Ice-Unet: A Very High-Resolution UAV-Optimized Deep Learning Model for Sea Ice Classification

Polar sea ice monitoring is critical for global climate research and Arctic ship navigation, yet traditional satellite remote sensing struggles to resolve micro-scale ice features due to resolution and weather constraints. This study presents a novel sea ice classification method integrating UAV-derived high-resolution optical imagery from the 2024 “Sun Yat-sen University Polar Vessel” Arctic expedition with deep learning. The dataset, comprising four types (sea ice, melt ponds, open water, ships), was constructed through geometric correction, and semi-automated annotation using the ISAT-SAM approach. The proposed Ice-Unet model, optimized via transfer learning from pre-trained weights, employs a VGG16-inspired backbone with multi-scale feature fusion and downscaling mechanisms for semantic segmentation. Comparative evaluations against DeepLabV3+ (Xception/MobileNet), PSPNet (ResNet50), and HRNet demonstrate Ice-Unet’s superiority, achieving leading IoU of 95.07% and recall rates of 97.11%, particularly excelling in melt pond detection and ice lead morphology characterization. Case analysis reveals precise quantification of melt pond spatial patterns and predictive capability for their evolution into sea ice leads. The research empirically confirms the operational synergy between UAV platforms and deep learning architectures in monitoring transient sea ice dynamics, establishing a sub-meter resolution methodology that significantly enhances the precision of sea ice classification based ship navigation through near-real-time geospatial analytics.