Abstract
The prediction of electromagnetic spectra for MXene-based solar absorbers is a computationally intensive task, traditionally addressed using full-wave solvers. This study introduces an efficient deep learning framework incorporating transfer learning, multi-channel spectral refinement (MCSR), and Savitzky-Golay smoothing to accelerate and enhance spectral prediction accuracy. The proposed architecture leverages a pretrained MobileNetV2 model, fine-tuned to predict 102-point absorption spectra from $64\times64$ metasurface designs. Additionally, the MCSR module processes the feature map through multi-channel convolutions, enhancing feature extraction, while Savitzky-Golay smoothing mitigates high-frequency noise. Experimental evaluations demonstrate that the proposed model significantly outperforms baseline Convolutional Neural Network (CNN) and deformable CNN models, achieving an average root mean squared error (RMSE) of 0.0245, coefficient of determination \( R^2 \) of 0.9578, and peak signal-to-noise ratio (PSNR) of 32.98 dB. The proposed framework presents a scalable and computationally efficient alternative to conventional solvers, positioning it as a viable candidate for rapid spectral prediction in nanophotonic design workflows.
Abstract (translated)
基于MXene的太阳能吸收器电磁光谱的预测是一项计算密集型任务，传统上使用全波求解器来处理。本研究提出了一种高效的深度学习框架，该框架结合了迁移学习、多通道光谱精炼（MCSR）和Savitzky-Golay平滑技术，旨在加速并提高光谱预测的准确性。所提出的架构利用了一个预训练的MobileNetV2模型，并对其进行微调以从$64\times64$元表面设计中预测102个点吸收光谱。此外，MCSR模块通过多通道卷积处理特征图，增强了特征提取过程；而Savitzky-Golay平滑则用于减少高频噪声。 实验评估表明，所提出的模型在基线卷积神经网络（CNN）和可变形CNN模型上表现出显著的性能优势，在平均均方根误差（RMSE）、决定系数 \( R^2 \) 和峰值信噪比（PSNR）方面分别达到了0.0245、0.9578和32.98 dB。所提出的框架为传统的求解器提供了一个可扩展且计算效率高的替代方案，使其成为纳米光子设计工作流程中快速光谱预测的可行候选方法。
URL
https://arxiv.org/abs/2602.08406
