Inversion of Ground Penetrating Radar Data Based on Neural Networks
Open Access
- 9 May 2018
- journal article
- letter
- Published by MDPI AG in Remote Sensing
- Vol. 10 (5) , 730
Abstract
We present a novel inversion approach using a neural network to locate subsurface targets and evaluate their backscattering properties from ground penetrating radar (GPR) data. The presented inversion strategy constructs an adaptive linear element (ADALINE) neural network, whose configuration is related to the unknown properties of the targets. The GPR data is reconstructed (compression) to fit the structure of the neural network. The constructed neural network works with a supervised training mode, where a series of primary functions derived from the GPR signal model are used as the input, and the reconstructed GPR data is the expected/target output. In this way, inverting the GPR data is the equivalent of training the network. The back-propagation (BP) algorithm is employed for the training of the neural network. The numerical experiments show that the proposed approach can return an exact estimation for the target’s location. Under sparse conditions, an inverted backscattering intensity with a relative error lower than 3% was achieved, whereas for the multi-dominating point scenario, a higher error rate was observed. Finally, the limitations and further developments for the inverting GPR data with the neural network are discussed.Keywords
Funding Information
- National Natural Science Foundation of China (61372160)
This publication has 21 references indexed in Scilit:
- 3D Ground Penetrating Radar to Detect Tree Roots and Estimate Root Biomass in the FieldRemote Sensing, 2014
- Improved Characterization of Fine-Texture Soils Using On-Ground GPR Full-Waveform InversionIEEE Transactions on Geoscience and Remote Sensing, 2013
- Non-destructive evaluation of concrete physical condition using radar and artificial neural networksConstruction and Building Materials, 2008
- Use of capacitive and GPR techniques for the non-destructive evaluation of cover concreteNDT & E International, 2008
- Ground-penetrating radar investigations for urban roadsProceedings of the Institution of Civil Engineers - Municipal Engineer, 2006
- Location of steel reinforcement in concrete using ground penetrating radar and neural networksNDT & E International, 2005
- An Electromagnetic Approach Based on Neural Networks for the GPR Investigation of Buried CylindersIEEE Geoscience and Remote Sensing Letters, 2005
- Neural detection of pipe signatures in ground penetrating radar imagesIEEE Transactions on Geoscience and Remote Sensing, 2000
- A kernel-based Adaline for function approximationIntelligent Data Analysis: An International Journal, 1999
- 30 years of adaptive neural networks: perceptron, Madaline, and backpropagationProceedings of the IEEE, 1990