MCD-Net: A Lightweight Deep Learning Baseline for Optical-Only Moraine Segmentation
This work addresses the challenge of glacial monitoring for climate research by providing a deployable baseline for optical-only moraine segmentation, though it is incremental as it builds on existing architectures.
The study tackled the problem of automated moraine segmentation from optical imagery by introducing a large-scale dataset and developing MCD-Net, a lightweight deep learning model that achieved 62.3% mIoU and 72.8% Dice coefficient while reducing computational cost by over 60%.
Glacial segmentation is essential for reconstructing past glacier dynamics and evaluating climate-driven landscape change. However, weak optical contrast and the limited availability of high-resolution DEMs hinder automated mapping. This study introduces the first large-scale optical-only moraine segmentation dataset, comprising 3,340 manually annotated high-resolution images from Google Earth covering glaciated regions of Sichuan and Yunnan, China. We develop MCD-Net, a lightweight baseline that integrates a MobileNetV2 encoder, a Convolutional Block Attention Module (CBAM), and a DeepLabV3+ decoder. Benchmarking against deeper backbones (ResNet152, Xception) shows that MCD-Net achieves 62.3% mean Intersection over Union (mIoU) and 72.8% Dice coefficient while reducing computational cost by more than 60%. Although ridge delineation remains constrained by sub-pixel width and spectral ambiguity, the results demonstrate that optical imagery alone can provide reliable moraine-body segmentation. The dataset and code are publicly available at https://github.com/Lyra-alpha/MCD-Net, establishing a reproducible benchmark for moraine-specific segmentation and offering a deployable baseline for high-altitude glacial monitoring.