Articles | Volume 17, issue 11
https://doi.org/10.5194/tc-17-4675-2023
© Author(s) 2023. 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-17-4675-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
09 Nov 2023
Research article |
| 09 Nov 2023
| 09 Nov 2023
Mapping the extent of giant Antarctic icebergs with deep learning
Anne Braakmann-Folgmann
CORRESPONDING AUTHOR
Centre for Polar Observation and Modelling (CPOM), University of Leeds, Leeds, LS2 9JT, UK
Department of Physics and Technology, UiT, The Arctic University of Norway, Tromsø, 9019, Norway
Andrew Shepherd
Centre for Polar Observation and Modelling (CPOM), University of Leeds, Leeds, LS2 9JT, UK
Department of Geography and Environmental Sciences, Northumbria University, Newcastle upon Tyne, NE1 8ST, UK
David Hogg
School of Computing, University of Leeds, Leeds, LS2 9JT, UK
Ella Redmond
Centre for Polar Observation and Modelling (CPOM), University of Leeds, Leeds, LS2 9JT, UK
Related authors
Anne Braakmann-Folgmann, Jack C. Landy, Geoffrey Dawson, and Robert Ricker
EGUsphere, https://doi.org/10.5194/egusphere-2025-2789, https://doi.org/10.5194/egusphere-2025-2789, 2025
This preprint is open for discussion and under review for The Cryosphere (TC).
Short summary
Short summary
To calculate sea ice thickness from altimetry, returns from ice and leads need to be differentiated. During summer, melt ponds complicate this task, as they resemble leads. In this study, we improve a previously suggested neural network classifier by expanding the training dataset fivefold, tuning the network architecture and introducing an additional class for thinned floes. We show that this increases the accuracy from 77 ± 5 % to 84 ± 2 % and that more leads are found.
Jack C. Landy, Claude de Rijke-Thomas, Carmen Nab, Isobel Lawrence, Isolde A. Glissenaar, Robbie D. C. Mallett, Renée M. Fredensborg Hansen, Alek Petty, Michel Tsamados, Amy R. Macfarlane, and Anne Braakmann-Folgmann
EGUsphere, https://doi.org/10.5194/egusphere-2024-2904, https://doi.org/10.5194/egusphere-2024-2904, 2024
Short summary
Short summary
In this study we use three satellites to test the planned remote sensing approach of the upcoming mission CRISTAL over sea ice: that its dual radars will accurately measure the heights of the top and base of snow sitting atop floating sea ice floes. Our results suggest that CRISTAL's dual radars won’t necessarily measure the snow top and base under all conditions. We find that accurate height measurements depend much more on surface roughness than on snow properties, as is commonly assumed.
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.
Anne Braakmann-Folgmann, Jack C. Landy, Geoffrey Dawson, and Robert Ricker
EGUsphere, https://doi.org/10.5194/egusphere-2025-2789, https://doi.org/10.5194/egusphere-2025-2789, 2025
This preprint is open for discussion and under review for The Cryosphere (TC).
Short summary
Short summary
To calculate sea ice thickness from altimetry, returns from ice and leads need to be differentiated. During summer, melt ponds complicate this task, as they resemble leads. In this study, we improve a previously suggested neural network classifier by expanding the training dataset fivefold, tuning the network architecture and introducing an additional class for thinned floes. We show that this increases the accuracy from 77 ± 5 % to 84 ± 2 % and that more leads are found.
Amy E. Swiggs, Isobel R. Lawrence, and Andrew Shepherd
EGUsphere, https://doi.org/10.5194/egusphere-2025-693, https://doi.org/10.5194/egusphere-2025-693, 2025
Preprint withdrawn
Short summary
Short summary
We produce a new sea ice concentration product in the Canadian Arctic. This region is vital for shipping, sea ice dependent species, and the movement of sea ice and freshwater. We find that the new dataset agrees well with existing sensors. As it is sensitive to leads, it can detect fine-scale sea ice features, and generally resolves a lower sea ice concentration for this reason. This different approach is important for monitoring sea ice dynamics in a changing climate.
Jack C. Landy, Claude de Rijke-Thomas, Carmen Nab, Isobel Lawrence, Isolde A. Glissenaar, Robbie D. C. Mallett, Renée M. Fredensborg Hansen, Alek Petty, Michel Tsamados, Amy R. Macfarlane, and Anne Braakmann-Folgmann
EGUsphere, https://doi.org/10.5194/egusphere-2024-2904, https://doi.org/10.5194/egusphere-2024-2904, 2024
Short summary
Short summary
In this study we use three satellites to test the planned remote sensing approach of the upcoming mission CRISTAL over sea ice: that its dual radars will accurately measure the heights of the top and base of snow sitting atop floating sea ice floes. Our results suggest that CRISTAL's dual radars won’t necessarily measure the snow top and base under all conditions. We find that accurate height measurements depend much more on surface roughness than on snow properties, as is commonly assumed.
Renée M. Fredensborg Hansen, Henriette Skourup, Eero Rinne, Arttu Jutila, Isobel R. Lawrence, Andrew Shepherd, Knut V. Høyland, Jilu Li, Fernando Rodriguez-Morales, Sebastian B. Simonsen, Jeremy Wilkinson, Gaelle Veyssiere, Donghui Yi, René Forsberg, and Taniâ G. D. Casal
EGUsphere, https://doi.org/10.5194/egusphere-2024-2854, https://doi.org/10.5194/egusphere-2024-2854, 2024
Short summary
Short summary
In December 2022, an airborne campaign collected unprecedented coincident multi-frequency radar and lidar data over sea ice along a CryoSat-2 and ICESat-2 (CRYO2ICE) orbit in the Weddell Sea useful for evaluating microwave penetration. We found limited snow penetration at Ka- and Ku-bands, with significant contributions from the air-snow interface, contradicting traditional assumptions. These findings challenge current methods for comparing air- and spaceborne altimeter estimates of sea ice.
Trystan Surawy-Stepney, Anna E. Hogg, Stephen L. Cornford, Benjamin J. Wallis, Benjamin J. Davison, Heather L. Selley, Ross A. W. Slater, Elise K. Lie, Livia Jakob, Andrew Ridout, Noel Gourmelen, Bryony I. D. Freer, Sally F. Wilson, and Andrew Shepherd
The Cryosphere, 18, 977–993, https://doi.org/10.5194/tc-18-977-2024, https://doi.org/10.5194/tc-18-977-2024, 2024
Short summary
Short summary
Here, we use satellite observations and an ice flow model to quantify the impact of sea ice buttressing on ice streams on the Antarctic Peninsula. The evacuation of 11-year-old landfast sea ice in the Larsen B embayment on the East Antarctic Peninsula in January 2022 was closely followed by major changes in the calving behaviour and acceleration (30 %) of the ocean-terminating glaciers. Our results show that sea ice buttressing had a negligible direct role in the observed dynamic changes.
Hélène Seroussi, Vincent Verjans, Sophie Nowicki, Antony J. Payne, Heiko Goelzer, William H. Lipscomb, Ayako Abe-Ouchi, Cécile Agosta, Torsten Albrecht, Xylar Asay-Davis, Alice Barthel, Reinhard Calov, Richard Cullather, Christophe Dumas, Benjamin K. Galton-Fenzi, Rupert Gladstone, Nicholas R. Golledge, Jonathan M. Gregory, Ralf Greve, Tore Hattermann, Matthew J. Hoffman, Angelika Humbert, Philippe Huybrechts, Nicolas C. Jourdain, Thomas Kleiner, Eric Larour, Gunter R. Leguy, Daniel P. Lowry, Chistopher M. Little, Mathieu Morlighem, Frank Pattyn, Tyler Pelle, Stephen F. Price, Aurélien Quiquet, Ronja Reese, Nicole-Jeanne Schlegel, Andrew Shepherd, Erika Simon, Robin S. Smith, Fiammetta Straneo, Sainan Sun, Luke D. Trusel, Jonas Van Breedam, Peter Van Katwyk, Roderik S. W. van de Wal, Ricarda Winkelmann, Chen Zhao, Tong Zhang, and Thomas Zwinger
The Cryosphere, 17, 5197–5217, https://doi.org/10.5194/tc-17-5197-2023, https://doi.org/10.5194/tc-17-5197-2023, 2023
Short summary
Short summary
Mass loss from Antarctica is a key contributor to sea level rise over the 21st century, and the associated uncertainty dominates sea level projections. We highlight here the Antarctic glaciers showing the largest changes and quantify the main sources of uncertainty in their future evolution using an ensemble of ice flow models. We show that on top of Pine Island and Thwaites glaciers, Totten and Moscow University glaciers show rapid changes and a strong sensitivity to warmer ocean conditions.
Trystan Surawy-Stepney, Anna E. Hogg, Stephen L. Cornford, and David C. Hogg
The Cryosphere, 17, 4421–4445, https://doi.org/10.5194/tc-17-4421-2023, https://doi.org/10.5194/tc-17-4421-2023, 2023
Short summary
Short summary
The presence of crevasses in Antarctica influences how the ice sheet behaves. It is important, therefore, to collect data on the spatial distribution of crevasses and how they are changing. We present a method of mapping crevasses from satellite radar imagery and apply it to 7.5 years of images, covering Antarctica's floating and grounded ice. We develop a method of measuring change in the density of crevasses and quantify increased fracturing in important parts of the West Antarctic Ice Sheet.
Inès N. Otosaka, Andrew Shepherd, Erik R. Ivins, Nicole-Jeanne Schlegel, Charles Amory, Michiel R. van den Broeke, Martin Horwath, Ian Joughin, Michalea D. King, Gerhard Krinner, Sophie Nowicki, Anthony J. Payne, Eric Rignot, Ted Scambos, Karen M. Simon, Benjamin E. Smith, Louise S. Sørensen, Isabella Velicogna, Pippa L. Whitehouse, Geruo A, Cécile Agosta, Andreas P. Ahlstrøm, Alejandro Blazquez, William Colgan, Marcus E. Engdahl, Xavier Fettweis, Rene Forsberg, Hubert Gallée, Alex Gardner, Lin Gilbert, Noel Gourmelen, Andreas Groh, Brian C. Gunter, Christopher Harig, Veit Helm, Shfaqat Abbas Khan, Christoph Kittel, Hannes Konrad, Peter L. Langen, Benoit S. Lecavalier, Chia-Chun Liang, Bryant D. Loomis, Malcolm McMillan, Daniele Melini, Sebastian H. Mernild, Ruth Mottram, Jeremie Mouginot, Johan Nilsson, Brice Noël, Mark E. Pattle, William R. Peltier, Nadege Pie, Mònica Roca, Ingo Sasgen, Himanshu V. Save, Ki-Weon Seo, Bernd Scheuchl, Ernst J. O. Schrama, Ludwig Schröder, Sebastian B. Simonsen, Thomas Slater, Giorgio Spada, Tyler C. Sutterley, Bramha Dutt Vishwakarma, Jan Melchior van Wessem, David Wiese, Wouter van der Wal, and Bert Wouters
Earth Syst. Sci. Data, 15, 1597–1616, https://doi.org/10.5194/essd-15-1597-2023, https://doi.org/10.5194/essd-15-1597-2023, 2023
Short summary
Short summary
By measuring changes in the volume, gravitational attraction, and ice flow of Greenland and Antarctica from space, we can monitor their mass gain and loss over time. Here, we present a new record of the Earth’s polar ice sheet mass balance produced by aggregating 50 satellite-based estimates of ice sheet mass change. This new assessment shows that the ice sheets have lost (7.5 x 1012) t of ice between 1992 and 2020, contributing 21 mm to sea level rise.
Karina von Schuckmann, Audrey Minière, Flora Gues, Francisco José Cuesta-Valero, Gottfried Kirchengast, Susheel Adusumilli, Fiammetta Straneo, Michaël Ablain, Richard P. Allan, Paul M. Barker, Hugo Beltrami, Alejandro Blazquez, Tim Boyer, Lijing Cheng, John Church, Damien Desbruyeres, Han Dolman, Catia M. Domingues, Almudena García-García, Donata Giglio, John E. Gilson, Maximilian Gorfer, Leopold Haimberger, Maria Z. Hakuba, Stefan Hendricks, Shigeki Hosoda, Gregory C. Johnson, Rachel Killick, Brian King, Nicolas Kolodziejczyk, Anton Korosov, Gerhard Krinner, Mikael Kuusela, Felix W. Landerer, Moritz Langer, Thomas Lavergne, Isobel Lawrence, Yuehua Li, John Lyman, Florence Marti, Ben Marzeion, Michael Mayer, Andrew H. MacDougall, Trevor McDougall, Didier Paolo Monselesan, Jan Nitzbon, Inès Otosaka, Jian Peng, Sarah Purkey, Dean Roemmich, Kanako Sato, Katsunari Sato, Abhishek Savita, Axel Schweiger, Andrew Shepherd, Sonia I. Seneviratne, Leon Simons, Donald A. Slater, Thomas Slater, Andrea K. Steiner, Toshio Suga, Tanguy Szekely, Wim Thiery, Mary-Louise Timmermans, Inne Vanderkelen, Susan E. Wjiffels, Tonghua Wu, and Michael Zemp
Earth Syst. Sci. Data, 15, 1675–1709, https://doi.org/10.5194/essd-15-1675-2023, https://doi.org/10.5194/essd-15-1675-2023, 2023
Short summary
Short summary
Earth's climate is out of energy balance, and this study quantifies how much heat has consequently accumulated over the past decades (ocean: 89 %, land: 6 %, cryosphere: 4 %, atmosphere: 1 %). Since 1971, this accumulated heat reached record values at an increasing pace. The Earth heat inventory provides a comprehensive view on the status and expectation of global warming, and we call for an implementation of this global climate indicator into the Paris Agreement’s Global Stocktake.
Martin Horwath, Benjamin D. Gutknecht, Anny Cazenave, Hindumathi Kulaiappan Palanisamy, Florence Marti, Ben Marzeion, Frank Paul, Raymond Le Bris, Anna E. Hogg, Inès Otosaka, Andrew Shepherd, Petra Döll, Denise Cáceres, Hannes Müller Schmied, Johnny A. Johannessen, Jan Even Øie Nilsen, Roshin P. Raj, René Forsberg, Louise Sandberg Sørensen, Valentina R. Barletta, Sebastian B. Simonsen, Per Knudsen, Ole Baltazar Andersen, Heidi Ranndal, Stine K. Rose, Christopher J. Merchant, Claire R. Macintosh, Karina von Schuckmann, Kristin Novotny, Andreas Groh, Marco Restano, and Jérôme Benveniste
Earth Syst. Sci. Data, 14, 411–447, https://doi.org/10.5194/essd-14-411-2022, https://doi.org/10.5194/essd-14-411-2022, 2022
Short summary
Short summary
Global mean sea-level change observed from 1993 to 2016 (mean rate of 3.05 mm yr−1) matches the combined effect of changes in water density (thermal expansion) and ocean mass. Ocean-mass change has been assessed through the contributions from glaciers, ice sheets, and land water storage or directly from satellite data since 2003. Our budget assessments of linear trends and monthly anomalies utilise new datasets and uncertainty characterisations developed within ESA's Climate Change Initiative.
Emma K. Fiedler, Matthew J. Martin, Ed Blockley, Davi Mignac, Nicolas Fournier, Andy Ridout, Andrew Shepherd, and Rachel Tilling
The Cryosphere, 16, 61–85, https://doi.org/10.5194/tc-16-61-2022, https://doi.org/10.5194/tc-16-61-2022, 2022
Short summary
Short summary
Sea ice thickness (SIT) observations derived from CryoSat-2 satellite measurements have been successfully used to initialise an ocean and sea ice forecasting model (FOAM). Other centres have previously used gridded and averaged SIT observations for this purpose, but we demonstrate here for the first time that SIT measurements along the satellite orbit track can be used. Validation of the resulting modelled SIT demonstrates improvements in the model performance compared to a control.
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.
Thomas Slater, Isobel R. Lawrence, Inès N. Otosaka, Andrew Shepherd, Noel Gourmelen, Livia Jakob, Paul Tepes, Lin Gilbert, and Peter Nienow
The Cryosphere, 15, 233–246, https://doi.org/10.5194/tc-15-233-2021, https://doi.org/10.5194/tc-15-233-2021, 2021
Short summary
Short summary
Satellite observations are the best method for tracking ice loss, because the cryosphere is vast and remote. Using these, and some numerical models, we show that Earth has lost 28 trillion tonnes (Tt) of ice since 1994 from Arctic sea ice (7.6 Tt), ice shelves (6.5 Tt), mountain glaciers (6.1 Tt), the Greenland (3.8 Tt) and Antarctic ice sheets (2.5 Tt), and Antarctic sea ice (0.9 Tt). It has taken just 3.2 % of the excess energy Earth has absorbed due to climate warming to cause this ice loss.
Heiko Goelzer, Sophie Nowicki, Anthony Payne, Eric Larour, Helene Seroussi, William H. Lipscomb, Jonathan Gregory, Ayako Abe-Ouchi, Andrew Shepherd, Erika Simon, Cécile Agosta, Patrick Alexander, Andy Aschwanden, Alice Barthel, Reinhard Calov, Christopher Chambers, Youngmin Choi, Joshua Cuzzone, Christophe Dumas, Tamsin Edwards, Denis Felikson, Xavier Fettweis, Nicholas R. Golledge, Ralf Greve, Angelika Humbert, Philippe Huybrechts, Sebastien Le clec'h, Victoria Lee, Gunter Leguy, Chris Little, Daniel P. Lowry, Mathieu Morlighem, Isabel Nias, Aurelien Quiquet, Martin Rückamp, Nicole-Jeanne Schlegel, Donald A. Slater, Robin S. Smith, Fiamma Straneo, Lev Tarasov, Roderik van de Wal, and Michiel van den Broeke
The Cryosphere, 14, 3071–3096, https://doi.org/10.5194/tc-14-3071-2020, https://doi.org/10.5194/tc-14-3071-2020, 2020
Short summary
Short summary
In this paper we use a large ensemble of Greenland ice sheet models forced by six different global climate models to project ice sheet changes and sea-level rise contributions over the 21st century.
The results for two different greenhouse gas concentration scenarios indicate that the Greenland ice sheet will continue to lose mass until 2100, with contributions to sea-level rise of 90 ± 50 mm and 32 ± 17 mm for the high (RCP8.5) and low (RCP2.6) scenario, respectively.
Hélène Seroussi, Sophie Nowicki, Antony J. Payne, Heiko Goelzer, William H. Lipscomb, Ayako Abe-Ouchi, Cécile Agosta, Torsten Albrecht, Xylar Asay-Davis, Alice Barthel, Reinhard Calov, Richard Cullather, Christophe Dumas, Benjamin K. Galton-Fenzi, Rupert Gladstone, Nicholas R. Golledge, Jonathan M. Gregory, Ralf Greve, Tore Hattermann, Matthew J. Hoffman, Angelika Humbert, Philippe Huybrechts, Nicolas C. Jourdain, Thomas Kleiner, Eric Larour, Gunter R. Leguy, Daniel P. Lowry, Chistopher M. Little, Mathieu Morlighem, Frank Pattyn, Tyler Pelle, Stephen F. Price, Aurélien Quiquet, Ronja Reese, Nicole-Jeanne Schlegel, Andrew Shepherd, Erika Simon, Robin S. Smith, Fiammetta Straneo, Sainan Sun, Luke D. Trusel, Jonas Van Breedam, Roderik S. W. van de Wal, Ricarda Winkelmann, Chen Zhao, Tong Zhang, and Thomas Zwinger
The Cryosphere, 14, 3033–3070, https://doi.org/10.5194/tc-14-3033-2020, https://doi.org/10.5194/tc-14-3033-2020, 2020
Short summary
Short summary
The Antarctic ice sheet has been losing mass over at least the past 3 decades in response to changes in atmospheric and oceanic conditions. This study presents an ensemble of model simulations of the Antarctic evolution over the 2015–2100 period based on various ice sheet models, climate forcings and emission scenarios. Results suggest that the West Antarctic ice sheet will continue losing a large amount of ice, while the East Antarctic ice sheet could experience increased snow accumulation.
Karina von Schuckmann, Lijing Cheng, Matthew D. Palmer, James Hansen, Caterina Tassone, Valentin Aich, Susheel Adusumilli, Hugo Beltrami, Tim Boyer, Francisco José Cuesta-Valero, Damien Desbruyères, Catia Domingues, Almudena García-García, Pierre Gentine, John Gilson, Maximilian Gorfer, Leopold Haimberger, Masayoshi Ishii, Gregory C. Johnson, Rachel Killick, Brian A. King, Gottfried Kirchengast, Nicolas Kolodziejczyk, John Lyman, Ben Marzeion, Michael Mayer, Maeva Monier, Didier Paolo Monselesan, Sarah Purkey, Dean Roemmich, Axel Schweiger, Sonia I. Seneviratne, Andrew Shepherd, Donald A. Slater, Andrea K. Steiner, Fiammetta Straneo, Mary-Louise Timmermans, and Susan E. Wijffels
Earth Syst. Sci. Data, 12, 2013–2041, https://doi.org/10.5194/essd-12-2013-2020, https://doi.org/10.5194/essd-12-2013-2020, 2020
Short summary
Short summary
Understanding how much and where the heat is distributed in the Earth system is fundamental to understanding how this affects warming oceans, atmosphere and land, rising temperatures and sea level, and loss of grounded and floating ice, which are fundamental concerns for society. This study is a Global Climate Observing System (GCOS) concerted international effort to obtain the Earth heat inventory over the period 1960–2018.
Cited articles
Andersson, T. R., Hosking, J. S., Pérez-Ortiz, M., Paige, B., Elliott, A., Russell, C., Law, S., Jones, D. C., Wilkinson, J., Phillips, T., Byrne, J., Tietsche, S., Sarojini, B. B., Blanchard-Wrigglesworth, E., Aksenov, Y., Downie, R. and Shuckburgh, E.: Seasonal Arctic sea ice forecasting with probabilistic deep learning, Nat. Commun., 12, 1–12, https://doi.org/10.1038/s41467-021-25257-4, 2021.
Barbat, M. M., Wesche, C., Werhli, A. V., and Mata, M. M.: An adaptive machine learning approach to improve automatic iceberg detection from SAR images, ISPRS J. Photogramm., 156, 247–259, https://doi.org/10.1016/j.isprsjprs.2019.08.015, 2019a.
Barbat, M. M., Rackow, T., Hellmer, H. H., Wesche, C., and Mata, M. M.: Three Years of Near-Coastal Antarctic Iceberg Distribution From a Machine Learning Approach Applied to SAR Imagery, J. Geophys. Res.-Oceans, 124, 6658–6672, https://doi.org/10.1029/2019JC015205, 2019b.
Barbat, M. M., Rackow, T., Wesche, C., Hellmer, H. H., and Mata, M. M.: Automated iceberg tracking with a machine learning approach applied to SAR imagery: A Weddell sea case study, ISPRS J. Photogramm., 172, 189–206, https://doi.org/10.1016/j.isprsjprs.2020.12.006, 2021.
Baumhoer, C. A., Dietz, A. J., Kneisel, C., and Kuenzer, C.: Au- 55 tomated extraction of antarctic glacier and ice shelf fronts from Sentinel-1 imagery using deep learning, Remote Sens., 11, 1–22, https://doi.org/10.3390/rs11212529, 2019.
Baumhoer, C. A., Dietz, A., Heidler, K., and Kuenzer, C.: IceLines – A new data set of Antarctic ice shelf front positions, Sci. Data, 10, 138, https://doi.org/10.1038/s41597-023-02045-x, 2023.
Bigg, G. R., Wadley, M. R., Stevens, D. P., and Johnson, J. A.: Modelling the dynamics and thermodynamics of icebergs, Cold Reg. Sci. Technol., 26, 113–135, https://doi.org/10.1016/S0165-232X(97)00012-8, 1997.
Bouhier, N., Tournadre, J., Rémy, F., and Gourves-Cousin, R.: Melting and fragmentation laws from the evolution of two large Southern Ocean icebergs estimated from satellite data, The Cryosphere, 12, 2267–2285, https://doi.org/10.5194/tc-12-2267-2018, 2018.
Braakmann-Folgmann, A.: Segmentation maps of giant Antarctic icebergs, Zenodo [video], https://doi.org/10.5281/zenodo.7875599, 2023.
Braakmann-Folgmann, A., Shepherd, A., and Ridout, A.: Tracking changes in the area, thickness, and volume of the Thwaites tabular iceberg “B30” using satellite altimetry and imagery, The Cryosphere, 15, 3861–3876, https://doi.org/10.5194/tc-15-3861-2021, 2021.
Braakmann-Folgmann, A., Shepherd, A., Gerrish, L., Izzard, J., and Ridout, A.: Observing the disintegration of the A68A iceberg from space, Remote Sens. Environ., 270, 112855, https://doi.org/10.1016/j.rse.2021.112855, 2022.
Bradski, G.: The OpenCV Library, Dr. Dobb's J. Softw. Tools, 25, 120–125, 2000.
Budge, J. S. and Long, D. G.: A Comprehensive Database for Antarctic Iceberg Tracking Using Scatterometer Data, IEEE J. Sel. Top. Appl., 11, 434–442, https://doi.org/10.1109/JSTARS.2017.2784186, 2018.
Chollet, F.: Xception: Deep learning with depthwise separable convolutions, Proc. – 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, 1800–1807, https://doi.org/10.1109/CVPR.2017.195, 2017.
Chollet, F. and Others: Keras, GitHub [code], https://github.com/fchollet/keras (last access: 6 August 2023), 2015.
Collares, L. L., Mata, M. M., Kerr, R., Arigony-Neto, J., and Barbat, M. M.: Iceberg drift and ocean circulation in the northwestern Weddell Sea, Antarctica, Deep.-Sea Res. Pt II, 149, 10–24, https://doi.org/10.1016/j.dsr2.2018.02.014, 2018.
Dirscherl, M., Dietz, A. J., Kneisel, C., and Kuenzer, C.: A novel method for automated supraglacial lake mapping in antarctica using sentinel-1 sar imagery and deep learning, Remote Sens., 13, 1–27, https://doi.org/10.3390/rs13020197, 2021.
Drinkwater, M. R.: Satellite Microwave Radar Observations of Antarctic Sea Ice, Anal. SAR Data Polar Ocean., 145–187, https://doi.org/10.1007/978-3-642-60282-5_8, 1998.
Duprat, L. P. A. M., Bigg, G. R., and Wilton, D. J.: Enhanced Southern Ocean marine productivity due to fertilization by giant icebergs, Nat. Geosci., 9, 219–221, https://doi.org/10.1038/ngeo2633, 2016.
England, M. R., Wagner, T. J. W., and Eisenman, I.: Modeling the breakup of tabular icebergs, Sci. Adv., 6, 1–9, https://doi.org/10.1126/sciadv.abd1273, 2020.
Frost, A., Ressel, R., and Lehner, S.: Automated iceberg detection using high resolution X-band SAR images, Can. J. Remote Sens., 42, 354–366, https://doi.org/10.1080/07038992.2016.1177451, 2016.
Gawlikowski, J., Tassi, C. R. N., Ali, M., Lee, J., Humt, M., Feng, J., Kruspe, A., Triebel, R., Jung, P., Roscher, R., Shahzad, M., Yang, W., Bamler, R., and Zhu, X. X.: A Survey of Uncertainty in Deep Neural Networks, Arxiv [preprint], https://doi.org/10.48550/arXiv.2107.03342, 2021.
Gill, R. S.: Operational detection of sea ice edges and icebergs using SAR, Can. J. Remote Sens., 27, 411–432, https://doi.org/10.1080/07038992.2001.10854884, 2001.
Greene, C. A., Gwyther, D. E., and Blankenship, D. D.: Antarctic Mapping Tools for MATLAB, Comput. Geosci., 104, 151–157, https://doi.org/10.1016/j.cageo.2016.08.003, 2017.
He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for image recognition, P. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016.
Helly, J. J., Kaufmann, R. S., Stephenson, G. R., and Vernet, M.: Cooling, dilution and mixing of ocean water by free-drifting icebergs in the Weddell Sea, Deep-Sea Res. Pt. II, 58, 1346–1363, https://doi.org/10.1016/j.dsr2.2010.11.010, 2011.
Jansen, D., Schodlok, M., and Rack, W.: Basal melting of A-38B: A physical model constrained by satellite observations, Remote Sens. Environ., 111, 195–203, https://doi.org/10.1016/j.rse.2007.03.022, 2007.
Jenkins, A.: The impact of melting ice on ocean waters, J. Phys. Oceanogr., 29, 2370–2381, https://doi.org/10.1175/1520-0485(1999)029<2370:TIOMIO>2.0.CO;2, 1999.
Kingma, D. P. and Ba, J. L.: Adam: A method for stochastic optimization, 3rd Int. Conf. Learn. Represent, ICLR 2015 – Conf. Track Proc., 1–15, https://doi.org/10.48550/arXiv.1412.6980, 2015.
Koo, Y., Xie, H., Ackley, S. F., Mestas-Nuñez, A. M., Macdonald, G. J., and Hyun, C.-U.: Semi-automated tracking of iceberg B43 using Sentinel-1 SAR images via Google Earth Engine, The Cryosphere, 15, 4727–4744, https://doi.org/10.5194/tc-15-4727-2021, 2021.
Kucik, A. and Stokholm, A.: AI4SeaIce: selecting loss functions for automated SAR sea ice concentration charting, Sci. Rep., 13, 1–10, https://doi.org/10.1038/s41598-023-32467-x, 2023.
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015.
Macqueen, J.: Some methods for classification and analysis of multivariate observations, in: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, California, University of California Press, vol. 233, 281–297, 1967.
Mazur, A. K., Wåhlin, A. K., and Krężel, A.: An object-based SAR image iceberg detection algorithm applied to the Amundsen Sea, Remote Sens. Environ., 189, 67–83, https://doi.org/10.1016/j.rse.2016.11.013, 2017.
Merino, N., Le Sommer, J., Durand, G., Jourdain, N. C., Madec, G., Mathiot, P., and Tournadre, J.: Antarctic icebergs melt over the Southern Ocean: Climatology and impact on sea ice, Ocean Model., 104, 99–110, https://doi.org/10.1016/j.ocemod.2016.05.001, 2016.
Mohajerani, Y., Wood, M., Velicogna, I., and Rignot, E.: Detection of glacier calving margins with convolutional neural networks: A case study, Remote Sens., 11, 1–13, https://doi.org/10.3390/rs11010074, 2019.
Mohajerani, Y., Jeong, S., Scheuchl, B., Velicogna, I., Rignot, E., and Milillo, P.: Automatic delineation of glacier grounding lines in differential interferometric synthetic-aperture radar data using deep learning, Sci. Rep., 11, 1–10, https://doi.org/10.1038/s41598-021-84309-3, 2021.
Otsu, N.: A Threshold Selection Method from Gray-Level Histograms, IEEE Trans. Syst. Man. Cybern., 9, 62–66, https://doi.org/10.1109/TSMC.1979.4310076, 1979.
Poliyapram, V., Imamoglu, N., and Nakamura, R.: Deep learning model for water/ice/land classification using large-scale medium resolution satellite images, IGARSS 2019 – 2019 IEEE Int. Geosci. Remote Sens. Symp., 3884–3887, https://doi.org/10.1109/IGARSS.2019.8900323, 2019.
Power, D., Youden, J., Lane, K., Randell, C., and Flett, D.: Iceberg detection capabilities of radarsat synthetic aperture radar, Can. J. Remote Sens., 27, 476–486, https://doi.org/10.1080/07038992.2001.10854888, 2001.
Ronneberger, O., Fischer, P., and Brox, T.: U-net: Convolutional networks for biomedical image segmentation, Lect. Notes Comput. Sci., 9351, 234–241, https://doi.org/10.1007/978-3-319-24574-4_28, 2015.
Sandven, S., Babiker, M., and Kloster, K.: Iceberg observations in the barents sea by radar and optical satellite images, in: Proceedings of the Envisat Symposium, https://www.researchgate.net/profile/Mohamed-Babiker-5/publication/228876866 _Iceberg_observations_in_the_barents_sea_by_radar_and_optical _satellite_images/links/00463528471121848f000000/Iceberg-observations-in-the-barents-sea-by-radar-and-optical-satellite-images.pdf (last access: 1 December 2022), 2007.
Schmidhuber, J.: Deep Learning in neural networks: An overview, Neural Networks, 61, 85–117, https://doi.org/10.1016/j.neunet.2014.09.003, 2015.
Sephton, A. J., Brown, L. M., Macklin, J. T., Partington, K. C., Veck, N. J., and Rees, W. G.: Segmentation of synthetic-aperture radar imagery of sea ice, Int. J. Remote Sens., 15, 803–825, https://doi.org/10.1080/01431169408954118, 1994.
Silva, T. A. M. and Bigg, G. R.: Computer-based identification and tracking of Antarctic icebergs in SAR Computer-based identification and tracking of Antarctic icebergs in SAR images, Remote Sens. Environ., 94, 287–297, https://doi.org/10.1016/j.rse.2004.10.002, 2005.
Silva, T. A. M., Bigg, G. R., and Nicholls, K. W.: Contribution of giant icebergs to the Southern Ocean freshwater flux, J. Geophys. Res., 111, 1–8, https://doi.org/10.1029/2004JC002843, 2006.
Singh, A., Kalke, H., Loewen, M., and Ray, N.: River Ice Segmentation with Deep Learning, IEEE T. Geosci. Remote, 58, 7570–7579, https://doi.org/10.1109/TGRS.2020.2981082, 2020.
Smith, K. L., Robison, B. H., Helly, J. J., Kaufmann, R. S., Ruhl, H. A., Shaw, T. J., Twining, B. S., and Vernet, M.: Free-drifting icebergs: Hot spots of chemical and biological enrichment in the Weddell Sea, Science, 317, 478–482, https://doi.org/10.1126/science.1142834, 2007.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R.: Dropout: A simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., 15, 1929–1958, 2014.
Stokholm, A., Wulf, T., Kucik, A., Saldo, R., Buus-Hinkler, J., and Hvidegaard, S. M.: AI4SeaIce: Toward Solving Ambiguous SAR Textures in Convolutional Neural Networks for Automatic Sea Ice Concentration Charting, IEEE T. Geosci. Remote, 60, 4304013, https://doi.org/10.1109/TGRS.2022.3149323, 2022.
Surawy-Stepney, T., Hogg, A. E., Cornford, S. L., and Davison, B. J.: Episodic dynamic change linked to damage on the thwaites glacier ice tongue, Nat. Geosci., 16, 37–43, https://doi.org/10.1038/s41561-022-01097-9, 2023.
Torres, R., Snoeij, P., Geudtner, D., Bibby, D., Davidson, M., Attema, E., Potin, P., Rommen, B., Floury, N., Brown, M., Navas, I., Deghaye, P., Duesmann, B., Rosich, B., Miranda, N., Bruno, C., Abbate, M. L., Croci, R., Pietropaolo, A., Huchler, M. and Rostan, F.: GMES Sentinel-1 mission, Remote Sens. Environ., 120, 9–24, https://doi.org/10.1016/j.rse.2011.05.028, 2012.
Tournadre, J., Bouhier, N., Girard-Ardhuin, F., and Rémy, F.: Antarctic icebergs distributions 1992–2014, J. Geophys. Res.-Oceans, 121, 327–349, https://doi.org/10.1002/2015JC011178, 2016.
Ulaby, F. T. and Long, D. G.: Microwave radar and radiometric remote sensing, The University of Michigan Press, ISBN 978-0-472-11935-6, 2014.
Vernet, M., Smith, K. L., Cefarelli, A. O., Helly, J. J., Kaufmann, R. S., Lin, H., Long, D. G., Murray, A. E., Robison, B. H., Ruhl, H. A., Shaw, T. J., Sherman, A. D., Sprintall, J., Stephenson, G. R., Stuart, K. M., and Twining, B. S.: Islands of ice: Influence of free-drifting Antarctic icebergs on pelagic marine ecosystems, Oceanography, 25, 38–39, https://doi.org/10.5670/oceanog.2012.72, 2012.
Wesche, C. and Dierking, W.: Iceberg signatures and detection in SAR images in two test regions of the Weddell Sea, Antarctica, J. Glaciol., 58, 325–339, https://doi.org/10.3189/2012J0G11J020, 2012.
Wesche, C. and Dierking, W.: Near-coastal circum-Antarctic iceberg size distributions determined from Synthetic Aperture Radar images, Remote Sens. Environ., 156, 561–569, https://doi.org/10.1016/j.rse.2014.10.025, 2015.
Williams, R. N., Rees, W. G., and Young, N. W.: A technique for the identification and analysis of icebergs in synthetic aperture radar images of Antarctica, Int. J. Remote Sens., 20, 3183–3199, https://doi.org/10.1080/014311699211697, 1999.
Willis, C. J., Macklin, J. T., Partington, K. C., Teleki, K. A., Rees, W. G., and Williams, G.: Iceberg detection using ers-1 synthetic aperture radar, Int. J. Remote Sens., 17, 1777–1795, https://doi.org/10.1080/01431169608948739, 1996.
Young, N. W. and Hyland, G.: Applications of time series of microwave backscatter over the Antarctic region, in: Proceedings of the third ERS Scientic Symposium, 17–21 March 1997, Florence, Italy, Frascati, Italy, European Space Agency, SP-414, 1007–1014, ISBN 92-9092-656-2, 1997.
Young, N. W., Turner, D., Hyland, G., and Williams, R. N.: Near-coastal iceberg distributions in East Antarctica, 50–145∘ E, Ann. Glaciol., 27, 68–74, https://doi.org/10.3189/1998aog27-1-68-74, 1998.
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.
Short summary
In this study, we propose a deep neural network to map the extent of giant Antarctic icebergs in Sentinel-1 images automatically. While each manual delineation requires several minutes, our U-net takes less than 0.01 s. In terms of accuracy, we find that U-net outperforms two standard segmentation techniques (Otsu, k-means) in most metrics and is more robust to challenging scenes with sea ice, coast and other icebergs. The absolute median deviation in iceberg area across 191 images is 4.1 %.
In this study, we propose a deep neural network to map the extent of giant Antarctic icebergs in...
