AI-ready Snow Radar Echogram Dataset (SRED) for climate change monitoring

2025-05-01

AI Summary

To address the lack of standardized, high-quality annotated datasets for polar snow radar echograms—which hinders reproducibility, model comparability, and performance in snow layer tracking—this work introduces the first deep learning–oriented polar snow radar echogram dataset. It comprises 13,717 pixel-level precise annotations and 57,815 weakly labeled samples, spanning diverse snow regimes including dry snow, ablation zones, and wet snow. We establish a unified benchmark framework integrating five state-of-the-art semantic segmentation models (e.g., U-Net, DeepLabv3+), enabling systematic evaluation. Experiments confirm that existing models reliably segment snow layers but struggle with end-to-end regression of snow depth and annual accumulation rates. The fully open-sourced dataset and benchmark have emerged as a new standard in polar remote sensing AI research, significantly advancing methodologies for ice-sheet layer tracking and snow parameter retrieval.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Tracking internal layers in radar echograms with high accuracy is essential for understanding ice sheet dynamics and quantifying the impact of accelerated ice discharge in Greenland and other polar regions due to contemporary global climate warming. Deep learning algorithms have become the leading approach for automating this task, but the absence of a standardized and well-annotated echogram dataset has hindered the ability to test and compare algorithms reliably, limiting the advancement of state-of-the-art methods for the radar echogram layer tracking problem. This study introduces the first comprehensive ``deep learning ready'' radar echogram dataset derived from Snow Radar airborne data collected during the National Aeronautics and Space Administration Operation Ice Bridge (OIB) mission in 2012. The dataset contains 13,717 labeled and 57,815 weakly-labeled echograms covering diverse snow zones (dry, ablation, wet) with varying along-track resolutions. To demonstrate its utility, we evaluated the performance of five deep learning models on the dataset. Our results show that while current computer vision segmentation algorithms can identify and track snow layer pixels in echogram images, advanced end-to-end models are needed to directly extract snow depth and annual accumulation from echograms, reducing or eliminating post-processing. The dataset and accompanying benchmarking framework provide a valuable resource for advancing radar echogram layer tracking and snow accumulation estimation, advancing our understanding of polar ice sheets response to climate warming.

Problem

• Lack of standardized dataset for radar echogram layer tracking
• Need accurate ice sheet dynamics understanding for climate impact
• Requirement for advanced models to extract snow data directly

Innovation

• Introduces first deep learning ready radar dataset
• Evaluates five deep learning models performance
• Proposes advanced end-to-end models for extraction