REGRESSION NETWORKS FOR CALCULATING ENGLACIAL LAYER THICKNESS

Debvrat Varshney; Maryam Rahnemoonfar; Masoud Yari; John Paden

doi:10.1109/IGARSS47720.2021.9553596

REGRESSION NETWORKS FOR CALCULATING ENGLACIAL LAYER THICKNESS

Debvrat Varshney, Maryam Rahnemoonfar, Masoud Yari, John Paden

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Ice thickness estimation is an important aspect of ice sheet modelling. In this work, we use convolutional neural networks (CNN) with multiple output nodes to regress and learn the thickness of internal ice layers in Snow Radar images captured over northwest Greenland. We experiment with some state-of-the-art CNNs to obtain a mean absolute error of 1.251 pixels of thickness estimation 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.

Original language	English
Title of host publication	IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2393-2396
Number of pages	4
ISBN (Electronic)	9781665403696
DOIs	https://doi.org/10.1109/IGARSS47720.2021.9553596
State	Published - 2021
Externally published	Yes
Event	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Brussels, Belgium Duration: Jul 12 2021 → Jul 16 2021

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2021-July

Conference

Conference	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Country/Territory	Belgium
City	Brussels
Period	07/12/21 → 07/16/21

Funding

This work is supported by NSF BIGDATA awards (IIS-1838230, IIS-1838024), IBM, and Amazon.

Keywords

Convolutional neural networks
Englacial ice thickness
Radar
Regression

Access to Document

10.1109/IGARSS47720.2021.9553596

Cite this

Varshney, D., Rahnemoonfar, M., Yari, M., & Paden, J. (2021). REGRESSION NETWORKS FOR CALCULATING ENGLACIAL LAYER THICKNESS. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 2393-2396). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2021-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS47720.2021.9553596

@inproceedings{9a632da789e44420ae44e1c4836d4719,

title = "REGRESSION NETWORKS FOR CALCULATING ENGLACIAL LAYER THICKNESS",

abstract = "Ice thickness estimation is an important aspect of ice sheet modelling. In this work, we use convolutional neural networks (CNN) with multiple output nodes to regress and learn the thickness of internal ice layers in Snow Radar images captured over northwest Greenland. We experiment with some state-of-the-art CNNs to obtain a mean absolute error of 1.251 pixels of thickness estimation 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.",

keywords = "Convolutional neural networks, Englacial ice thickness, Radar, Regression",

author = "Debvrat Varshney and Maryam Rahnemoonfar and Masoud Yari and John Paden",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE; 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 ; Conference date: 12-07-2021 Through 16-07-2021",

year = "2021",

doi = "10.1109/IGARSS47720.2021.9553596",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2393--2396",

booktitle = "IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

}

Varshney, D, Rahnemoonfar, M, Yari, M & Paden, J 2021, REGRESSION NETWORKS FOR CALCULATING ENGLACIAL LAYER THICKNESS. in IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2021-July, Institute of Electrical and Electronics Engineers Inc., pp. 2393-2396, 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium, 07/12/21. https://doi.org/10.1109/IGARSS47720.2021.9553596

REGRESSION NETWORKS FOR CALCULATING ENGLACIAL LAYER THICKNESS. / Varshney, Debvrat; Rahnemoonfar, Maryam; Yari, Masoud et al.
IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. p. 2393-2396 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2021-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - REGRESSION NETWORKS FOR CALCULATING ENGLACIAL LAYER THICKNESS

AU - Varshney, Debvrat

AU - Rahnemoonfar, Maryam

AU - Yari, Masoud

AU - Paden, John

PY - 2021

Y1 - 2021

N2 - Ice thickness estimation is an important aspect of ice sheet modelling. In this work, we use convolutional neural networks (CNN) with multiple output nodes to regress and learn the thickness of internal ice layers in Snow Radar images captured over northwest Greenland. We experiment with some state-of-the-art CNNs to obtain a mean absolute error of 1.251 pixels of thickness estimation 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.

AB - Ice thickness estimation is an important aspect of ice sheet modelling. In this work, we use convolutional neural networks (CNN) with multiple output nodes to regress and learn the thickness of internal ice layers in Snow Radar images captured over northwest Greenland. We experiment with some state-of-the-art CNNs to obtain a mean absolute error of 1.251 pixels of thickness estimation 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.

KW - Convolutional neural networks

KW - Englacial ice thickness

KW - Radar

KW - Regression

UR - http://www.scopus.com/inward/record.url?scp=85126037512&partnerID=8YFLogxK

U2 - 10.1109/IGARSS47720.2021.9553596

DO - 10.1109/IGARSS47720.2021.9553596

M3 - Conference contribution

AN - SCOPUS:85126037512

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 2393

EP - 2396

BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

Y2 - 12 July 2021 through 16 July 2021

ER -

Varshney D, Rahnemoonfar M, Yari M, Paden J. REGRESSION NETWORKS FOR CALCULATING ENGLACIAL LAYER THICKNESS. In IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. p. 2393-2396. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS47720.2021.9553596

REGRESSION NETWORKS FOR CALCULATING ENGLACIAL LAYER THICKNESS

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this