Continuous monitoring of glacier calving fronts is essential for sea level rise projections. This study benchmarks Deep Learning systems for front delineation in Synthetic Aperture Radar imagery. While Deep Learning systems exhibit errors up to 221 m, human annotators deviate by only 38 m, underscoring the need for further research.

Calving front positions of marine-terminating glaciers are an essential parameter for understanding dynamic glacier changes and constraining ice modelling. In particular, for the Antarctic Peninsula, where the current ice mass loss is driven by dynamic glacier changes, accurate and comprehensive data products are of major importance. Current calving front data products are limited in coverage and temporal resolution because they rely on manual delineation, which is time-consuming and unfeasible for the increasing amount of satellite data. To simplify the mapping of calving fronts, we apply a deep-learning-based processing system designed to automatically delineate glacier fronts from multi-spectral Landsat imagery. The U-Net-based framework was initially trained on 869 Greenland glacier front positions. For this study, we extended the training data by 252 front positions of the Antarctic Peninsula. The data product presented here includes 4817 calving front locations of 42 key outlet glaciers from 2013 to 2023 and achieves a sub-seasonal temporal resolution. The mean difference between automated and manual extraction is estimated at 59.3±5.9 m. This dataset will help to better understand marine-terminating glacier dynamics on an intra-annual scale, study ice–ocean interactions in more detail and constrain glacier models. The data are publicly available at PANGAEA at https://doi.org/10.1594/PANGAEA.963725 (Loebel et al., 2024a).

The Greenland Ice Sheet has steadily lost mass over the past decades, presently representing the second-largest single contributor to global sea-level rise. In line with the rest of the Greenland Ice Sheet, the glaciers draining the northeast Greenland ice stream have been observed to retreat and thin. Here, we present a comprehensive study of processes affecting and being affected by the mass balance of marine-terminating and peripheral glaciers in northeast (NE) Greenland. Our focus is on the 79N Glacier (79NG), which hosts Greenland’s largest floating ice tongue. We provide new insight into the ice surface melt, the ice mass balance, glacier dynamics, the regional solid Earth response, the ocean-driven basal melt and the consequences of meltwater discharge into the ocean. Our study is based on field observations, remote sensing and simulations with numerical models of different complexity, most of them originating from the Greenland Ice Sheet–Ocean Interaction (GROCE) experiment. We find the overall negative climatic mass balance of 79NG to co-vary with summertime volumes of supraglacial lakes and show that the spatial pattern of the overall negative ice mass balance for NE Greenland is mirrored by the pattern of glacial-isostatic adjustment. We find near-coastal mass losses of both marine-terminating and peripheral glaciers in NE Greenland to be of a similar magnitude in the last decade. In contrast to the neighboring Zachariæ Isstrøm, 79NG – despite experiencing massive thinning of the floating tongue – has resisted an acceleration of ice discharge across the grounding line due to buttressing imposed by lateral friction of the 70 km long ice tongue in the narrow glacial fjord. Observations and models employed in this study are consistent in terms of melt rates occurring below the floating ice tongue. Our results suggest that the multidecadal warming of Atlantic Intermediate Water flowing into the cavity below the ice tongue – supplied by the recirculating branch of the West Spitsbergen Current in Fram Strait – is the main driver of the recent major increase in basal melt rates. We find that the meltwater leaving the cavity toward the ocean at subsurface levels quickly dilutes on the wide shelf. The study concludes by summarizing important estimates of changes to the state of the atmosphere, ice, land and ocean domains.

The mass balance of the Greenland Ice Sheet is strongly influenced by the dynamics of its outlet glaciers. Therefore, it is of paramount importance to accurately and continuously monitor these glaciers, especially the variation in their frontal positions. A temporally comprehensive parameterization of glacier calving is essential for understanding dynamic changes and constraining ice sheet modeling. However, many current calving front records are limited in terms of temporal resolution as they rely on manual delineation, which is laborious and not appropriate considering the increasing amount of satellite imagery available. In this contribution, we address this problem by applying an automated method to extract calving fronts from optical satellite imagery. The core of this workflow builds on recent advances in the field of deep learning while taking full advantage of multispectral input information. The performance of the method is evaluated using three independent test datasets. For the three datasets, we calculate mean delineation errors of 61.2, 73.7, and 73.5 m, respectively. Eventually, we apply the technique to Landsat-8 imagery. We generate 9243 calving front positions across 23 outlet glaciers in Greenland for the period 2013–2021. Resulting time series not only resolve long-term and seasonal signals but also resolve subseasonal patterns. We discuss the implications for glaciological studies and present a first application for analyzing the effect of bedrock topography on calving front variations. Our method and derived results represent an important step towards the development of intelligent processing strategies for glacier monitoring, opening up new possibilities for studying and modeling the dynamics of Greenland's outlet glaciers.

The Greenland and Antarctic ice sheets are important indicators of climate change and major contributors to sea level rise. Hence, precise, long-term observations of ice mass change are required to assess their contribution to sea level rise. Such observations can be achieved through three different methods. They can be achieved directly by measuring regional changes in the Earth's gravity field using the Gravity Recovery and Climate Experiment Follow-On (GRACE-FO) satellite system. Alternatively, they can be achieved indirectly by measuring changes in ice thickness using satellite altimetry or by estimating changes in the mass budget using a combination of regional climate model data and ice discharge across the grounding line, based on multi-sensor satellite radar observations of ice velocity (Hanna et al., 2013). Satellite radar altimetry has been used to measure elevation change since 1992 through a combination of various missions. In addition to the surface slope and complex topography, it has been shown that one of the most challenging issues concerns spatial and temporal variability in radar pulse penetration into the snowpack. This results in an inaccurate measurement of the true surface elevation and consequently affects surface elevation change (SEC) estimates. To increase the accuracy of surface elevation measurements retrieved by retracking the radar return waveform and thus reduce the uncertainty in the SEC, we developed a deep convolutional-neural-network architecture (AWI-ICENet1). AWI-ICENet1 is trained using a simulated reference data set with 3.8 million waveforms, taking into account different surface slopes, topography, and attenuation. The successfully trained network is finally applied as an AWI-ICENet1 retracker to the full time series of CryoSat-2 Low Resolution Mode (LRM) waveforms over both ice sheets. We compare the AWI-ICENet1-retrieved SEC with estimates from conventional retrackers, including the threshold first-maximum retracker algorithm (TFMRA) and the European Space Agency's (ESA) ICE1 and ICE2 products. Our results show less uncertainty and a great decrease in the effect of time-variable radar penetration, reducing the need for corrections based on its close relationship with backscatter and/or leading-edge width, which are typically used in SEC processing. This technique provides new opportunities to utilize convolutional neural networks in the processing of satellite altimetry data and is thus applicable to historical, recent, and future missions.

Abstract. Calving front positions of marine-terminating glaciers are an essential parameter to understanding dynamic glacier changes and constraining ice modelling. In particular, for the Antarctic Peninsula, where the current ice mass loss is driven by dynamic glacier changes, accurate and comprehensive data products are of major importance. Current calving front data products are limited in coverage and temporal resolution because they rely on manual delineation being time-consuming and unfeasible for the increasing amount of satellite data. To simplify the mapping of calving fronts we apply a deep learning based processing system designed to automatically delineate glacier fronts from multispectral Landsat imagery. The U-Net based framework was initially trained on 869 Greenland glacier front positions and is here extended by 236 front positions of the Antarctic Peninsula. The here presented data product includes 2064 calving front locations of 19 key outlet glaciers from 2013 to 2023 and achieves sub-seasonal temporal resolution. This data set will help to better understand marine-terminating glacier dynamics on an intra-annual scale, study ice-ocean interactions in more detail and constrain glacier models. The data is publicly available at PANGAEA under https://doi.pangaea.de/10.1594/PANGAEA.963725 (Loebel et al., 2023b).

Abstract. The Greenland Ice Sheet has steadily lost mass over the past decades, presently representing the second-largest single contributor to global sea-level rise. Even the glaciers draining the Northeast Greenland ice stream have been observed to retreat and thin. Here, we present a comprehensive study of processes affecting and being affected by the mass balance of marine terminating and peripheral glaciers in Northeast Greenland. Our focus is on the 79N Glacier (79NG), which hosts Greenland’s largest floating ice tongue. We provide new insight into the ice surface melt, ice mass balance, glacier dynamics, regional solid earth response, ocean-driven basal melt and the consequences of meltwater discharge into the ocean. Our study is based on observations, remote sensing and simulations with numerical models of different complexity, most of them originating from the Greenland Ice Sheet–Ocean Interaction Experiment (GROCE). We find the overall negative climatic mass balance of the 79NG to co-vary with summertime volumes of supraglacial lakes, and show the spatial pattern of overall negative ice mass balance for NE Greenland to be mirrored by the pattern of glacial isostatic adjustment. We find near coastal mass losses of both marine terminating and peripheral glaciers in NE Greenland to be of similar magnitude in the last decade. In contrast to the neighboring Zachariae Isstrøm, the 79NG – despite experiencing massive thinning of the floating tongue – has resisted an acceleration of ice discharge across the grounding line due to buttressing imposed by lateral friction of the 70 km-long ice tongue in the narrow glacial fjord. Observations and models employed in this study are consistent in terms of melt rates occurring below the floating ice tongue. Our results suggest the multidecadal warming of Atlantic Intermediate Water flowing into the cavity below the ice tongue – supplied by the recirculating branch of the West Spitsbergen Current in Fram Strait – to be the main driver of the recent major increase in basal melt rates. We find the melt water leaving the cavity toward the ocean at subsurface levels to quickly dilute on the wide shelf. The study concludes by summarizing important estimates of changes to the state of the atmosphere, ice, land and ocean domains.

The largest floating tongue of Greenland’s ice sheet, Nioghalvfjerdsbrae, has so far been relatively stable with respect to areal retreat. Curiously, it experienced significant less thinning and ice flow acceleration than its neighbour Zacharias Isbrae. Draining more than 6% of the ice sheet, Nioghalvfjerdsbrae might become a large contributor to sea level rise in the future. Therefore, the stability of the floating tongue is a focus of this study. We employ a suite of observational methods to detect recent changes. We found that the calving style has changed at the southern part of the eastern calving front from normal tongue-type calving to a crack evolution initiated at frontal ice rises reaching 5-7km and progressing further upstream compared to 2010. The calving front area is further weakened by a substantial increase of a zone of fragments and open water at the tongue’s southern margin, leading to the formation of a narrow ice bridge. These geometric and mechanical changes are a precursor of instability of the floating tongue. We complement our study by numerical ice flow simulations to estimate the impact of future break-up or disintegration events on the ice discharge. These idealised scenarios reveal that a loss of the south-eastern area would lead to 1% of increase of ice discharge at the grounding line, while a sudden collapse of the frontal area (46% of the floating tongue area) will enhance the ice discharge by 8.3% due to loss in buttressing.Humbert, A., Helm, V., Neckel, N., Zeising, O., Rückamp, M., Khan, S. A., Loebel, E., Gross, D., Sondershaus, R., and Müller, R.: Precursor of disintegration of Greenland's largest floating ice tongue, The Cryosphere Discuss. [preprint], https://doi.org/10.5194/tc-2022-171, in review, 2022

Outlet glaciers in Greenland experience a combination of seasonal and climate-driven change. In this study, we investigate the temporal evolution of the ice front position at Kangiata Nunaata Sermia (KNS), southwest Greenland. At this outlet glacier, a seasonal ice tongue forms almost every year in winter and breaks up in spring. The motion of the ice-ocean interface is one key driver of ice dynamics. Hence, it is important to understand and reconstruct terminus fluctuations. Utilizing the increasing availability of remote sensing data and deep learning algorithms, we accurately and frequently map the ice/ocean transition from optical satellite imagery. How can we incorporate that geometrical information of frontal positions into ice sheet models? The ice flow counteracts the mass loss due to iceberg calving and frontal melt. All those processes result in moving ice fronts over time. The interaction between ice flow and ice discharge is one challenge in combining observed ice front positions and modelling. We present two ways to include the geometric information of ice front positions into the Ice-sheet and Sea-level System Model (ISSM). In a first approach, we engage a level-set method to incorporate the derived calving front positions into the ice sheet model. By prescribing observed front positions, we ignore any physical basis of ice flow dynamics. However, the level-set method allows us to solve a differential equation continuous in time and space. Since we have to deal with observational gaps of ice front positions, not all stress changes caused by changing ice front positions might be resolved by this approach. In the second approach, we discuss physical drivers of terminus changes in more detail. We show parametrizations of calving and frontal melt depending on stress thresholds and subglacial water fluxes to reproduce the observed temporal evolution of the ice front position. The parametrization due to calving leads to ice loss velocities that are one order of magnitude higher than the one due to ocean melt. In the end, we want to combine both approaches to come up with an accurate parameterization of ice loss due to calving and melting, which fit observations and incorporate the physics of glacier flow.

We present a deep active contour model for detecting and delineating glacier calving fronts from satellite imagery. Contrary to existing deep learning-based calving front detectors, our model does not perform an intermediate segmentation or pixel-wise edge detection, but instead directly predicts the contour parametrized by a fixed number of vertices. The model works by first deriving feature maps from an input image, and then updating an initial contour in an iterative fashion. Evaluating on the CALFIN dataset, which maps calving fronts in Greenland, our model outperforms existing approaches. Code for the experiments and animated predictions can be found at https://github.com/khdlr/deep-acm

A lot of things in life need money and so does polar science: money is needed to participate in conferences, undertake fieldwork campaigns or pay for salaries, such as in PhD projects or permanent research positions. To give an overview on the general funding landscape for polar early-career scientists in Germany, APECS Germany (the German National Committee of the Association of Polar Early Career Scientists, APECS) has started to host a list of grant, fellowship and other funding opportunities at https://apecs-germany.de/funding/ (last access: 15 October 2022). This is visualized in Fig. 1. Once a suitable funding scheme has been found, grant writing requires good preparation, a well-structured and written proposal, and several back-up plans.

An accurate parameterization of glacier calving is essential for understanding glacier dynamics and constraining ice-sheet models. The increasing availability and quality of remote sensing imagery open the prospect of a continuous and precise mapping of relevant parameters, such as calving front locations. However, it also calls for automated and scalable analysis strategies. Deep neural networks provide powerful tools for processing large quantities of remote sensing data. In this contribution, we assess the benefit of diverse input data for calving front extraction. In particular, we focus on Landsat-8 imagery supplementing single-band inputs with multispectral data, topography, and textural information. We assess the benefit of these three datasets using a dropped-variable approach. The associated reference dataset comprises 728 manually delineated calving front positions of 23 Greenland and two Antarctic outlet glaciers from 2013 to 2021. Resulting feature importance emphasizes both the potential integrating additional input information as well as the significance of their thoughtful selection. We advocate utilizing multispectral features as their integration leads generally to more accurate predictions compared with conventional single-band inputs. This is especially prevalent for challenging ice mélange and illumination conditions. In contrast, the application of both textural and topographic inputs cannot be recommended without reservation, since they may lead to model overfitting. The results of this assessment are not only relevant for advancing automated calving front extraction but also for a wider range of glaciology-related land surface classification tasks using deep neural networks.

The calving of tidewater glaciers has a strong impact on the stresses of outlet glaciers and their discharge. However, it is still underrepresented in current ice-sheet models incorporating the dynamics of marine-terminating glaciers. This has an impact on simulation results when projecting future sea-level contributions of the Greenland ice sheet. The increasing availability and quality of remote sensing imagery enable us to realize a continuous and precise mapping of relevant parameters such as calving front locations. However, the huge amount of data also accentuates the necessity for intelligent analysis strategies. In this contribution, we apply an automated workflow to extract calving front positions from multi-spectral Landsat-8 imagery utilizing deep learning. The core of the proposed workflow comprises a convolutional neural network (CNN) for image segmentation exploiting the full range of Landsat-8 multi-spectral capabilities, a statistical textural feature analysis performed on the high-resolution panchromatic band as well as topography model data. The proposed method is evaluated by an independent set of diverse test images as well as by comparing with already available ESA-CCI, MEaSUREs and PROMICE data products. With an estimated prediction error of fewer than two pixels (which equals a spatial resolution of 60 m), automatically extracted calving front locations show very small or even non-distinguishable differences to manually delineated locations. The importance of multi-spectral, textural and topographic features used as input for the CNN is estimated by a permute-and-relearn approach emphasizing their benefit, especially in challenging ice-melange, cloud, and illumination conditions. Jointly with the proposed methodology we present an exceedingly dense dataset for 20 of the most important Greenlandic outlet glaciers for the period from 2013 to 2021. Eventually, the derived calving front positions are incorporated into the Ice Sheet and Sea-Level System Model (ISSM). For this, we engage a level set method. This method allows deriving a continuous function in time and space from discrete information at satellite acquisition time steps. As the satellite data is mainly available for fast-flowing outlet glaciers, we use simulated front positions for all remaining ice margins. An alpha-shape method seamlessly links the temporal changing calving fronts to the Greenlandic ice sheet.

“Artificial Intelligence for Cold Regions” (AI-CORE) is a collaborative project of the German Aerospace Center (DLR), the Alfred Wegener Institute (AWI), the Technical University Dresden (TU Dresden), and is funded by the Helmholtz Foundation since early 2020. The project aims at developing artificial intelligence methods for addressing some of the most challenging research questions in remote sensing of the cryosphere. Rapidly changing ice sheets and thawing permafrost are big societal challenges, hence quantifying these changes and understanding the mechanisms are of major importance. Given the vast extent of polar regions and the availability of exponentially increasing satellite remote sensing data, intelligent data analysis is urgently required to exploit the full information in satellite time series. This is where AI-CORE comes into play: Four geoscientific use cases have been defined, including a) change pattern identification of outlet glaciers in Greenland; b) object identification in permafrost areas; c) edge detection of calving fronts of glaciers/ice shelves in Antarctica; d) firn line detection and monitoring: The glacier mass balance indicator. For these four use cases, AI-methods are being developed to allow for an accurate, efficient, and automated extraction of the desired parameters. Once these methods have been successfully developed, they will be implemented in processing infrastructures at AWI, TU Dresden, and DLR, and subsequently made available to other research institutes. The presentation will outline the specific goals and challenges of the four use cases as well as the current state of the developments and preliminary results.