Unsupervised Detection of Underground Tunnels in Ground-Penetrating Radar Using Depth-Restricted Reconstruction Scoring
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionMachine Learning
AI summaryⓘ
The authors developed a way to detect hidden tunnels under pipelines without needing examples of tunnels for training. They used a special type of AI called a denoising convolutional autoencoder that learns what normal ground looks like by studying radar images. When the system sees unusual patterns, it flags them as potential tunnels, focusing only on specific depths where tunnels are likely. This method improved detection accuracy and reduced missed tunnels without using any labeled tunnel data. Their final model worked well on real field data with very few false alarms.
ground-penetrating radardenoising convolutional autoencoderunsupervised anomaly detectionreconstruction errorpipeline securitydepth restrictiontop-k anomaly scoreAUCfalse alarm rateradargram
Authors
Muhammad Junaid, Shoab A. Khan, Nisar Ahmed
Abstract
Clandestine tunneling beneath oil and gas pipelines enables fuel theft, smuggling, and sabotage, yet conventional monitoring detects damage only after a pipeline has been compromised. Ground-penetrating radar (GPR) can image such tunnels non-invasively, but manual radargram interpretation does not scale to continuous corridor surveillance, and supervised detectors require tunnel examples that are scarce in practice. We present a fully unsupervised detection pipeline trained exclusively on normal subsurface radargrams collected at a purpose-built field site containing three buried tunnels at 1.5-3 m depth. A denoising convolutional autoencoder learns the structure of anomaly-free ground; at inference, tunnels are flagged by reconstruction error. Our central contribution is a depth-restricted top-k anomaly score, which pools the highest reconstruction errors only within the depth band where tunnels can physically occur. This physically motivated rule raises AUC from 0.986 to 0.994 and cuts missed detections from 74 to 17 of 634 tunnel windows, relative to whole-image scoring, without any retraining or labels. We further show that the optimal top-k fraction interacts with the depth restriction - 1% pooling is best on full images, 5% once scoring is depth-restricted - and that spatial voting across overlapping survey windows helps weak per-image detectors but offers no benefit once the scoring rule is strong. The final system attains AUC 0.994, F1 0.975, recall 0.973, and precision 0.976 on 1,600 field test windows spanning 55 survey lines, at a 1.6% false-alarm rate, using no tunnel labels for training, scoring, or threshold calibration.