Regression Networks For Calculating Englacial Layer Thickness

TL;DR

This paper introduces convolutional neural networks, specifically ResNet50, for estimating internal ice layer thickness from radar images, achieving low error rates and highlighting potential improvements through domain knowledge integration.

Contribution

The study applies regression neural networks to ice layer thickness estimation, demonstrating the effectiveness of ResNet50 with residual connections for this task.

Findings

Achieved mean absolute error of 1.251 pixels with ResNet50.

Regression networks outperform traditional methods in ice thickness estimation.

Embedding domain knowledge could further enhance accuracy.

Abstract

Ice thickness estimation is an important aspect of ice sheet studies. In this work, we use convolutional neural networks with multiple output nodes to regress and learn the thickness of internal ice layers in Snow Radar images collected in northwest Greenland. We experiment with some state-of-the-art networks and find that with the residual connections of ResNet50, we could achieve a mean absolute error of 1.251 pixels over the test set. Such regression-based networks can further be improved by embedding domain knowledge and radar information in the neural network in order to reduce the requirement of manual annotations.