Abstract
This article focuses on the possible drawbacks and pitfalls in the GPR data interpretation process commonly followed by most GPR practitioners in archaeological prospection. Standard processing techniques aim to remove some noise, enhance reflections of the subsurface. Next, one has to calculate the instantaneous envelope and produce C-scans which are 2D amplitude maps showing high reflectivity surfaces. These amplitude maps are mainly used for data interpretation and provide a good insight into the subsurface but cannot fully describe it. The main limitations are discussed while studies aiming to overcome them are reviewed. These studies involve integrated interpretation approaches using both B-scans and C-scans, attribute analysis, fusion approaches, and recent attempts to automatically interpret C-scans using Deep Learning (DL) algorithms. To contribute to the automatic interpretation of GPR data using DL, an application of Convolutional Neural Networks (CNNs) to classify GPR data is also presented and discussed.
Highlights
The interpretation of Ground Penetrating Radar (GPR) data collected from archaeological surveys using the common-offset systems is often a challenging task that requires time, experience, and skill
Even though similar studies for archeological prospection are currently lacking, there are some interesting examples that use GPR data derived from civil engineering applications, which show that Deep Learning (DL) is a promising direction worth investigating
The training datasets were constructed from scratch using data collected from several archaeological sites, 50 of them being located in Greece, 1 in Cyprus, and 1 in Naxos, In this example, the application of Convolutional Neural Networks (CNNs) using AlexNet architecture [48] is presented and evaluated as a tool that provides useful insights, contributes to data interpretation, and classifies ancient, buried structures from GPR C-scans
Summary
The interpretation of Ground Penetrating Radar (GPR) data collected from archaeological surveys using the common-offset systems is often a challenging task that requires time, experience, and skill. Two-dimensional reflection profiles called B-scans are collected. B-scans are complex and non-intuitive to interpret, making it difficult to identify the reflections related to the archaeological context. The archaeological surveys with GPR follow more or less the same approach that is established as a standard. The latter involves processing the collected survey grids by applying standard methods and techniques at the collected GPR B-scans to remove noise while enhancing reflections from the subsurface [2,3]. A pseudo 3D or 2.5D approach is followed to extract amplitude maps of the subsurface called C-scans. The step is to browse the resulted C-scans studying the presented reflections and interpreting the reflectors. Other examples that show the importance of integrating B-scans, C-scans, and iso-surface amplitudes for data interpretation are presented in Reference [10]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
