Evaluating aufeis detection methods using Landsat imagery: Comparative assessment and recommendations

In the continuous permafrost environment of the North Slope of Alaska, extensive aufeis fields develop each winter on river floodplains, primarily via discharge from perennial springs. Currently, changes to the spatial and temporal distribution of large aufeis fields are predominantly monitored usin...

Full description

Saved in:
Bibliographic Details
Main Authors: Julian Dann, Simon Zwieback, Paul Leonard, W. Robert Bolton
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Science of Remote Sensing
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666017225000367
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850217751537254400
author Julian Dann
Simon Zwieback
Paul Leonard
W. Robert Bolton
author_facet Julian Dann
Simon Zwieback
Paul Leonard
W. Robert Bolton
author_sort Julian Dann
collection DOAJ
description In the continuous permafrost environment of the North Slope of Alaska, extensive aufeis fields develop each winter on river floodplains, primarily via discharge from perennial springs. Currently, changes to the spatial and temporal distribution of large aufeis fields are predominantly monitored using optical satellite imagery. However, existing detection methods struggle to distinguish between snow and ice surfaces.This study compares the accuracy of two techniques for identifying aufeis in a dataset comprising 515 Landsat optical images across four aufeis fields on the North Slope of Alaska. The first method involves empirical thresholding on snow and ice indices (2FT), while the second applies random forest (RF) machine learning methods. We evaluate their performance on multiple training and test datasets with pixel-, image-, and site-based stratification. Additionally, we evaluate the utility of additional bands and indices in aufeis detection using a grid-search for the top features (3FT) and feature importance metrics.The more complex RF classifier, which relies on an extensive training dataset, outperforms both feature thresholding methods across all validation datasets with an average F1 score of 0.967±0.029. Feature importance metrics indicate that the near-infrared is effective for distinguishing between snow and ice surfaces. These findings demonstrate that machine learning approaches significantly enhance aufeis detection capabilities in snow-affected scenes and improve the retrieval of the annual maximum aufeis extent. While scaling challenges remain for these techniques, the results provide a foundation for improving our ability to monitor regional aufeis dynamics and their role in hydrologic and permafrost systems.
format Article
id doaj-art-98d6ebf24bb44a6680a7aa4fc9285b1c
institution OA Journals
issn 2666-0172
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Science of Remote Sensing
spelling doaj-art-98d6ebf24bb44a6680a7aa4fc9285b1c2025-08-20T02:07:59ZengElsevierScience of Remote Sensing2666-01722025-06-011110023010.1016/j.srs.2025.100230Evaluating aufeis detection methods using Landsat imagery: Comparative assessment and recommendationsJulian Dann0Simon Zwieback1Paul Leonard2W. Robert Bolton3Alaska Climate Adaptation Science Center, University of Alaska Fairbanks, Fairbanks, AK, USA; Corresponding author.Geophysical Institute, University of Alaska Fairbanks, Fairbanks, AK, USAFairbanks Fish and Wildlife Field Office, U.S. Fish and Wildlife Service, Fairbanks, AK, USAEnvironmental Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN, USAIn the continuous permafrost environment of the North Slope of Alaska, extensive aufeis fields develop each winter on river floodplains, primarily via discharge from perennial springs. Currently, changes to the spatial and temporal distribution of large aufeis fields are predominantly monitored using optical satellite imagery. However, existing detection methods struggle to distinguish between snow and ice surfaces.This study compares the accuracy of two techniques for identifying aufeis in a dataset comprising 515 Landsat optical images across four aufeis fields on the North Slope of Alaska. The first method involves empirical thresholding on snow and ice indices (2FT), while the second applies random forest (RF) machine learning methods. We evaluate their performance on multiple training and test datasets with pixel-, image-, and site-based stratification. Additionally, we evaluate the utility of additional bands and indices in aufeis detection using a grid-search for the top features (3FT) and feature importance metrics.The more complex RF classifier, which relies on an extensive training dataset, outperforms both feature thresholding methods across all validation datasets with an average F1 score of 0.967±0.029. Feature importance metrics indicate that the near-infrared is effective for distinguishing between snow and ice surfaces. These findings demonstrate that machine learning approaches significantly enhance aufeis detection capabilities in snow-affected scenes and improve the retrieval of the annual maximum aufeis extent. While scaling challenges remain for these techniques, the results provide a foundation for improving our ability to monitor regional aufeis dynamics and their role in hydrologic and permafrost systems.http://www.sciencedirect.com/science/article/pii/S2666017225000367AufeisLandsatSnow & iceIcingNaledRandom forest
spellingShingle Julian Dann
Simon Zwieback
Paul Leonard
W. Robert Bolton
Evaluating aufeis detection methods using Landsat imagery: Comparative assessment and recommendations
Science of Remote Sensing
Aufeis
Landsat
Snow & ice
Icing
Naled
Random forest
title Evaluating aufeis detection methods using Landsat imagery: Comparative assessment and recommendations
title_full Evaluating aufeis detection methods using Landsat imagery: Comparative assessment and recommendations
title_fullStr Evaluating aufeis detection methods using Landsat imagery: Comparative assessment and recommendations
title_full_unstemmed Evaluating aufeis detection methods using Landsat imagery: Comparative assessment and recommendations
title_short Evaluating aufeis detection methods using Landsat imagery: Comparative assessment and recommendations
title_sort evaluating aufeis detection methods using landsat imagery comparative assessment and recommendations
topic Aufeis
Landsat
Snow & ice
Icing
Naled
Random forest
url http://www.sciencedirect.com/science/article/pii/S2666017225000367
work_keys_str_mv AT juliandann evaluatingaufeisdetectionmethodsusinglandsatimagerycomparativeassessmentandrecommendations
AT simonzwieback evaluatingaufeisdetectionmethodsusinglandsatimagerycomparativeassessmentandrecommendations
AT paulleonard evaluatingaufeisdetectionmethodsusinglandsatimagerycomparativeassessmentandrecommendations
AT wrobertbolton evaluatingaufeisdetectionmethodsusinglandsatimagerycomparativeassessmentandrecommendations