Assessing Annotation Accuracy in Ice Sheets Using Quantitative Metrics

TL;DR

This paper introduces quantitative metrics to evaluate the accuracy of ice sheet annotation methods, comparing manual and automated techniques like ARESELP and MARESELP, to improve data interpretation for climate change studies.

Contribution

It presents a novel suite of computer vision metrics tailored for ice sheet annotation validation, enhancing automated methods' accuracy against expert annotations.

Findings

Automated MARESELP improves layer continuity.

Metrics effectively evaluate annotation quality.

Automated methods approach expert-level accuracy.

Abstract

The increasing threat of sea level rise due to climate change necessitates a deeper understanding of ice sheet structures. This study addresses the need for accurate ice sheet data interpretation by introducing a suite of quantitative metrics designed to validate ice sheet annotation techniques. Focusing on both manual and automated methods, including ARESELP and its modified version, MARESELP, we assess their accuracy against expert annotations. Our methodology incorporates several computer vision metrics, traditionally underutilized in glaciological research, to evaluate the continuity and connectivity of ice layer annotations. The results demonstrate that while manual annotations provide invaluable expert insights, automated methods, particularly MARESELP, improve layer continuity and alignment with expert labels.