机器学习辅助的棱镜型表面等离子体共振传感器分析与逆设计
Machine Learning-Assisted Analysis and Inverse Design of Prism-Based Surface Plasmon Resonance Sensors
浏览论文内容
中文总结 AI 辅助
该研究提出一种整合ML基准、可解释性及优化的框架，采用四种ML模型高效分析与逆设计SPR传感器，计算速度提升千至万倍且精度高。
中文摘要 AI 辅助
本研究展示了一种用于高效设计和优化Kretschmann构型表面等离子体共振（SPR）传感器的数据驱动机器学习（ML）框架。基于物理原理，采用基于MATLAB的传输矩阵法（TMM）生成了涵盖不同材料特性、层厚及多层结构的数据集；以光学特性和层厚作为输入特征，以品质因数（FOM）和最小反射率（Rmin）作为目标性能参数。对CatBoost、XGBoost、LightGBM和多层感知器（MLP）这四种ML模型，采用决定系数（R²）、平均绝对误差（MAE）和均方根误差（RMSE）进行基准测试。该框架整合了ML基准测试、SHAP可解释性分析、鲁棒性分析及优化驱动的逆设计；通过SHAP加权扰动实验评估模型对输入变化的鲁棒性，采用四种优化算法进行传感器逆设计，随后分析参数恢复与性能，还通过独立正向设计任务评估优化算法，重复运行均收敛于同一结构，优化设计与直接TMM计算结果吻合度高，FOM误差为0.6-0.9%，Rmin误差低于0.7%。ML模型的R²值均大于0.99，计算成本从秒级降至毫秒级，与直接TMM模拟相比加速约10³至10⁴倍。总体而言，结果表明，基于物理的代理ML模型结合可解释性与优化，为快速SPR传感器分析、逆设计及优化提供了计算高效且可解释的框架。
英文摘要
In this work, we demonstrate a data-driven machine learning (ML) framework for the efficient design and optimization of Kretschmann-configuration-based surface plasmon resonance (SPR) sensors. A physics-based dataset was generated using a MATLAB-based transfer matrix method (TMM), covering diverse material properties, layer thicknesses, and multilayer configurations. Optical properties and layer thicknesses were used as input features, while figure of merit (FOM) and minimum reflectance (Rmin) were the target performance parameters. Four ML models, namely CatBoost, XGBoost, LightGBM, and multilayer perceptron (MLP), were benchmarked using R2, mean absolute error (MAE), and root mean squared error (RMSE). The framework integrates ML benchmarking, SHAP explainability, robustness analysis, and optimization-driven inverse design. SHAP-weighted perturbation experiments assessed the model's robustness to input variations. Four optimization algorithms were employed for inverse sensor design, followed by an analysis of parameter recovery and performance. The optimizers were also evaluated using an independent forward-design task, in which repeated runs converged on a common configuration. The optimized designs agreed closely with direct TMM calculations, with FOM errors of 0.6-0.9 percent and Rmin errors below 0.7 percent. The ML models achieved R2 values greater than 0.99 while reducing computational cost from seconds to milliseconds, corresponding to an acceleration of approximately 10^3 to 10^4 times compared with direct TMM simulations. Overall, the results demonstrate that physics-based surrogate ML models combined with explainability and optimization provide a computationally efficient and interpretable framework for rapid SPR sensor analysis, inverse design, and optimization.
