TSSA: Two-Step Semi-Supervised Annotation for Radargrams on the Greenland Ice Sheet

Simple item page
dc.contributor.authorJebeli, Atefeh
dc.contributor.authorTama, Bayu Adhi
dc.contributor.authorJaneja, Vandana
dc.contributor.authorHolschuh, Nicholas
dc.contributor.authorJensen, Claire
dc.contributor.authorMorlighem, Mathieu
dc.contributor.authorMacGregor, Joseph A.
dc.contributor.authorFahnestock, Mark A.
dc.date.accessioned2024-08-27T20:38:02Z
dc.date.available2024-08-27T20:38:02Z
dc.date.issued2023-07
dc.descriptionIGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, 16-21 July 2023, Pasadena, CA, USA
dc.description.abstractIce-penetrating radar surveys have been conducted across the Greenland Ice Sheet since the 1960s, producing radargrams that measure ice thickness and detect the ice sheet’s radiostratigraphy. However, these radargrams are relatively under-explored and not yet fully annotated, mapped, or interpreted glaciologically. We aim to move towards automatic radargram annotation using deep learning-based methods. To provide a training set for these methods, we develop a two-step semi-supervised annotation (TSSA) approach that uses an existing unsupervised layer annotation (ARESELP) method and a deep learning-based segmentation approach (U-Net) to detect surface, and bottom reflectors (representing the bedrock) layers in radargrams. Here we focus on two evaluations of our approach: 1. Surface and bottom annotations; and 2. Data augmentation and transfer learning techniques for improving the performance of deep learning methods. Our study is a foundation for improving the efficacy of AI-based methods for auto-annotation of radargrams, where the training set is generated seamlessly through unsupervised learning.
dc.description.sponsorshipThis work is funded by the National Science Foundation (iHARP, Award #2118285). The authors would like to thank Dr. Sanjay Purushotham for insightful discussions.
dc.description.urihttps://ieeexplore.ieee.org/document/10282880
dc.format.extent4 pages
dc.genreconference papers and proceedings
dc.genrepostprints
dc.identifierdoi:10.13016/m22map-hcon
dc.identifier.citationJebeli, Atefeh, Bayu Adhi Tama, Vandana P. Janeja, Nicholas Holschuh, Claire Jensen, Mathieu Morlighem, Joseph A. MacGregor, and Mark A. Fahnestock. “TSSA: Two-Step Semi-Supervised Annotation for Radargrams on the Greenland Ice Sheet.” In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, 56–59, 2023. https://doi.org/10.1109/IGARSS52108.2023.10282880.
dc.identifier.urihttps://doi.org/10.1109/IGARSS52108.2023.10282880
dc.identifier.urihttp://hdl.handle.net/11603/35807
dc.language.isoen_US
dc.publisherIEEE
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Information Systems Department
dc.relation.ispartofUMBC Student Collection
dc.relation.ispartofUMBC Faculty Collection
dc.relation.ispartofUMBC College of Engineering and Information Technology Dean's Office
dc.rights© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
dc.subjectice sheet
dc.subjectTraining
dc.subjectComputational modeling
dc.subjectsupervised learning
dc.subjectDeep learning
dc.subjectunsupervised learning
dc.subjectAnnotations
dc.subjectData augmentation
dc.subjectTransfer learning
dc.subjectTransformers
dc.subjectdeep neural network
dc.subjectice penetrating radar
dc.titleTSSA: Two-Step Semi-Supervised Annotation for Radargrams on the Greenland Ice Sheet
dc.title.alternativeTSSA: two-step semi-supervised annotation for englacial radargrams on the Greenland ice sheet
dc.typeText
dcterms.creatorhttps://orcid.org/0000-0003-4043-2193
dcterms.creatorhttps://orcid.org/0000-0002-1821-6438
dcterms.creatorhttps://orcid.org/0000-0003-0130-6135

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
10426455.pdf
Size:
477.73 KB
Format:
Adobe Portable Document Format
Download

Collections

UMBC Information Systems Department
UMBC College of Engineering and Information Technology Dean's Office
UMBC Faculty Collection
UMBC Student Collection