Robust Recognition of Anomalous Distribution From Electrical Resistivity Tomography

Electrical resistivity tomography (ERT) is widely used for near-surface engineering investigations, but volume and shielding effects often blur anomaly geometry and hinder interpretation in conventional inversion sections. This paper introduces a multi-scale imaging-segmentation framework, ERTSegNet, that learns an end-to-end mapping from traditional inversion images to binary anomaly masks, thereby improving the interpretability of ERT reconstructions. ERTSegNet integrates Vision Mamba modules into a UNet-style encoder-decoder with dense multi-scale skip connections to capture long-range context while preserving local detail, and employs a randomized multi-scale training strategy to handle varying electrode configurations. Experiments on synthetic and field data demonstrate accurate anomaly delineation and strong robustness to scale mismatch.