Wang Zhaoyu, Zhang Qinghe, Shen Zhaoyang, Zhang Lei, Liu Han
College of Computer and Information Technology, China Three Gorges University, Yichang 443002, China.
Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering, China Three Gorges University, Yichang 443002, China.
Sensors (Basel). 2025 Apr 15;25(8):2481. doi: 10.3390/s25082481.
Numerical simulation of ground-penetrating radar (GPR) has been widely used to enhance the interpretation of GPR data and serves as a key component in Full Waveform Inversion (FWI). In response to the time-consuming numerical computation of layered medium and buried targets, which leads to inefficiency in full-wave inversion, this paper proposes a machine learning-based forward scattering rapid solution method. Using the detection of rebar buried in concrete under sand as the GPR application scenario, with scene parameters such as concrete moisture content, rebar radius, and burial depth, scattering echo signals are obtained via Finite Difference Time Domain (FDTD) simulation. Principal component analysis (PCA) is applied to reduce the dimensionality of the echo data, and the first 40 principal component weight coefficients are selected as the output of the deep learning network. An innovative cyclic nested deep learning network architecture is designed, which not only fully explores the intrinsic causal relationship between the scene parameters and the principal component weight coefficients, but also refines and corrects each predicted principal component. The numerical results demonstrate that, compared with traditional machine learning methods, the cyclic nested machine learning network architecture offers higher prediction accuracy and learning efficiency, validating the effectiveness of the proposed method.
探地雷达（GPR）的数值模拟已被广泛用于增强GPR数据的解释，并作为全波形反演（FWI）的关键组成部分。针对层状介质和埋藏目标数值计算耗时、导致全波反演效率低下的问题，本文提出了一种基于机器学习的前向散射快速求解方法。以砂土下混凝土中埋入钢筋的探测为GPR应用场景，结合混凝土含水量、钢筋半径、埋深等场景参数，通过时域有限差分（FDTD）模拟得到散射回波信号。应用主成分分析（PCA）对回波数据进行降维，选取前40个主成分权重系数作为深度学习网络的输出。设计了一种创新的循环嵌套深度学习网络架构，该架构不仅充分挖掘了场景参数与主成分权重系数之间的内在因果关系，还对每个预测主成分进行了细化和校正。数值结果表明，与传统机器学习方法相比，循环嵌套机器学习网络架构具有更高的预测精度和学习效率，验证了所提方法的有效性。
