DMRF-UNet: A Two-Stage Deep Learning Scheme for GPR Data Inversion Under Heterogeneous Soil Conditions

• Published in: IEEE transactions on antennas and propagation Vol. 70; no. 8; pp. 6313 - 6328
• Main Authors: Dai, Qiqi, Lee, Yee Hui, Sun, Hai-Han, Ow, Genevieve, Yusof, Mohamed Lokman Mohd, Yucel, Abdulkadir C.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Clutter; Convolution; Deep learning; Deep neural network (DNN); Ground penetrating radar; ground-penetrating radar (GPR) data inversion; heterogeneous soil conditions; Image reconstruction; Inhomogeneity; Iterative algorithms; Iterative methods; Machine learning; Noise measurement; Permittivity; Reflection; Soil; Soil conditions; Soils; Training

Traditional ground-penetrating radar (GPR) data inversion leverages iterative algorithms that suffer from high computation costs and low accuracy when applied to complex subsurface scenarios. Existing deep learning-based methods focus on the ideal homogeneous subsurface environments and ignore the i...