich structural information. TRMD’s global attention mechanism, while computing global correlations, tends to weaken the focused emphasis on these critical peak features, which limits model performance improvement. To further enhance model performance, this paper proposes TRMD with Pyramid Attention and Learnable Feature Fusion (TRMD-PALFF). Based on TRMD, a pyramid attention mechanism is employed to progressively reduce the feature dimensionality in the attention process, guiding the model from global perception to local focus and extracting multi-level features. Meanwhile, a Learnable Feature Fusion (LFF) module is introduced to adaptively adjust the contribution of each level’s features through a set of learnable weights, thereby enhancing the weight of peak region features and improving overall model performance. The final model achieves a loss value converging to 6.14 × 10⁻⁵ on the validation set, with the predicted absorber structures producing absorption spectra highly consistent with the target spectra.