Articles | Volume 16, issue 10
https://doi.org/10.5194/tc-16-4273-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/tc-16-4273-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
13 Oct 2022
Research article |
| 13 Oct 2022
| 13 Oct 2022
Glacier extraction based on high-spatial-resolution remote-sensing images using a deep-learning approach with attention mechanism
Xinde Chu
College of Geography and Environmental Science, Northwest Normal
University, Lanzhou, 730070, China
Xiaojun Yao
CORRESPONDING AUTHOR
College of Geography and Environmental Science, Northwest Normal
University, Lanzhou, 730070, China
Hongyu Duan
College of Geography and Environmental Science, Northwest Normal
University, Lanzhou, 730070, China
Cong Chen
Key Laboratory of Western China's Environmental Systems (Ministry of Education), College of Earth and Environmental Sciences, Lanzhou University, Lanzhou, 730000, China
Jing Li
College of Geography and Environmental Science, Northwest Normal
University, Lanzhou, 730070, China
Wenlong Pang
Xining Center of Natural Resources Comprehensive Survey, China
Geological Survey, Xining, 810000, China
Related authors
No articles found.
Fuming Xie, Shiyin Liu, Yongpeng Gao, Yu Zhu, Tobias Bolch, Andreas Kääb, Shimei Duan, Wenfei Miao, Jianfang Kang, Yaonan Zhang, Xiran Pan, Caixia Qin, Kunpeng Wu, Miaomiao Qi, Xianhe Zhang, Ying Yi, Fengze Han, Xiaojun Yao, Qiao Liu, Xin Wang, Zongli Jiang, Donghui Shangguan, Yong Zhang, Richard Grünwald, Muhammad Adnan, Jyoti Karki, and Muhammad Saifullah
Earth Syst. Sci. Data, 15, 847–867, https://doi.org/10.5194/essd-15-847-2023, https://doi.org/10.5194/essd-15-847-2023, 2023
Short summary
Short summary
In this study, first we generated inventories which allowed us to systematically detect glacier change patterns in the Karakoram range. We found that, by the 2020s, there were approximately 10 500 glaciers in the Karakoram mountains covering an area of 22 510.73 km2, of which ~ 10.2 % is covered by debris. During the past 30 years (from 1990 to 2020), the total glacier cover area in Karakoram remained relatively stable, with a slight increase in area of 23.5 km2.
Hongyu Duan, Xiaojun Yao, Yuan Zhang, Huian Jin, Qi Wang, Zhishui Du, Jiayu Hu, Bin Wang, and Qianxun Wang
The Cryosphere, 17, 591–616, https://doi.org/10.5194/tc-17-591-2023, https://doi.org/10.5194/tc-17-591-2023, 2023
Short summary
Short summary
We conducted a comprehensive investigation of Bienong Co, a moraine-dammed glacial lake on the southeastern Tibetan Plateau (SETP), to assess its potential hazards. The maximum lake depth is ~181 m, and the lake volume is ~102.3 × 106 m3. Bienong Co is the deepest known glacial lake with the same surface area on the Tibetan Plateau. Ice avalanches may produce glacial lake outburst floods that threaten the downstream area. This study could provide new insight into glacial lakes on the SETP.
Yu Zhu, Shiyin Liu, Junfeng Wei, Kunpeng Wu, Tobias Bolch, Junli Xu, Wanqin Guo, Zongli Jiang, Fuming Xie, Ying Yi, Donghui Shangguan, Xiaojun Yao, and Zhen Zhang
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2022-473, https://doi.org/10.5194/essd-2022-473, 2023
Preprint withdrawn
Short summary
Short summary
In this study, we presented a nearly complete inventory of glacier mass change dataset across the eastern Tibetan Plateau by using topographical maps, which will enhance the knowledge on the heterogeneity of glacier change before 2000. Our dataset, in combination with the published results, provide a nearly five decades mass balance to support hydrological simulation, and to evaluate the contribution of mountain glacier loss to sea level.
Meiping Sun, Sugang Zhou, Xiaojun Yao, Hongyu Duan, and Yuan Zhang
EGUsphere, https://doi.org/10.5194/egusphere-2022-765, https://doi.org/10.5194/egusphere-2022-765, 2022
Preprint withdrawn
Short summary
Short summary
For understanding the occurrence mechanism of surging glaciers in High Mountain Asia, it is essential to ascertain their amounts, distribution and periodicity. Based on images from Landsat satellite from 1986–2021, we identified 244 surging glaciers with high confidence and 2802 events of glacier surge. We also analyzed the periodicity of 36 glaciers which experienced two or more surges. The findings will benefit to enrich dataset and provide basic information of surging glaciers in HMA.
Dahong Zhang, Gang Zhou, Wen Li, Shiqiang Zhang, Xiaojun Yao, and Shimei Wei
Earth Syst. Sci. Data, 14, 3889–3913, https://doi.org/10.5194/essd-14-3889-2022, https://doi.org/10.5194/essd-14-3889-2022, 2022
Short summary
Short summary
The length of a glacier is a key determinant of its geometry; glacier centerlines are crucial inputs for many glaciological applications. Based on the European allocation theory, we present a new global dataset that includes the centerlines and lengths of 198 137 mountain glaciers. The accuracy of the glacier centerlines was 89.68 %. The constructed dataset comprises 17 sub-datasets which contain the centerlines and lengths of glacier tributaries.
Related subject area
Discipline: Glaciers | Subject: Remote Sensing
Refined glacial lake extraction in a high-Asia region by deep neural network and superpixel-based conditional random field methods
Annual to seasonal glacier mass balance in High Mountain Asia derived from Pléiades stereo images: examples from the Pamir and the Tibetan Plateau
Out-of-the-box calving-front detection method using deep learning
GLAcier Feature Tracking testkit (GLAFT): a statistically and physically based framework for evaluating glacier velocity products derived from optical satellite image feature tracking
Cast shadows reveal changes in glacier surface elevation
Characterizing the surge behaviour and associated ice-dammed lake evolution of the Kyagar Glacier in the Karakoram
Constraining regional glacier reconstructions using past ice thickness of deglaciating areas – a case study in the European Alps
Climatic control on seasonal variations in mountain glacier surface velocity
A low-cost and open-source approach for supraglacial debris thickness mapping using UAV-based infrared thermography
High-resolution debris-cover mapping using UAV-derived thermal imagery: limits and opportunities
Automated ArcticDEM iceberg detection tool: insights into area and volume distributions, and their potential application to satellite imagery and modelling of glacier–iceberg–ocean systems
TermPicks: a century of Greenland glacier terminus data for use in scientific and machine learning applications
Surge dynamics of Shisper Glacier revealed by time-series correlation of optical satellite images and their utility to substantiate a generalized sliding law
Offset of MODIS land surface temperatures from in situ air temperatures in the upper Kaskawulsh Glacier region (St. Elias Mountains) indicates near-surface temperature inversions
Three different glacier surges at a spot: what satellites observe and what not
Correlation dispersion as a measure to better estimate uncertainty in remotely sensed glacier displacements
Glacier and rock glacier changes since the 1950s in the La Laguna catchment, Chile
Brief communication: Increased glacier mass loss in the Russian High Arctic (2010–2017)
Contrasting surface velocities between lake- and land-terminating glaciers in the Himalayan region
Aerodynamic roughness length of crevassed tidewater glaciers from UAV mapping
Image classification of marine-terminating outlet glaciers in Greenland using deep learning methods
Brief communication: Detection of glacier surge activity using cloud computing of Sentinel-1 radar data
InSAR-based characterization of rock glacier movement in the Uinta Mountains, Utah, USA
Surface composition of debris-covered glaciers across the Himalaya using linear spectral unmixing of Landsat 8 OLI imagery
Mapping seasonal glacier melt across the Hindu Kush Himalaya with time series synthetic aperture radar (SAR)
Estimating surface mass balance patterns from unoccupied aerial vehicle measurements in the ablation area of the Morteratsch–Pers glacier complex (Switzerland)
High-resolution topography of the Antarctic Peninsula combining the TanDEM-X DEM and Reference Elevation Model of Antarctica (REMA) mosaic
Measuring the state and temporal evolution of glaciers in Alaska and Yukon using synthetic-aperture-radar-derived (SAR-derived) 3D time series of glacier surface flow
Tracking changes in the area, thickness, and volume of the Thwaites tabular iceberg “B30” using satellite altimetry and imagery
Analyzing glacier retreat and mass balances using aerial and UAV photogrammetry in the Ötztal Alps, Austria
Surges of Harald Moltke Bræ, north-western Greenland: seasonal modulation and initiation at the terminus
Brief communication: An empirical relation between center frequency and measured thickness for radar sounding of temperate glaciers
Glacier Image Velocimetry: an open-source toolbox for easy and rapid calculation of high-resolution glacier velocity fields
Calving Front Machine (CALFIN): glacial termini dataset and automated deep learning extraction method for Greenland, 1972–2019
Annual and inter-annual variability and trends of albedo of Icelandic glaciers
Observing traveling waves in glaciers with remote sensing: new flexible time series methods and application to Sermeq Kujalleq (Jakobshavn Isbræ), Greenland
Detecting seasonal ice dynamics in satellite images
Sharp contrasts in observed and modeled crevasse patterns at Greenland's marine terminating glaciers
Variability in glacier albedo and links to annual mass balance for the gardens of Eden and Allah, Southern Alps, New Zealand
The seasonal evolution of albedo across glaciers and the surrounding landscape of Taylor Valley, Antarctica
Recent glacier and lake changes in High Mountain Asia and their relation to precipitation changes
Multisensor validation of tidewater glacier flow fields derived from synthetic aperture radar (SAR) intensity tracking
Detecting dynamics of cave floor ice with selective cloud-to-cloud approach
Changes of the tropical glaciers throughout Peru between 2000 and 2016 – mass balance and area fluctuations
Iceberg topography and volume classification using TanDEM-X interferometry
Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach
Sensitivity of glacier volume change estimation to DEM void interpolation
Extracting recent short-term glacier velocity evolution over southern Alaska and the Yukon from a large collection of Landsat data
Change detection of bare-ice albedo in the Swiss Alps
Characterizing the behaviour of surge- and non-surge-type glaciers in the Kingata Mountains, eastern Pamir, from 1999 to 2016
Yungang Cao, Rumeng Pan, Meng Pan, Ruodan Lei, Puying Du, and Xueqin Bai
The Cryosphere, 18, 153–168, https://doi.org/10.5194/tc-18-153-2024, https://doi.org/10.5194/tc-18-153-2024, 2024
Short summary
Short summary
This study built a glacial lake dataset with 15376 samples in seven types and proposed an automatic method by two-stage (the semantic segmentation network and post-processing) optimizations to detect glacial lakes. The proposed method for glacial lake extraction has achieved the best results so far, in which the F1 score and IoU reached 0.945 and 0.907, respectively. The area of the minimum glacial lake that can be entirely and correctly extracted has been raised to the 100 m2 level.
Daniel Falaschi, Atanu Bhattacharya, Gregoire Guillet, Lei Huang, Owen King, Kriti Mukherjee, Philipp Rastner, Tandong Yao, and Tobias Bolch
The Cryosphere, 17, 5435–5458, https://doi.org/10.5194/tc-17-5435-2023, https://doi.org/10.5194/tc-17-5435-2023, 2023
Short summary
Short summary
Because glaciers are crucial freshwater sources in the lowlands surrounding High Mountain Asia, constraining short-term glacier mass changes is essential. We investigate the potential of state-of-the-art satellite elevation data to measure glacier mass changes in two selected regions. The results demonstrate the ability of our dataset to characterize glacier changes of different magnitudes, allowing for an increase in the number of inaccessible glaciers that can be readily monitored.
Oskar Herrmann, Nora Gourmelon, Thorsten Seehaus, Andreas Maier, Johannes J. Fürst, Matthias H. Braun, and Vincent Christlein
The Cryosphere, 17, 4957–4977, https://doi.org/10.5194/tc-17-4957-2023, https://doi.org/10.5194/tc-17-4957-2023, 2023
Short summary
Short summary
Delineating calving fronts of marine-terminating glaciers in satellite images is a labour-intensive task. We propose a method based on deep learning that automates this task. We choose a deep learning framework that adapts to any given dataset without needing deep learning expertise. The method is evaluated on a benchmark dataset for calving-front detection and glacier zone segmentation. The framework can beat the benchmark baseline without major modifications.
Whyjay Zheng, Shashank Bhushan, Maximillian Van Wyk De Vries, William Kochtitzky, David Shean, Luke Copland, Christine Dow, Renette Jones-Ivey, and Fernando Pérez
The Cryosphere, 17, 4063–4078, https://doi.org/10.5194/tc-17-4063-2023, https://doi.org/10.5194/tc-17-4063-2023, 2023
Short summary
Short summary
We design and propose a method that can evaluate the quality of glacier velocity maps. The method includes two numbers that we can calculate for each velocity map. Based on statistics and ice flow physics, velocity maps with numbers close to the recommended values are considered to have good quality. We test the method using the data from Kaskawulsh Glacier, Canada, and release an open-sourced software tool called GLAcier Feature Tracking testkit (GLAFT) to help users assess their velocity maps.
Monika Pfau, Georg Veh, and Wolfgang Schwanghart
The Cryosphere, 17, 3535–3551, https://doi.org/10.5194/tc-17-3535-2023, https://doi.org/10.5194/tc-17-3535-2023, 2023
Short summary
Short summary
Cast shadows have been a recurring problem in remote sensing of glaciers. We show that the length of shadows from surrounding mountains can be used to detect gains or losses in glacier elevation.
Guanyu Li, Mingyang Lv, Duncan J. Quincey, Liam S. Taylor, Xinwu Li, Shiyong Yan, Yidan Sun, and Huadong Guo
The Cryosphere, 17, 2891–2907, https://doi.org/10.5194/tc-17-2891-2023, https://doi.org/10.5194/tc-17-2891-2023, 2023
Short summary
Short summary
Kyagar Glacier in the Karakoram is well known for its surge history and its frequent blocking of the downstream valley, leading to a series of high-magnitude glacial lake outburst floods. Using it as a test bed, we develop a new approach for quantifying surge behaviour using successive digital elevation models. This method could be applied to other surge studies. Combined with the results from optical satellite images, we also reconstruct the surge process in unprecedented detail.
Christian Sommer, Johannes J. Fürst, Matthias Huss, and Matthias H. Braun
The Cryosphere, 17, 2285–2303, https://doi.org/10.5194/tc-17-2285-2023, https://doi.org/10.5194/tc-17-2285-2023, 2023
Short summary
Short summary
Knowledge on the volume of glaciers is important to project future runoff. Here, we present a novel approach to reconstruct the regional ice thickness distribution from easily available remote-sensing data. We show that past ice thickness, derived from spaceborne glacier area and elevation datasets, can constrain the estimated ice thickness. Based on the unique glaciological database of the European Alps, the approach will be most beneficial in regions without direct thickness measurements.
Ugo Nanni, Dirk Scherler, Francois Ayoub, Romain Millan, Frederic Herman, and Jean-Philippe Avouac
The Cryosphere, 17, 1567–1583, https://doi.org/10.5194/tc-17-1567-2023, https://doi.org/10.5194/tc-17-1567-2023, 2023
Short summary
Short summary
Surface melt is a major factor driving glacier movement. Using satellite images, we have tracked the movements of 38 glaciers in the Pamirs over 7 years, capturing their responses to rapid meteorological changes with unprecedented resolution. We show that in spring, glacier accelerations propagate upglacier, while in autumn, they propagate downglacier – all resulting from changes in meltwater input. This provides critical insights into the interplay between surface melt and glacier movement.
Jérôme Messmer and Alexander R. Groos
The Cryosphere Discuss., https://doi.org/10.5194/tc-2023-41, https://doi.org/10.5194/tc-2023-41, 2023
Revised manuscript accepted for TC
Short summary
Short summary
The lower part of mountain glaciers is often covered with debris. Knowing the thickness of the debris is important as it influences the melting and future evolution of the affected glaciers. We have developed an open-source approach to map variations in debris thickness on glaciers using a low-cost drone equipped with a thermal infrared camera. The resulting high-resolution maps of debris surface temperature and thickness enable more accurate monitoring and modelling of debris-covered glaciers.
Deniz Tobias Gök, Dirk Scherler, and Leif Stefan Anderson
The Cryosphere, 17, 1165–1184, https://doi.org/10.5194/tc-17-1165-2023, https://doi.org/10.5194/tc-17-1165-2023, 2023
Short summary
Short summary
We performed high-resolution debris-thickness mapping using land surface temperature (LST) measured from an unpiloted aerial vehicle (UAV) at various times of the day. LSTs from UAVs require calibration that varies in time. We test two approaches to quantify supraglacial debris cover, and we find that the non-linearity of the relationship between LST and debris thickness increases with LST. Choosing the best model to predict debris thickness depends on the time of the day and the terrain aspect.
Connor J. Shiggins, James M. Lea, and Stephen Brough
The Cryosphere, 17, 15–32, https://doi.org/10.5194/tc-17-15-2023, https://doi.org/10.5194/tc-17-15-2023, 2023
Short summary
Short summary
Iceberg detection is spatially and temporally limited around the Greenland Ice Sheet. This study presents a new, accessible workflow to automatically detect icebergs from timestamped ArcticDEM strip data. The workflow successfully produces comparable output to manual digitisation, with results revealing new iceberg area-to-volume conversion equations that can be widely applied to datasets where only iceberg outlines can be extracted (e.g. optical and SAR imagery).
Sophie Goliber, Taryn Black, Ginny Catania, James M. Lea, Helene Olsen, Daniel Cheng, Suzanne Bevan, Anders Bjørk, Charlie Bunce, Stephen Brough, J. Rachel Carr, Tom Cowton, Alex Gardner, Dominik Fahrner, Emily Hill, Ian Joughin, Niels J. Korsgaard, Adrian Luckman, Twila Moon, Tavi Murray, Andrew Sole, Michael Wood, and Enze Zhang
The Cryosphere, 16, 3215–3233, https://doi.org/10.5194/tc-16-3215-2022, https://doi.org/10.5194/tc-16-3215-2022, 2022
Short summary
Short summary
Terminus traces have been used to understand how Greenland's glaciers have changed over time; however, manual digitization is time-intensive, and a lack of coordination leads to duplication of efforts. We have compiled a dataset of over 39 000 terminus traces for 278 glaciers for scientific and machine learning applications. We also provide an overview of an updated version of the Google Earth Engine Digitization Tool (GEEDiT), which has been developed specifically for the Greenland Ice Sheet.
Flavien Beaud, Saif Aati, Ian Delaney, Surendra Adhikari, and Jean-Philippe Avouac
The Cryosphere, 16, 3123–3148, https://doi.org/10.5194/tc-16-3123-2022, https://doi.org/10.5194/tc-16-3123-2022, 2022
Short summary
Short summary
Understanding sliding at the bed of glaciers is essential to understand the future of sea-level rise and glacier-related hazards. Yet there is currently no universal law to describe this mechanism. We propose a universal glacier sliding law and a method to qualitatively constrain it. We use satellite remote sensing to create velocity maps over 6 years at Shisper Glacier, Pakistan, including its recent surge, and show that the observations corroborate the generalized theory.
Ingalise Kindstedt, Kristin M. Schild, Dominic Winski, Karl Kreutz, Luke Copland, Seth Campbell, and Erin McConnell
The Cryosphere, 16, 3051–3070, https://doi.org/10.5194/tc-16-3051-2022, https://doi.org/10.5194/tc-16-3051-2022, 2022
Short summary
Short summary
We show that neither the large spatial footprint of the MODIS sensor nor poorly constrained snow emissivity values explain the observed cold offset in MODIS land surface temperatures (LSTs) in the St. Elias. Instead, the offset is most prominent under conditions associated with near-surface temperature inversions. This work represents an advance in the application of MODIS LSTs to glaciated alpine regions, where we often depend solely on remote sensing products for temperature information.
Frank Paul, Livia Piermattei, Désirée Treichler, Lin Gilbert, Luc Girod, Andreas Kääb, Ludivine Libert, Thomas Nagler, Tazio Strozzi, and Jan Wuite
The Cryosphere, 16, 2505–2526, https://doi.org/10.5194/tc-16-2505-2022, https://doi.org/10.5194/tc-16-2505-2022, 2022
Short summary
Short summary
Glacier surges are widespread in the Karakoram and have been intensely studied using satellite data and DEMs. We use time series of such datasets to study three glacier surges in the same region of the Karakoram. We found strongly contrasting advance rates and flow velocities, maximum velocities of 30 m d−1, and a change in the surge mechanism during a surge. A sensor comparison revealed good agreement, but steep terrain and the two smaller glaciers caused limitations for some of them.
Bas Altena, Andreas Kääb, and Bert Wouters
The Cryosphere, 16, 2285–2300, https://doi.org/10.5194/tc-16-2285-2022, https://doi.org/10.5194/tc-16-2285-2022, 2022
Short summary
Short summary
Repeat overflights of satellites are used to estimate surface displacements. However, such products lack a simple error description for individual measurements, but variation in precision occurs, since the calculation is based on the similarity of texture. Fortunately, variation in precision manifests itself in the correlation peak, which is used for the displacement calculation. This spread is used to make a connection to measurement precision, which can be of great use for model inversion.
Benjamin Aubrey Robson, Shelley MacDonell, Álvaro Ayala, Tobias Bolch, Pål Ringkjøb Nielsen, and Sebastián Vivero
The Cryosphere, 16, 647–665, https://doi.org/10.5194/tc-16-647-2022, https://doi.org/10.5194/tc-16-647-2022, 2022
Short summary
Short summary
This work uses satellite and aerial data to study glaciers and rock glacier changes in La Laguna catchment within the semi-arid Andes of Chile, where ice melt is an important factor in river flow. The results show the rate of ice loss of Tapado Glacier has been increasing since the 1950s, which possibly relates to a dryer, warmer climate over the previous decades. Several rock glaciers show high surface velocities and elevation changes between 2012 and 2020, indicating they may be ice-rich.
Christian Sommer, Thorsten Seehaus, Andrey Glazovsky, and Matthias H. Braun
The Cryosphere, 16, 35–42, https://doi.org/10.5194/tc-16-35-2022, https://doi.org/10.5194/tc-16-35-2022, 2022
Short summary
Short summary
Arctic glaciers have been subject to extensive warming due to global climate change, yet their contribution to sea level rise has been relatively small in the past. In this study we provide mass changes of most glaciers of the Russian High Arctic (Franz Josef Land, Severnaya Zemlya, Novaya Zemlya). We use TanDEM-X satellite measurements to derive glacier surface elevation changes. Our results show an increase in glacier mass loss and a sea level rise contribution of 0.06 mm/a (2010–2017).
Jan Bouke Pronk, Tobias Bolch, Owen King, Bert Wouters, and Douglas I. Benn
The Cryosphere, 15, 5577–5599, https://doi.org/10.5194/tc-15-5577-2021, https://doi.org/10.5194/tc-15-5577-2021, 2021
Short summary
Short summary
About 10 % of Himalayan glaciers flow directly into lakes. This study finds, using satellite imagery, that such glaciers show higher flow velocities than glaciers without ice–lake contact. In particular near the glacier tongue the impact of a lake on the glacier flow can be dramatic. The development of current and new meltwater bodies will influence the flow of an increasing number of Himalayan glaciers in the future, a scenario not currently considered in regional ice loss projections.
Armin Dachauer, Richard Hann, and Andrew J. Hodson
The Cryosphere, 15, 5513–5528, https://doi.org/10.5194/tc-15-5513-2021, https://doi.org/10.5194/tc-15-5513-2021, 2021
Short summary
Short summary
This study investigated the aerodynamic roughness length (z0) – an important parameter to determine the surface roughness – of crevassed tidewater glaciers on Svalbard using drone data. The results point out that the range of z0 values across a crevassed glacier is large but in general significantly higher compared to non-crevassed glacier surfaces. The UAV approach proved to be an ideal tool to provide distributed z0 estimates of crevassed glaciers which can be used to model turbulent fluxes.
Melanie Marochov, Chris R. Stokes, and Patrice E. Carbonneau
The Cryosphere, 15, 5041–5059, https://doi.org/10.5194/tc-15-5041-2021, https://doi.org/10.5194/tc-15-5041-2021, 2021
Short summary
Short summary
Research into the use of deep learning for pixel-level classification of landscapes containing marine-terminating glaciers is lacking. We adapt a novel and transferable deep learning workflow to classify satellite imagery containing marine-terminating outlet glaciers in Greenland. Our workflow achieves high accuracy and mimics human visual performance, potentially providing a useful tool to monitor glacier change and further understand the impacts of climate change in complex glacial settings.
Paul Willem Leclercq, Andreas Kääb, and Bas Altena
The Cryosphere, 15, 4901–4907, https://doi.org/10.5194/tc-15-4901-2021, https://doi.org/10.5194/tc-15-4901-2021, 2021
Short summary
Short summary
In this study we present a novel method to detect glacier surge activity. Surges are relevant as they disturb the link between glacier change and climate, and studying surges can also increase understanding of glacier flow. We use variations in Sentinel-1 radar backscatter strength, calculated with the use of Google Earth Engine, to detect surge activity. In our case study for the year 2018–2019 we find 69 cases of surging glaciers globally. Many of these were not previously known to be surging.
George Brencher, Alexander L. Handwerger, and Jeffrey S. Munroe
The Cryosphere, 15, 4823–4844, https://doi.org/10.5194/tc-15-4823-2021, https://doi.org/10.5194/tc-15-4823-2021, 2021
Short summary
Short summary
We use satellite InSAR to inventory and monitor rock glaciers, frozen bodies of ice and rock debris that are an important water resource in the Uinta Mountains, Utah, USA. Our inventory contains 205 rock glaciers, which occur within a narrow elevation band and deform at 1.94 cm yr-1 on average. Uinta rock glacier movement changes seasonally and appears to be driven by spring snowmelt. The role of rock glaciers as a perennial water resource is threatened by ice loss due to climate change.
Adina E. Racoviteanu, Lindsey Nicholson, and Neil F. Glasser
The Cryosphere, 15, 4557–4588, https://doi.org/10.5194/tc-15-4557-2021, https://doi.org/10.5194/tc-15-4557-2021, 2021
Short summary
Short summary
Supraglacial debris cover comprises ponds, exposed ice cliffs, debris material and vegetation. Understanding these features is important for glacier hydrology and related hazards. We use linear spectral unmixing of satellite data to assess the composition of map supraglacial debris across the Himalaya range in 2015. One of the highlights of this study is the automated mapping of supraglacial ponds, which complements and expands the existing supraglacial debris and lake databases.
Corey Scher, Nicholas C. Steiner, and Kyle C. McDonald
The Cryosphere, 15, 4465–4482, https://doi.org/10.5194/tc-15-4465-2021, https://doi.org/10.5194/tc-15-4465-2021, 2021
Short summary
Short summary
Time series synthetic aperture radar enables detection of seasonal reach-scale glacier surface melting across continents, a key component of surface energy balance for mountain glaciers. We observe melting across all areas of the Hindu Kush Himalaya (HKH) cryosphere. Surface melting for the HKH lasts for close to 5 months per year on average and for just below 2 months at elevations exceeding 7000 m a.s.l. Further, there are indications that melting is more than superficial at high elevations.
Lander Van Tricht, Philippe Huybrechts, Jonas Van Breedam, Alexander Vanhulle, Kristof Van Oost, and Harry Zekollari
The Cryosphere, 15, 4445–4464, https://doi.org/10.5194/tc-15-4445-2021, https://doi.org/10.5194/tc-15-4445-2021, 2021
Short summary
Short summary
We conducted innovative research on the use of drones to determine the surface mass balance (SMB) of two glaciers. Considering appropriate spatial scales, we succeeded in determining the SMB in the ablation area with large accuracy. Consequently, we are convinced that our method and the use of drones to monitor the mass balance of a glacier’s ablation area can be an add-on to stake measurements in order to obtain a broader picture of the heterogeneity of the SMB of glaciers.
Yuting Dong, Ji Zhao, Dana Floricioiu, Lukas Krieger, Thomas Fritz, and Michael Eineder
The Cryosphere, 15, 4421–4443, https://doi.org/10.5194/tc-15-4421-2021, https://doi.org/10.5194/tc-15-4421-2021, 2021
Short summary
Short summary
We generated a consistent, gapless and high-resolution (12 m) topography product of the Antarctic Peninsula by combining the complementary advantages of the two most recent high-resolution digital elevation model (DEM) products: the TanDEM-X DEM and the Reference Elevation Model of Antarctica. The generated DEM maintains the characteristics of the TanDEM-X DEM, has a better quality due to the correction of the residual height errors in the non-edited TanDEM-X DEM and will be freely available.
Sergey Samsonov, Kristy Tiampo, and Ryan Cassotto
The Cryosphere, 15, 4221–4239, https://doi.org/10.5194/tc-15-4221-2021, https://doi.org/10.5194/tc-15-4221-2021, 2021
Short summary
Short summary
The direction and intensity of glacier surface flow adjust in response to a warming climate, causing sea level rise, seasonal flooding and droughts, and changing landscapes and habitats. We developed a technique that measures the evolution of surface flow for a glaciated region in three dimensions with high temporal and spatial resolution and used it to map the temporal evolution of glaciers in southeastern Alaska (Agassiz, Seward, Malaspina, Klutlan, Walsh, and Kluane) during 2016–2021.
Anne Braakmann-Folgmann, Andrew Shepherd, and Andy Ridout
The Cryosphere, 15, 3861–3876, https://doi.org/10.5194/tc-15-3861-2021, https://doi.org/10.5194/tc-15-3861-2021, 2021
Short summary
Short summary
We investigate the disintegration of the B30 iceberg using satellite remote sensing and find that the iceberg lost 378 km3 of ice in 6.5 years, corresponding to 80 % of its initial volume. About two thirds are due to fragmentation at the sides, and one third is due to melting at the iceberg’s base. The release of fresh water and nutrients impacts ocean circulation, sea ice formation, and biological production. We show that adding a snow layer is important when deriving iceberg thickness.
Joschka Geissler, Christoph Mayer, Juilson Jubanski, Ulrich Münzer, and Florian Siegert
The Cryosphere, 15, 3699–3717, https://doi.org/10.5194/tc-15-3699-2021, https://doi.org/10.5194/tc-15-3699-2021, 2021
Short summary
Short summary
The study demonstrates the potential of photogrammetry for analyzing glacier retreat with high spatial resolution. Twenty-three glaciers within the Ötztal Alps are analyzed. We compare photogrammetric and glaciologic mass balances of the Vernagtferner by using the ELA for our density assumption and an UAV survey for a temporal correction of the geodetic mass balances. The results reveal regions of anomalous mass balance and allow estimates of the imbalance between mass balances and ice dynamics.
Lukas Müller, Martin Horwath, Mirko Scheinert, Christoph Mayer, Benjamin Ebermann, Dana Floricioiu, Lukas Krieger, Ralf Rosenau, and Saurabh Vijay
The Cryosphere, 15, 3355–3375, https://doi.org/10.5194/tc-15-3355-2021, https://doi.org/10.5194/tc-15-3355-2021, 2021
Short summary
Short summary
Harald Moltke Bræ, a marine-terminating glacier in north-western Greenland, undergoes remarkable surges of episodic character. Our data show that a recent surge from 2013 to 2019 was initiated at the glacier front and exhibits a pronounced seasonality with flow velocities varying by 1 order of magnitude, which has not been observed at Harald Moltke Bræ in this way before. These findings are crucial for understanding surge mechanisms at Harald Moltke Bræ and other marine-terminating glaciers.
Joseph A. MacGregor, Michael Studinger, Emily Arnold, Carlton J. Leuschen, Fernando Rodríguez-Morales, and John D. Paden
The Cryosphere, 15, 2569–2574, https://doi.org/10.5194/tc-15-2569-2021, https://doi.org/10.5194/tc-15-2569-2021, 2021
Short summary
Short summary
We combine multiple recent global glacier datasets and extend one of them (GlaThiDa) to evaluate past performance of radar-sounding surveys of the thickness of Earth's temperate glaciers. An empirical envelope for radar performance as a function of center frequency is determined, its limitations are discussed and its relevance to future radar-sounder survey and system designs is considered.
Maximillian Van Wyk de Vries and Andrew D. Wickert
The Cryosphere, 15, 2115–2132, https://doi.org/10.5194/tc-15-2115-2021, https://doi.org/10.5194/tc-15-2115-2021, 2021
Short summary
Short summary
We can measure glacier flow and sliding velocity by tracking patterns on the ice surface in satellite images. The surface velocity of glaciers provides important information to support assessments of glacier response to climate change, to improve regional assessments of ice thickness, and to assist with glacier fieldwork. Our paper describes Glacier Image Velocimetry (GIV), a new, easy-to-use, and open-source toolbox for calculating high-resolution velocity time series for any glacier on earth.
Daniel Cheng, Wayne Hayes, Eric Larour, Yara Mohajerani, Michael Wood, Isabella Velicogna, and Eric Rignot
The Cryosphere, 15, 1663–1675, https://doi.org/10.5194/tc-15-1663-2021, https://doi.org/10.5194/tc-15-1663-2021, 2021
Short summary
Short summary
Tracking changes in Greenland's glaciers is important for understanding Earth's climate, but it is time consuming to do so by hand. We train a program, called CALFIN, to automatically track these changes with human levels of accuracy. CALFIN is a special type of program called a neural network. This method can be applied to other glaciers and eventually other tracking tasks. This will enhance our understanding of the Greenland Ice Sheet and permit better models of Earth's climate.
Andri Gunnarsson, Sigurdur M. Gardarsson, Finnur Pálsson, Tómas Jóhannesson, and Óli G. B. Sveinsson
The Cryosphere, 15, 547–570, https://doi.org/10.5194/tc-15-547-2021, https://doi.org/10.5194/tc-15-547-2021, 2021
Short summary
Short summary
Surface albedo quantifies the fraction of the sunlight reflected by the surface of the Earth. During the melt season in the Northern Hemisphere solar energy absorbed by snow- and ice-covered surfaces is mainly controlled by surface albedo. For Icelandic glaciers, air temperature and surface albedo are the dominating factors governing annual variability of glacier surface melt. Satellite data from the MODIS sensor are used to create a data set spanning the glacier melt season.
Bryan Riel, Brent Minchew, and Ian Joughin
The Cryosphere, 15, 407–429, https://doi.org/10.5194/tc-15-407-2021, https://doi.org/10.5194/tc-15-407-2021, 2021
Short summary
Short summary
The availability of large volumes of publicly available remote sensing data over terrestrial glaciers provides new opportunities for studying the response of glaciers to a changing climate. We present an efficient method for tracking changes in glacier speeds at high spatial and temporal resolutions from surface observations, demonstrating the recovery of traveling waves over Jakobshavn Isbræ, Greenland. Quantification of wave properties may ultimately enhance understanding of glacier dynamics.
Chad A. Greene, Alex S. Gardner, and Lauren C. Andrews
The Cryosphere, 14, 4365–4378, https://doi.org/10.5194/tc-14-4365-2020, https://doi.org/10.5194/tc-14-4365-2020, 2020
Short summary
Short summary
Seasonal variability is a fundamental characteristic of any Earth surface system, but we do not fully understand which of the world's glaciers speed up and slow down on an annual cycle. Such short-timescale accelerations may offer clues about how individual glaciers will respond to longer-term changes in climate, but understanding any behavior requires an ability to observe it. We describe how to use satellite image feature tracking to determine the magnitude and timing of seasonal ice dynamics.
Ellyn M. Enderlin and Timothy C. Bartholomaus
The Cryosphere, 14, 4121–4133, https://doi.org/10.5194/tc-14-4121-2020, https://doi.org/10.5194/tc-14-4121-2020, 2020
Short summary
Short summary
Accurate predictions of future changes in glacier flow require the realistic simulation of glacier terminus position change in numerical models. We use crevasse observations for 19 Greenland glaciers to explore whether the two commonly used crevasse depth models match observations. The models cannot reproduce spatial patterns, and we largely attribute discrepancies between modeled and observed depths to the models' inability to account for advection.
Angus J. Dowson, Pascal Sirguey, and Nicolas J. Cullen
The Cryosphere, 14, 3425–3448, https://doi.org/10.5194/tc-14-3425-2020, https://doi.org/10.5194/tc-14-3425-2020, 2020
Short summary
Short summary
Satellite observations over 19 years are used to characterise the spatial and temporal variability of surface albedo across the gardens of Eden and Allah, two of New Zealand’s largest ice fields. The variability in response of individual glaciers reveals the role of topographic setting and suggests that glaciers in the Southern Alps do not behave as a single climatic unit. There is evidence that the timing of the minimum surface albedo has shifted to later in the summer on 10 of the 12 glaciers.
Anna Bergstrom, Michael N. Gooseff, Madeline Myers, Peter T. Doran, and Julian M. Cross
The Cryosphere, 14, 769–788, https://doi.org/10.5194/tc-14-769-2020, https://doi.org/10.5194/tc-14-769-2020, 2020
Short summary
Short summary
This study sought to understand patterns of reflectance of visible light across the landscape of the McMurdo Dry Valleys, Antarctica. We used a helicopter-based platform to measure reflectance along an entire valley with a particular focus on the glaciers, as reflectance strongly controls glacier melt and available water to the downstream ecosystem. We found that patterns are controlled by gradients in snowfall, wind redistribution, and landscape structure, which can trap snow and sediment.
Désirée Treichler, Andreas Kääb, Nadine Salzmann, and Chong-Yu Xu
The Cryosphere, 13, 2977–3005, https://doi.org/10.5194/tc-13-2977-2019, https://doi.org/10.5194/tc-13-2977-2019, 2019
Short summary
Short summary
Glacier growth such as that found on the Tibetan Plateau (TP) is counterintuitive in a warming world. Climate models and meteorological data are conflicting about the reasons for this glacier anomaly. We quantify the glacier changes in High Mountain Asia using satellite laser altimetry as well as the growth of over 1300 inland lakes on the TP. Our study suggests that increased summer precipitation is likely the largest contributor to the recently observed increases in glacier and lake masses.
Christoph Rohner, David Small, Jan Beutel, Daniel Henke, Martin P. Lüthi, and Andreas Vieli
The Cryosphere, 13, 2953–2975, https://doi.org/10.5194/tc-13-2953-2019, https://doi.org/10.5194/tc-13-2953-2019, 2019
Short summary
Short summary
The recent increase in ice flow and calving rates of ocean–terminating glaciers contributes substantially to the mass loss of the Greenland Ice Sheet. Using in situ reference observations, we validate the satellite–based method of iterative offset tracking of Sentinel–1A data for deriving flow speeds. Our investigations highlight the importance of spatial resolution near the fast–flowing calving front, resulting in significantly higher ice velocities compared to large–scale operational products.
Jozef Šupinský, Ján Kaňuk, Zdenko Hochmuth, and Michal Gallay
The Cryosphere, 13, 2835–2851, https://doi.org/10.5194/tc-13-2835-2019, https://doi.org/10.5194/tc-13-2835-2019, 2019
Short summary
Short summary
Cave ice formations can be considered an indicator of long-term changes in the landscape. Using terrestrial laser scanning we generated a time series database of a 3-D cave model. We present a novel approach toward registration of scan missions into a unified coordinate system and methodology for detection of cave floor ice changes. We demonstrate the results of the ice dynamics monitoring correlated with meteorological observations in the Silická ľadnica cave situated in the Slovak Karst.
Thorsten Seehaus, Philipp Malz, Christian Sommer, Stefan Lippl, Alejo Cochachin, and Matthias Braun
The Cryosphere, 13, 2537–2556, https://doi.org/10.5194/tc-13-2537-2019, https://doi.org/10.5194/tc-13-2537-2019, 2019
Short summary
Short summary
The glaciers in Peru are strongly affected by climate change and have shown significant ice loss in the last century. We present the first multi-temporal, countrywide quantification of glacier area and ice mass changes. A glacier area loss of −548.5 ± 65.7 km2 (−29 %) and ice mass loss of −7.62 ± 1.05 Gt is obtained for the period 2000–2016. The ice loss rate increased towards the end of the observation period. The glacier changes revealed can be attributed to regional climatic changes and ENSO.
Dyre O. Dammann, Leif E. B. Eriksson, Son V. Nghiem, Erin C. Pettit, Nathan T. Kurtz, John G. Sonntag, Thomas E. Busche, Franz J. Meyer, and Andrew R. Mahoney
The Cryosphere, 13, 1861–1875, https://doi.org/10.5194/tc-13-1861-2019, https://doi.org/10.5194/tc-13-1861-2019, 2019
Short summary
Short summary
We validate TanDEM-X interferometry as a tool for deriving iceberg subaerial morphology using Operation IceBridge data. This approach enables a volumetric classification of icebergs, according to volume relevant to iceberg drift and decay, freshwater contribution, and potential impact on structures. We find iceberg volumes to generally match within 7 %. These results suggest that TanDEM-X could pave the way for future interferometric systems of scientific and operational iceberg classification.
Enze Zhang, Lin Liu, and Lingcao Huang
The Cryosphere, 13, 1729–1741, https://doi.org/10.5194/tc-13-1729-2019, https://doi.org/10.5194/tc-13-1729-2019, 2019
Short summary
Short summary
Conventionally, calving front positions have been manually delineated from remote sensing images. We design a novel method to automatically delineate the calving front positions of Jakobshavn Isbræ based on deep learning, the first of this kind for Greenland outlet glaciers. We generate high-temporal-resolution (about two measurements every month) calving fronts, demonstrating our methodology can be applied to many other tidewater glaciers through this successful case study on Jakobshavn Isbræ.
Robert McNabb, Christopher Nuth, Andreas Kääb, and Luc Girod
The Cryosphere, 13, 895–910, https://doi.org/10.5194/tc-13-895-2019, https://doi.org/10.5194/tc-13-895-2019, 2019
Short summary
Short summary
Estimating glacier changes involves measuring elevation changes, often using elevation models derived from satellites. Many elevation models have data gaps (voids), which affect estimates of glacier change. We compare 11 methods for interpolating voids, finding that some methods bias estimates of glacier change by up to 20 %, though most methods have a smaller effect. Some methods produce reliable results even with large void areas, suggesting that noisy elevation data are still useful.
Bas Altena, Ted Scambos, Mark Fahnestock, and Andreas Kääb
The Cryosphere, 13, 795–814, https://doi.org/10.5194/tc-13-795-2019, https://doi.org/10.5194/tc-13-795-2019, 2019
Short summary
Short summary
Many glaciers in southern Alaska and the Yukon experience changes in flow speed, which occur in episodes or sporadically. These flow changes can be measured with satellites, but the resulting raw velocity products are messy. Thus in this study we developed an automatic method to produce a synthesized velocity product over a large glacier region of roughly 600 km by 200 km. Velocities are at a monthly resolution and at 300 m resolution, making all kinds of glacier dynamics observable.
Kathrin Naegeli, Matthias Huss, and Martin Hoelzle
The Cryosphere, 13, 397–412, https://doi.org/10.5194/tc-13-397-2019, https://doi.org/10.5194/tc-13-397-2019, 2019
Short summary
Short summary
The paper investigates the temporal changes of bare-ice glacier surface albedo in the Swiss Alps between 1999 and 2016 from a regional to local scale using satellite data. Significant negative trends were found in the lowermost elevations and margins of the ablation zones. Although significant changes of glacier ice albedo are only present over a limited area, we emphasize that albedo feedback will considerably enhance the rate of glacier mass loss in the Swiss Alps in the near future.
Mingyang Lv, Huadong Guo, Xiancai Lu, Guang Liu, Shiyong Yan, Zhixing Ruan, Yixing Ding, and Duncan J. Quincey
The Cryosphere, 13, 219–236, https://doi.org/10.5194/tc-13-219-2019, https://doi.org/10.5194/tc-13-219-2019, 2019
Short summary
Short summary
We highlight 28 glaciers in the Kingata Mountains, among which 17 have changed markedly over the last decade. We identify four advancing and 13 surge-type glaciers. The dynamic evolution of the surges is similar to that of Karakoram, suggesting that both hydrological and thermal controls are important for surge initiation and recession. Topography seems to be a dominant control on non-surge glacier behaviour. Most glaciers experienced a significant and diverse change in their motion patterns.
Cited articles
Azam, M. F., Wagnon, P., Berthier, E., Vincent, C., Fujita, K., and Kargel,
J. S.: Review of the status and mass changes of Himalayan-Karakoram
glaciers, J. Glaciol., 64, 61–74, https://doi.org/10.1017/jog.2017.86, 2018.
Badrinarayanan, V., Kendall, A., and Cipolla, R.: SegNet: A Deep
Convolutional Encoder-Decoder Architecture for Image Segmentation, IEEE T.
Pattern Anal., 39, 2481–2495, https://doi.org/10.1109/TPAMI.2016.2644615,
2017.
Baumhoer, C. A., Dietz, A. J., Kneisel, C., and Kuenzer, C.: Automated
Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery
Using Deep Learning, Remote Sens.-Basel, 11, 2529,
https://doi.org/10.3390/rs11212529, 2019.
Bishop, M. P., Olsenholler, J. A., Shroder, J. F., Barry, R. G., Raup, B.
H., Bush, A. B. G., Copland, L., Dwyer, J. L., Fountain, A. G., Haeberli,
W., Kääb, A., Paul, F., Hall, D. K., Kargel, J. S., Molnia, B. F.,
Trabant, D. C., and Wessels, R.: Global Land Ice Measurements from Space
(GLIMS): Remote Sensing and GIS Investigations of the Earth's Cryosphere,
Geocarto Int., 19, 57–84, https://doi.org/10.1080/10106040408542307, 2004.
Bolch, T., Kulkarni, A., Kaab, A., Huggel, C., Paul, F., Cogley, J. G.,
Frey, H., Kargel, J. S., Fujita, K., Scheel, M., Bajracharya, S., and
Stoffel, M.: The state and fate of Himalayan glaciers, Science, 336,
310–314, https://doi.org/10.1126/science.1215828, 2012.
Braithwaite, R. J. and Raper, S. C. B.: Estimating equilibrium-line altitude
(ELA) from glacier inventory data, Ann. Glaciol., 50, 127–132,
https://doi.org/10.3189/172756410790595930, 2009.
Chen, L. C., Zhu, Y. K., Papandreou, G., Schroff, F., and Adam, H.:
Encoder-Decoder with Atrous Separable Convolution for Semantic Image
Segmentation, Proceedings of the European Conference on Computer Vision,
Munich, Germany, 8–14 September 2018, 801–818,
https://doi.org/10.1007/978-3-030-01234-2_49, 2018.
Cheng, D., Hayes, W., Larour, E., Mohajerani, Y., Wood, M., Velicogna, I., and Rignot, E.: Calving Front Machine (CALFIN): glacial termini dataset and automated deep learning extraction method for Greenland, 1972–2019, The Cryosphere, 15, 1663–1675, https://doi.org/10.5194/tc-15-1663-2021, 2021.
China High-resolution Earth Observation System: Homepage, https://www.cheosgrid.org.cn/, last access: 16 May 2022.
Chollet, F.: Xception: Deep Learning with Depthwise Separable Convolutions,
Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition, Honolulu, Hawaii, 22–25 July 2017, 1251–1258,
https://doi.org/10.1109/CVPR.2017.195, 2017.
Chu, X.: yiyou101/Attention-DeepLab-V3plus: A deep learning approach to extract the glacier outlines (v2.1), Zenodo [code and software], https://doi.org/10.5281/zenodo.7132888, 2022.
Girshick, R.: Fast R-CNN, Proceedings of the IEEE International Conference
on Computer Vision, Santiago, Chile, 13–16 December 2015, 1440–1448,
https://doi.org/10.1109/ICCV.2015.169, 2015.
Grinsted, A.: An estimate of global glacier volume, The Cryosphere, 7, 141–151, https://doi.org/10.5194/tc-7-141-2013, 2013.
Guo, W. Q., Liu, S. Y., Xu, J. L., Wu, L. Z., Shangguan, D. H., Yao, X. J.,
Wei, J. F., Bao, W. J., Yu, P. C., Liu, Q., and Jiang, Z. L.: The second
Chinese glacier inventory: data, methods and results, J. Glaciol., 61,
357–372, https://doi.org/10.3189/2015JoG14J209, 2017.
He, K. M., Zhang, X. Y., Ren, S. Q., and Sun, J.: Deep residual learning for
image recognition, in: Proceedings of the IEEE Conference on Computer Vision and
Pattern Recognition, Las Vegas, USA, 27–30 June 2016, 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016.
He, Y., Yao, S., Yang, W., Yan, H. W., Zhang, L. F., Wen, Z. Q., Zhang, Y.
L., and Liu, T.: An Extraction Method for Glacial Lakes Based on Landsat-8
Imagery Using an Improved U-Net Network, IEEE J-STARS, 14, 6544–6558,
https://doi.org/10.1109/jstars.2021.3085397, 2021.
Heimann, T., van Ginneken, B., Styner, M. A., Arzhaeva, Y., Aurich, V.,
Bauer, C., Beck, A., Becker, C., Beichel, R., Bekes, G., Bello, F., Binnig,
G., Bischof, H., Bornik, A., Cashman, P. M., Chi, Y., Cordova, A., Dawant,
B. M., Fidrich, M., Furst, J. D., Furukawa, D., Grenacher, L., Hornegger,
J., Kainmuller, D., Kitney, R. I., Kobatake, H., Lamecker, H., Lange, T.,
Lee, J., Lennon, B., Li, R., Li, S., Meinzer, H. P., Nemeth, G., Raicu, D.
S., Rau, A. M., van Rikxoort, E. M., Rousson, M., Rusko, L., Saddi, K. A.,
Schmidt, G., Seghers, D., Shimizu, A., Slagmolen, P., Sorantin, E., Soza,
G., Susomboon, R., Waite, J. M., Wimmer, A., and Wolf, I.: Comparison and
evaluation of methods for liver segmentation from CT datasets, IEEE T. Med.
Imaging, 28, 1251–1265, https://doi.org/10.1109/TMI.2009.2013851, 2009.
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T.,
Andreetto, M., and Adam, H.: Mobilenets: Efficient convolutional neural
networks for mobile vision applications, arXiv [preprint], https://doi.org/10.48550/arXiv.1704.04861,
17 April 2017.
Huang, B., Zhao, B., and Song, Y. M.: Urban land-use mapping using a deep
convolutional neural network with high spatial resolution multispectral
remote sensing imagery, Remote Sens. Environ., 214, 73–86,
https://doi.org/10.1016/j.rse.2018.04.050, 2018.
Immerzeel, W. W., van Beek, L. P., and Bierkens, M. F.: Climate change will
affect the Asian water towers, Science, 328, 1382–1385,
https://doi.org/10.1126/science.1183188, 2010.
Ji, Q., Dong, J., Liu, R., Xiao, Z. L., and Yang, T. B.: Glacier Changes in
Response to Climate Change in the Himalayas in 1990–2015, Scientia
Geographica Sinica, 40, 486–496,
https://doi.org/10.13249/j.cnki.sgs.2020.03.017, 2020.
King, M. A., Bingham, R. J., Moore, P., Whitehouse, P. L., Bentley, M. J.,
and Milne, G. A.: Lower satellite-gravimetry estimates of Antarctic
sea-level contribution, Nature, 491, 586–589,
https://doi.org/10.1038/nature11621, 2012.
Li, X., Cheng, G. D., Jin, H. J., Kang, E., Che, T., Jin, R., Wu, L. Z.,
Nan, Z. T., Wang, J., and Shen, Y. P.: Cryospheric change in China, Global
Planet. Change, 62, 210–218,
https://doi.org/10.1016/j.gloplacha.2008.02.001, 2008.
Liu, J., Yao, X. J., Liu, S. Y., Guo, W. Q., and Xu, J. L.: Glacial changes
in the Gangdisê Mountains from 1970 to 2016, J. Geogr. Sci., 30,
131–144, https://doi.org/10.1007/s11442-020-1719-6, 2020.
Long, J., Shelhamer, E., and Darrell, T.: Fully Convolutional Networks for
Semantic Segmentation, Proceedings of the IEEE Conference on Computer Vision
and Pattern Recognition, Boston, US, 8–10 June 2015, 3431–3440,
https://doi.org/10.1109/CVPR.2015.7298965, 2015.
Marochov, M., Stokes, C. R., and Carbonneau, P. E.: Image classification of marine-terminating outlet glaciers in Greenland using deep learning methods, The Cryosphere, 15, 5041–5059, https://doi.org/10.5194/tc-15-5041-2021, 2021.
Milletari, F., Navab, N., and Ahmadi, S.: V-Net: Fully Convolutional Neural
Networks for Volumetric Medical Image Segmentation, in: 2016 Fourth
International Conference on 3D Vision, Stanford, US, 25–28 October 2016,
565–571, https://doi.org/10.1109/3DV.2016.79, 2016.
Nie, Y., Zhang, Y. L., Liu, L. S., and Zhang, J. P.: Monitoring Glacier
Change Based on Remote Sensing in the Mt. Qomolangma National Nature
Preserve, 1976–2006, Acta Geographica Sinica, 65, 13–28,
https://doi.org/10.11821/xb201001003, 2010.
Nuimura, T., Sakai, A., Taniguchi, K., Nagai, H., Lamsal, D., Tsutaki, S., Kozawa, A., Hoshina, Y., Takenaka, S., Omiya, S., Tsunematsu, K., Tshering, P., and Fujita, K.: The GAMDAM glacier inventory: a quality-controlled inventory of Asian glaciers, The Cryosphere, 9, 849–864, https://doi.org/10.5194/tc-9-849-2015, 2015.
Oerlemans, J.: Quantifying global warming from the retreat of glaciers,
Science, 264, 243–245, https://doi.org/10.1126/science.264.5156.243, 1994.
Olofsson, P., Foody, G. M., Herold, M., Stehman, S. V., Woodcock, C. E., and
Wulder, M. A.: Good practices for estimating area and assessing accuracy of
land change, Remote Sens. Environ., 148, 42–57,
https://doi.org/10.1016/j.rse.2014.02.015, 2014.
Pfeffer, W. T., Harper, J. T., and O'Neel, S.: Kinematic Constraints on
Glacier Contributions to 21st-Century Sea-Level Rise, Science, 321,
1340–1343, https://doi.org/10.1126/science.1159099, 2008.
Racoviteanu, A. E., Arnaud, Y., Williams, M. W., and Manley, W. F.: Spatial patterns in glacier characteristics and area changes from 1962 to 2006 in the Kanchenjunga–Sikkim area, eastern Himalaya, The Cryosphere, 9, 505–523, https://doi.org/10.5194/tc-9-505-2015, 2015.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A.: You Only Look Once:
Unified, Real-Time Object Detection, Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition, Las Vegas, US, 26 June–1 July 2016, 779–788, https://doi.org/10.1109/CVPR.2016.91, 2016.
Robson, B. A., Nuth, C., Dahl, S. O., Hölbling, D., Strozzi, T., and
Nielsen, P. R.: Automated classification of debris-covered glaciers
combining optical, SAR and topographic data in an object-based environment,
Remote Sens. Environ., 170, 372–387,
https://doi.org/10.1016/j.rse.2015.10.001, 2015.
Robson, B. A., Bolch, T., MacDonell, S., Hölbling, D., Rastner, P., and
Schaffer, N.: Automated detection of rock glaciers using deep learning and
object-based image analysis, Remote Sens. Environ., 250, 112033,
https://doi.org/10.1016/j.rse.2020.112033, 2020.
Ronneberger, O., Fischer, P., and Brox, T.: U-Net: Convolutional Networks
for Biomedical Image Segmentation, arXiv [preprint], https://doi.org/10.48550/arXiv.1505.04597, 18
May 2015.
Schrama, E. J. O., Wouters, B., and Rietbroek, R.: A mascon approach to
assess ice sheet and glacier mass balances and their uncertainties from
GRACE data, J. Geophys. Res.-Sol. Ea., 119, 60480–6066,
https://doi.org/10.1002/2013jb010923, 2014.
Sun, M. P., Liu, S. Y., Yao, X. J., Guo, W. Q., and Xu, J. L.: Glacier
changes in the Qilian Mountains in the past half-century: Based on the
revised First and Second Chinese Glacier Inventory, J. Geogr. Sci., 28,
206–220, https://doi.org/10.1007/s11442-018-1468-y, 2018.
Telgarsky, M.: Benefits of depth in neural networks, in: Proceedings of
Machine Learning Research, 29th Annual Conference on Learning Theory, New
York, US, 23–26 June 2016, 1517–1539, http://proceedings.mlr.press/v49/telgarsky16.html (last access: 4 October 2022), 2016.
Tong, X. Y., Xia, G. S., Lu, Q. K., Shen, H. F., Li, S. Y., You, S. C., and
Zhang, L. P.: Land-cover classification with high-resolution remote sensing
images using transferable deep models, Remote Sens. Environ., 237, 111322,
https://doi.org/10.1016/j.rse.2019.111322, 2020.
Wang, Y. L., Du, W. B., and Wang, S. T.: Extracting glacier information from
remote sensing imageries by automatic threshold method of Gaussian mixture
model, National Remote Sensing Bulletin, 25, 1434–1444,
https://doi.org/10.11834/jrs.20219153, 2021.
Wang, Z. Q., Zhou, Y., Wang, F. T., Wang, S. X., and Xu, Z. Y.: SDGH-Net:
Ship Detection in Optical Remote Sensing Images Based on Gaussian Heatmap
Regression, Remote Sens.-Basel, 13, 499, https://doi.org/10.3390/rs13030499,
2021.
Woo, S., Park, J., Lee, J.-Y., and Kweon, I. S.: CBAM: Convolutional Block
Attention Module, in: Proceedings of the European Conference on Computer Vision,
Munich, Germany, 8–14 September 2018, 3–19,
https://doi.org/10.1007/978-3-030-01234-2_1, 2018.
Xie, Z. Y., Haritashya, U. K., Asari, V. K., Young, B. W., Bishop, M. P.,
and Kargel, J. S.: GlacierNet: A Deep-Learning Approach for Debris-Covered
Glacier Mapping, IEEE Access, 8, 83495–83510,
https://doi.org/10.1109/access.2020.2991187, 2020.
Yan, L. L. and Wang, J.: Study of Extracting Glacier lnformation from Remote
Sensing, Journal of Glaciology and Geocryology, 35, 110–118,
10.7522/j.issn.1000-0240.2013.0013, 2013.
Yao, T. D., Thompson, L., Yang, W., Yu, W. S., Gao, Y., Guo, X. J., Yang, X.
X., Duan, K. Q., Zhao, H. B., Xu, B. Q., Pu, J. C., Lu, A. X., Xiang, Y.,
Kattel, D. B., and Joswiak, D.: Different glacier status with atmospheric
circulations in Tibetan Plateau and surroundings, Nat. Clim. Change, 2,
663–667, https://doi.org/10.1038/nclimate1580, 2012.
Ye, Q. H.: Glacier coverage data on the Tibetan Plateau in 2017 (TPG2017,
Version1.0), National Tibetan Plateau Data Center [data set],
https://doi.org/10.11888/Glacio.tpdc.270924, 2019.
Ye, Q. H., Zong, J. B., Tian, L. D., Cogley, J. G., Song, C. Q., and Guo, W.
Q.: Glacier changes on the Tibetan Plateau derived from Landsat imagery:
mid-1970s – 2000–13, J. Glaciol., 63, 273–287,
https://doi.org/10.1017/jog.2016.137, 2017.
Yu, F. and Koltun, V.: Multi-scale context aggregation by dilated
convolutions, arXiv [preprint], https://doi.org/10.48550/arXiv.1511.07122, 23 November 2015.
Zhang, E., Liu, L., and Huang, L.: Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach, The Cryosphere, 13, 1729–1741, https://doi.org/10.5194/tc-13-1729-2019, 2019.
Zhang, E., Liu, L., Huang, L., and Ng, K. S.: An automated, generalized,
deep-learning-based method for delineating the calving fronts of Greenland
glaciers from multi-sensor remote sensing imagery, Remote Sens. Environ.,
254, 112265, https://doi.org/10.1016/j.rse.2020.112265, 2021.
Zhao, X. R., Wang, X., Wei, J. F., Jiang, Z. L., Zhang, Y., and Liu, S. Y.:
Spatiotemporal variability of glacier changes and their controlling factors
in the Kanchenjunga region, Himalaya based on multi-source remote sensing
data from 1975 to 2015, Sci. Total Environ., 745, 140995,
https://doi.org/10.1016/j.scitotenv.2020.140995, 2020.
Short summary
The available remote-sensing data are increasingly abundant, and the efficient and rapid acquisition of glacier boundaries based on these data is currently a frontier issue in glacier research. In this study, we designed a complete solution to automatically extract glacier outlines from the high-resolution images. Compared with other methods, our method achieves the best performance for glacier boundary extraction in parts of the Tanggula Mountains, Kunlun Mountains and Qilian Mountains.
The available remote-sensing data are increasingly abundant, and the efficient and rapid...
