Deep Ice Layer Tracking and Thickness Estimation using Fully Convolutional Networks

TL;DR

This paper presents a novel deep learning approach using Fully Convolutional Networks to automatically detect and estimate the thickness of internal ice layers from Snow Radar images, aiding climate change monitoring.

Contribution

It introduces the first automated method for detecting and measuring individual ice layer thicknesses using deep learning and semantic segmentation on radar images.

Findings

Achieved a mean absolute error of approximately 3.6 pixels in thickness estimation.

Performed multi-class semantic segmentation to identify ice layers.

Developed a pre-processing technique for training label generation.

Abstract

Global warming is rapidly reducing glaciers and ice sheets across the world. Real time assessment of this reduction is required so as to monitor its global climatic impact. In this paper, we introduce a novel way of estimating the thickness of each internal ice layer using Snow Radar images and Fully Convolutional Networks. The estimated thickness can be used to understand snow accumulation each year. To understand the depth and structure of each internal ice layer, we perform multi-class semantic segmentation on radar images, which hasn't been performed before. As the radar images lack good training labels, we carry out a pre-processing technique to get a clean set of labels. After detecting each ice layer uniquely, we calculate its thickness and compare it with the processed ground truth. This is the first time that each ice layer is detected separately and its thickness calculated through automated techniques. Through this procedure we were able to estimate the ice-layer thicknesses within a Mean Absolute Error of approximately 3.6 pixels. Such a Deep Learning based method can be used with ever-increasing datasets to make accurate assessments for cryospheric studies.