Subsurface Cavity Imaging Based on UNET and Cross–Hole Radar Travel–Time Fingerprint Construction

As a significant geological hazard in large–scale engineering construction, deep subsurface voids demand effective and precise detection methods. Cross–hole radar tomography overcomes depth limitations by transmitting/receiving electromagnetic (EM) waves between boreholes, enabling the accurate dete...

Full description

Saved in:
Bibliographic Details
Main Authors: Hui Cheng, Yonghui Zhao, Kunwei Feng
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/12/1986
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850164585504440320
author Hui Cheng
Yonghui Zhao
Kunwei Feng
author_facet Hui Cheng
Yonghui Zhao
Kunwei Feng
author_sort Hui Cheng
collection DOAJ
description As a significant geological hazard in large–scale engineering construction, deep subsurface voids demand effective and precise detection methods. Cross–hole radar tomography overcomes depth limitations by transmitting/receiving electromagnetic (EM) waves between boreholes, enabling the accurate determination of the spatial distribution and EM properties of subsurface cavities. However, conventional inversion approaches, such as travel–time/attenuation tomography and full–waveform inversion, still face challenges in terms of their stability, accuracy, and computational efficiency. To address these limitations, this study proposes a deep learning–based imaging method that introduces the concept of travel–time fingerprints, which compress raw radar data into structured, low–dimensional inputs that retain key spatial features. A large synthetic dataset of irregular subsurface cavity models is used to pre–train a UNET model, enabling it to learn nonlinear mapping, from fingerprints to velocity structures. To enhance real–world applicability, transfer learning (TL) is employed to fine–tune the model using a small amount of field data. The refined model is then tested on cross–hole radar datasets collected from a highway construction site in Guizhou Province, China. The results demonstrate that the method can accurately recover the shape, location, and extent of underground cavities, outperforming traditional tomography in terms of clarity and interpretability. This approach offers a high–precision, computationally efficient solution for subsurface void detection, with strong engineering applicability in complex geological environments.
format Article
id doaj-art-f8828cbfc6dc4e4681f6cd09b3a64c90
institution OA Journals
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-f8828cbfc6dc4e4681f6cd09b3a64c902025-08-20T02:21:57ZengMDPI AGRemote Sensing2072-42922025-06-011712198610.3390/rs17121986Subsurface Cavity Imaging Based on UNET and Cross–Hole Radar Travel–Time Fingerprint ConstructionHui Cheng0Yonghui Zhao1Kunwei Feng2School of Ocean & Earth Science, Tongji University, Shanghai 200092, ChinaSchool of Ocean & Earth Science, Tongji University, Shanghai 200092, ChinaGuizhou Transportation Planning Survey & Design Academe Co., Ltd., Guiyang 550081, ChinaAs a significant geological hazard in large–scale engineering construction, deep subsurface voids demand effective and precise detection methods. Cross–hole radar tomography overcomes depth limitations by transmitting/receiving electromagnetic (EM) waves between boreholes, enabling the accurate determination of the spatial distribution and EM properties of subsurface cavities. However, conventional inversion approaches, such as travel–time/attenuation tomography and full–waveform inversion, still face challenges in terms of their stability, accuracy, and computational efficiency. To address these limitations, this study proposes a deep learning–based imaging method that introduces the concept of travel–time fingerprints, which compress raw radar data into structured, low–dimensional inputs that retain key spatial features. A large synthetic dataset of irregular subsurface cavity models is used to pre–train a UNET model, enabling it to learn nonlinear mapping, from fingerprints to velocity structures. To enhance real–world applicability, transfer learning (TL) is employed to fine–tune the model using a small amount of field data. The refined model is then tested on cross–hole radar datasets collected from a highway construction site in Guizhou Province, China. The results demonstrate that the method can accurately recover the shape, location, and extent of underground cavities, outperforming traditional tomography in terms of clarity and interpretability. This approach offers a high–precision, computationally efficient solution for subsurface void detection, with strong engineering applicability in complex geological environments.https://www.mdpi.com/2072-4292/17/12/1986cross–hole radarcavityUNETtravel–time fingerprinttransfer learning
spellingShingle Hui Cheng
Yonghui Zhao
Kunwei Feng
Subsurface Cavity Imaging Based on UNET and Cross–Hole Radar Travel–Time Fingerprint Construction
Remote Sensing
cross–hole radar
cavity
UNET
travel–time fingerprint
transfer learning
title Subsurface Cavity Imaging Based on UNET and Cross–Hole Radar Travel–Time Fingerprint Construction
title_full Subsurface Cavity Imaging Based on UNET and Cross–Hole Radar Travel–Time Fingerprint Construction
title_fullStr Subsurface Cavity Imaging Based on UNET and Cross–Hole Radar Travel–Time Fingerprint Construction
title_full_unstemmed Subsurface Cavity Imaging Based on UNET and Cross–Hole Radar Travel–Time Fingerprint Construction
title_short Subsurface Cavity Imaging Based on UNET and Cross–Hole Radar Travel–Time Fingerprint Construction
title_sort subsurface cavity imaging based on unet and cross hole radar travel time fingerprint construction
topic cross–hole radar
cavity
UNET
travel–time fingerprint
transfer learning
url https://www.mdpi.com/2072-4292/17/12/1986
work_keys_str_mv AT huicheng subsurfacecavityimagingbasedonunetandcrossholeradartraveltimefingerprintconstruction
AT yonghuizhao subsurfacecavityimagingbasedonunetandcrossholeradartraveltimefingerprintconstruction
AT kunweifeng subsurfacecavityimagingbasedonunetandcrossholeradartraveltimefingerprintconstruction