Changes over the Last 35 Years in Alaska’s Glaciated Landscape: A Novel Deep Learning Approach to Mapping Glaciers at Fine Temporal Granularity

Glaciers are important sentinels of a changing climate, crucial components of the global cryosphere and integral to their local landscapes. However, many of the commonly used methods for mapping glacier change are labor-intensive and limit the temporal and spatial scope of existing research. This st...

Full description

Bibliographic Details
Published in:Remote Sensing
Main Authors: Ben M. Roberts-Pierel, Peter B. Kirchner, John B. Kilbride, Robert E. Kennedy
Format: Article in Journal/Newspaper
Language:English
Published: MDPI AG 2022
Subjects:
Q
Online Access:https://doi.org/10.3390/rs14184582
https://doaj.org/article/d52bf24dc2ee4240bcc25f09172e3d9f
id ftdoajarticles:oai:doaj.org/article:d52bf24dc2ee4240bcc25f09172e3d9f
record_format openpolar
spelling ftdoajarticles:oai:doaj.org/article:d52bf24dc2ee4240bcc25f09172e3d9f 2023-05-15T15:46:59+02:00 Changes over the Last 35 Years in Alaska’s Glaciated Landscape: A Novel Deep Learning Approach to Mapping Glaciers at Fine Temporal Granularity Ben M. Roberts-Pierel Peter B. Kirchner John B. Kilbride Robert E. Kennedy 2022-09-01T00:00:00Z https://doi.org/10.3390/rs14184582 https://doaj.org/article/d52bf24dc2ee4240bcc25f09172e3d9f EN eng MDPI AG https://www.mdpi.com/2072-4292/14/18/4582 https://doaj.org/toc/2072-4292 doi:10.3390/rs14184582 2072-4292 https://doaj.org/article/d52bf24dc2ee4240bcc25f09172e3d9f Remote Sensing, Vol 14, Iss 4582, p 4582 (2022) glacier change glacier inventory deep learning neural network remote sensing Landsat Science Q article 2022 ftdoajarticles https://doi.org/10.3390/rs14184582 2022-12-30T22:02:17Z Glaciers are important sentinels of a changing climate, crucial components of the global cryosphere and integral to their local landscapes. However, many of the commonly used methods for mapping glacier change are labor-intensive and limit the temporal and spatial scope of existing research. This study addresses some of the limitations of prior approaches by developing a novel deep-learning-based method called GlacierCoverNet. GlacierCoverNet is a deep neural network that relies on an extensive, purpose-built training dataset. Using this model, we created a record of over three decades long at a fine temporal cadence (every two years) for the state of Alaska. We conducted a robust error analysis of this dataset and then used the dataset to characterize changes in debris-free glaciers and supraglacial debris over the last ~35 years. We found that our deep learning model could produce maps comparable to existing approaches in the capture of areal extent, but without manual editing required. The model captured the area covered with glaciers that was ~97% of the Randolph Glacier Inventory 6.0 with ~6% and ~9% omission and commission rates in the southern portion of Alaska, respectively. The overall model area capture was lower and omission and commission rates were significantly higher in the northern Brooks Range. Overall, the glacier-covered area retreated by 8425 km 2 (−13%) between 1985 and 2020, and supraglacial debris expanded by 2799 km 2 (64%) during the same period across the state of Alaska. Article in Journal/Newspaper Brooks Range glacier glaciers Alaska Directory of Open Access Journals: DOAJ Articles Remote Sensing 14 18 4582
institution Open Polar
collection Directory of Open Access Journals: DOAJ Articles
op_collection_id ftdoajarticles
language English
topic glacier change
glacier inventory
deep learning
neural network
remote sensing
Landsat
Science
Q
spellingShingle glacier change
glacier inventory
deep learning
neural network
remote sensing
Landsat
Science
Q
Ben M. Roberts-Pierel
Peter B. Kirchner
John B. Kilbride
Robert E. Kennedy
Changes over the Last 35 Years in Alaska’s Glaciated Landscape: A Novel Deep Learning Approach to Mapping Glaciers at Fine Temporal Granularity
topic_facet glacier change
glacier inventory
deep learning
neural network
remote sensing
Landsat
Science
Q
description Glaciers are important sentinels of a changing climate, crucial components of the global cryosphere and integral to their local landscapes. However, many of the commonly used methods for mapping glacier change are labor-intensive and limit the temporal and spatial scope of existing research. This study addresses some of the limitations of prior approaches by developing a novel deep-learning-based method called GlacierCoverNet. GlacierCoverNet is a deep neural network that relies on an extensive, purpose-built training dataset. Using this model, we created a record of over three decades long at a fine temporal cadence (every two years) for the state of Alaska. We conducted a robust error analysis of this dataset and then used the dataset to characterize changes in debris-free glaciers and supraglacial debris over the last ~35 years. We found that our deep learning model could produce maps comparable to existing approaches in the capture of areal extent, but without manual editing required. The model captured the area covered with glaciers that was ~97% of the Randolph Glacier Inventory 6.0 with ~6% and ~9% omission and commission rates in the southern portion of Alaska, respectively. The overall model area capture was lower and omission and commission rates were significantly higher in the northern Brooks Range. Overall, the glacier-covered area retreated by 8425 km 2 (−13%) between 1985 and 2020, and supraglacial debris expanded by 2799 km 2 (64%) during the same period across the state of Alaska.
format Article in Journal/Newspaper
author Ben M. Roberts-Pierel
Peter B. Kirchner
John B. Kilbride
Robert E. Kennedy
author_facet Ben M. Roberts-Pierel
Peter B. Kirchner
John B. Kilbride
Robert E. Kennedy
author_sort Ben M. Roberts-Pierel
title Changes over the Last 35 Years in Alaska’s Glaciated Landscape: A Novel Deep Learning Approach to Mapping Glaciers at Fine Temporal Granularity
title_short Changes over the Last 35 Years in Alaska’s Glaciated Landscape: A Novel Deep Learning Approach to Mapping Glaciers at Fine Temporal Granularity
title_full Changes over the Last 35 Years in Alaska’s Glaciated Landscape: A Novel Deep Learning Approach to Mapping Glaciers at Fine Temporal Granularity
title_fullStr Changes over the Last 35 Years in Alaska’s Glaciated Landscape: A Novel Deep Learning Approach to Mapping Glaciers at Fine Temporal Granularity
title_full_unstemmed Changes over the Last 35 Years in Alaska’s Glaciated Landscape: A Novel Deep Learning Approach to Mapping Glaciers at Fine Temporal Granularity
title_sort changes over the last 35 years in alaska’s glaciated landscape: a novel deep learning approach to mapping glaciers at fine temporal granularity
publisher MDPI AG
publishDate 2022
url https://doi.org/10.3390/rs14184582
https://doaj.org/article/d52bf24dc2ee4240bcc25f09172e3d9f
genre Brooks Range
glacier
glaciers
Alaska
genre_facet Brooks Range
glacier
glaciers
Alaska
op_source Remote Sensing, Vol 14, Iss 4582, p 4582 (2022)
op_relation https://www.mdpi.com/2072-4292/14/18/4582
https://doaj.org/toc/2072-4292
doi:10.3390/rs14184582
2072-4292
https://doaj.org/article/d52bf24dc2ee4240bcc25f09172e3d9f
op_doi https://doi.org/10.3390/rs14184582
container_title Remote Sensing
container_volume 14
container_issue 18
container_start_page 4582
_version_ 1766381798189694976