Articles | Volume 16, issue 15
https://doi.org/10.5194/gmd-16-4521-2023
© 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/gmd-16-4521-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Automatic snow type classification of snow micropenetrometer profiles with machine learning algorithms
Julia Kaltenborn
CORRESPONDING AUTHOR
WSL Institute for Snow and
Avalanche Research SLF, Flüelastrasse 11, 7260 Davos Dorf, Switzerland
Institute of Cognitive Science, University Osnabrück, Wachsbleiche 27, 49090 Osnabrück, Germany
Mila – Quebec AI Institute, 6666 Rue Saint-Urbain, QC H2S 3H1, Montréal, Canada
School of Computer Science, McGill University, 3480 Rue University, QC H3A 2A7, Montréal, Canada
Amy R. Macfarlane
WSL Institute for Snow and
Avalanche Research SLF, Flüelastrasse 11, 7260 Davos Dorf, Switzerland
Viviane Clay
Institute of Cognitive Science, University Osnabrück, Wachsbleiche 27, 49090 Osnabrück, Germany
Numenta, 889 Winslow Street, Redwood City, CA 94063, USA
WSL Institute for Snow and
Avalanche Research SLF, Flüelastrasse 11, 7260 Davos Dorf, Switzerland
Related authors
No articles found.
Yubing Cheng, Bin Cheng, Roberta Pirazzini, Amy R. Macfarlane, Timo Vihma, Wolfgang Dorn, Ruzica Dadic, Martin Schneebeli, Stefanie Arndt, and Annette Rinke
EGUsphere, https://doi.org/10.5194/egusphere-2025-1164, https://doi.org/10.5194/egusphere-2025-1164, 2025
Short summary
Short summary
We study snow density from the MOSAiC expedition. Several snow density schemes were tested and compared with observation. A thermodynamic ice model was employed to assess the impact of snow density and precipitation on the thermal regime of sea ice. The parameterized mean snow densities are consistent with observations. Increased snow density reduces snow and ice temperatures, promoting ice growth, while increased precipitation leads to warmer snow and ice temperatures and reduced ice thickness.
Cecile B. Menard, Sirpa Rasmus, Ioanna Merkouriadi, Gianpaolo Balsamo, Annett Bartsch, Chris Derksen, Florent Domine, Marie Dumont, Dorothee Ehrich, Richard Essery, Bruce C. Forbes, Gerhard Krinner, David Lawrence, Glen Liston, Heidrun Matthes, Nick Rutter, Melody Sandells, Martin Schneebeli, and Sari Stark
The Cryosphere, 18, 4671–4686, https://doi.org/10.5194/tc-18-4671-2024, https://doi.org/10.5194/tc-18-4671-2024, 2024
Short summary
Short summary
Computer models, like those used in climate change studies, are written by modellers who have to decide how best to construct the models in order to satisfy the purpose they serve. Using snow modelling as an example, we examine the process behind the decisions to understand what motivates or limits modellers in their decision-making. We find that the context in which research is undertaken is often more crucial than scientific limitations. We argue for more transparency in our research practice.
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.
Moein Mellat, Amy R. Macfarlane, Camilla F. Brunello, Martin Werner, Martin Schneebeli, Ruzica Dadic, Stefanie Arndt, Kaisa-Riikka Mustonen, Jeffrey M. Welker, and Hanno Meyer
EGUsphere, https://doi.org/10.5194/egusphere-2024-719, https://doi.org/10.5194/egusphere-2024-719, 2024
Preprint archived
Short summary
Short summary
Our research, utilizing data from the Arctic MOSAiC expedition, reveals how snow on Arctic sea ice changes due to weather conditions. By analyzing snow samples collected over a year, we found differences in snow layers that tell us about their origins and how they've been affected by the environment. We discovered variations in snow and vapour that reflect the influence of weather patterns and surface processes like wind and sublimation.
Amy R. Macfarlane, Henning Löwe, Lucille Gimenes, David N. Wagner, Ruzica Dadic, Rafael Ottersberg, Stefan Hämmerle, and Martin Schneebeli
The Cryosphere, 17, 5417–5434, https://doi.org/10.5194/tc-17-5417-2023, https://doi.org/10.5194/tc-17-5417-2023, 2023
Short summary
Short summary
Snow acts as an insulating blanket on Arctic sea ice, keeping the underlying ice "warm", relative to the atmosphere. Knowing the snow's thermal conductivity is essential for understanding winter ice growth. During the MOSAiC expedition, we measured the thermal conductivity of snow. We found spatial and vertical variability to overpower any temporal variability or dependency on underlying ice type and the thermal resistance to be directly influenced by snow height.
Baptiste Vandecrux, Jason E. Box, Andreas P. Ahlstrøm, Signe B. Andersen, Nicolas Bayou, William T. Colgan, Nicolas J. Cullen, Robert S. Fausto, Dominik Haas-Artho, Achim Heilig, Derek A. Houtz, Penelope How, Ionut Iosifescu Enescu, Nanna B. Karlsson, Rebecca Kurup Buchholz, Kenneth D. Mankoff, Daniel McGrath, Noah P. Molotch, Bianca Perren, Maiken K. Revheim, Anja Rutishauser, Kevin Sampson, Martin Schneebeli, Sandy Starkweather, Simon Steffen, Jeff Weber, Patrick J. Wright, Henry Jay Zwally, and Konrad Steffen
Earth Syst. Sci. Data, 15, 5467–5489, https://doi.org/10.5194/essd-15-5467-2023, https://doi.org/10.5194/essd-15-5467-2023, 2023
Short summary
Short summary
The Greenland Climate Network (GC-Net) comprises stations that have been monitoring the weather on the Greenland Ice Sheet for over 30 years. These stations are being replaced by newer ones maintained by the Geological Survey of Denmark and Greenland (GEUS). The historical data were reprocessed to improve their quality, and key information about the weather stations has been compiled. This augmented dataset is available at https://doi.org/10.22008/FK2/VVXGUT (Steffen et al., 2022).
Marie Dumont, Simon Gascoin, Marion Réveillet, Didier Voisin, François Tuzet, Laurent Arnaud, Mylène Bonnefoy, Montse Bacardit Peñarroya, Carlo Carmagnola, Alexandre Deguine, Aurélie Diacre, Lukas Dürr, Olivier Evrard, Firmin Fontaine, Amaury Frankl, Mathieu Fructus, Laure Gandois, Isabelle Gouttevin, Abdelfateh Gherab, Pascal Hagenmuller, Sophia Hansson, Hervé Herbin, Béatrice Josse, Bruno Jourdain, Irene Lefevre, Gaël Le Roux, Quentin Libois, Lucie Liger, Samuel Morin, Denis Petitprez, Alvaro Robledano, Martin Schneebeli, Pascal Salze, Delphine Six, Emmanuel Thibert, Jürg Trachsel, Matthieu Vernay, Léo Viallon-Galinier, and Céline Voiron
Earth Syst. Sci. Data, 15, 3075–3094, https://doi.org/10.5194/essd-15-3075-2023, https://doi.org/10.5194/essd-15-3075-2023, 2023
Short summary
Short summary
Saharan dust outbreaks have profound effects on ecosystems, climate, health, and the cryosphere, but the spatial deposition pattern of Saharan dust is poorly known. Following the extreme dust deposition event of February 2021 across Europe, a citizen science campaign was launched to sample dust on snow over the Pyrenees and the European Alps. This campaign triggered wide interest and over 100 samples. The samples revealed the high variability of the dust properties within a single event.
Vishnu Nandan, Rosemary Willatt, Robbie Mallett, Julienne Stroeve, Torsten Geldsetzer, Randall Scharien, Rasmus Tonboe, John Yackel, Jack Landy, David Clemens-Sewall, Arttu Jutila, David N. Wagner, Daniela Krampe, Marcus Huntemann, Mallik Mahmud, David Jensen, Thomas Newman, Stefan Hendricks, Gunnar Spreen, Amy Macfarlane, Martin Schneebeli, James Mead, Robert Ricker, Michael Gallagher, Claude Duguay, Ian Raphael, Chris Polashenski, Michel Tsamados, Ilkka Matero, and Mario Hoppmann
The Cryosphere, 17, 2211–2229, https://doi.org/10.5194/tc-17-2211-2023, https://doi.org/10.5194/tc-17-2211-2023, 2023
Short summary
Short summary
We show that wind redistributes snow on Arctic sea ice, and Ka- and Ku-band radar measurements detect both newly deposited snow and buried snow layers that can affect the accuracy of snow depth estimates on sea ice. Radar, laser, meteorological, and snow data were collected during the MOSAiC expedition. With frequent occurrence of storms in the Arctic, our results show that
wind-redistributed snow needs to be accounted for to improve snow depth estimates on sea ice from satellite radars.
Julia Martin and Martin Schneebeli
The Cryosphere, 17, 1723–1734, https://doi.org/10.5194/tc-17-1723-2023, https://doi.org/10.5194/tc-17-1723-2023, 2023
Short summary
Short summary
The grain size of snow determines how light is reflected and other physical properties. The IceCube measures snow grain size at the specific near-infrared wavelength of 1320 nm. In our study, the preparation of snow samples for the IceCube creates a thin layer of small particles. Comparisons of the grain size with computed tomography, particle counting and numerical simulation confirm the aforementioned observation. We conclude that measurements at this wavelength underestimate the grain size.
Julienne Stroeve, Vishnu Nandan, Rosemary Willatt, Ruzica Dadic, Philip Rostosky, Michael Gallagher, Robbie Mallett, Andrew Barrett, Stefan Hendricks, Rasmus Tonboe, Michelle McCrystall, Mark Serreze, Linda Thielke, Gunnar Spreen, Thomas Newman, John Yackel, Robert Ricker, Michel Tsamados, Amy Macfarlane, Henna-Reetta Hannula, and Martin Schneebeli
The Cryosphere, 16, 4223–4250, https://doi.org/10.5194/tc-16-4223-2022, https://doi.org/10.5194/tc-16-4223-2022, 2022
Short summary
Short summary
Impacts of rain on snow (ROS) on satellite-retrieved sea ice variables remain to be fully understood. This study evaluates the impacts of ROS over sea ice on active and passive microwave data collected during the 2019–20 MOSAiC expedition. Rainfall and subsequent refreezing of the snowpack significantly altered emitted and backscattered radar energy, laying important groundwork for understanding their impacts on operational satellite retrievals of various sea ice geophysical variables.
Océane Hames, Mahdi Jafari, David Nicholas Wagner, Ian Raphael, David Clemens-Sewall, Chris Polashenski, Matthew D. Shupe, Martin Schneebeli, and Michael Lehning
Geosci. Model Dev., 15, 6429–6449, https://doi.org/10.5194/gmd-15-6429-2022, https://doi.org/10.5194/gmd-15-6429-2022, 2022
Short summary
Short summary
This paper presents an Eulerian–Lagrangian snow transport model implemented in the fluid dynamics software OpenFOAM, which we call snowBedFoam 1.0. We apply this model to reproduce snow deposition on a piece of ridged Arctic sea ice, which was produced during the MOSAiC expedition through scan measurements. The model appears to successfully reproduce the enhanced snow accumulation and deposition patterns, although some quantitative uncertainties were shown.
David N. Wagner, Matthew D. Shupe, Christopher Cox, Ola G. Persson, Taneil Uttal, Markus M. Frey, Amélie Kirchgaessner, Martin Schneebeli, Matthias Jaggi, Amy R. Macfarlane, Polona Itkin, Stefanie Arndt, Stefan Hendricks, Daniela Krampe, Marcel Nicolaus, Robert Ricker, Julia Regnery, Nikolai Kolabutin, Egor Shimanshuck, Marc Oggier, Ian Raphael, Julienne Stroeve, and Michael Lehning
The Cryosphere, 16, 2373–2402, https://doi.org/10.5194/tc-16-2373-2022, https://doi.org/10.5194/tc-16-2373-2022, 2022
Short summary
Short summary
Based on measurements of the snow cover over sea ice and atmospheric measurements, we estimate snowfall and snow accumulation for the MOSAiC ice floe, between November 2019 and May 2020. For this period, we estimate 98–114 mm of precipitation. We suggest that about 34 mm of snow water equivalent accumulated until the end of April 2020 and that at least about 50 % of the precipitated snow was eroded or sublimated. Further, we suggest explanations for potential snowfall overestimation.
Sönke Maus, Martin Schneebeli, and Andreas Wiegmann
The Cryosphere, 15, 4047–4072, https://doi.org/10.5194/tc-15-4047-2021, https://doi.org/10.5194/tc-15-4047-2021, 2021
Short summary
Short summary
As the hydraulic permeability of sea ice is difficult to measure, observations are sparse. The present work presents numerical simulations of the permeability of young sea ice based on a large set of 3D X-ray tomographic images. It extends the relationship between permeability and porosity available so far down to brine porosities near the percolation threshold of a few per cent. Evaluation of pore scales and 3D connectivity provides novel insight into the percolation behaviour of sea ice.
Julienne Stroeve, Vishnu Nandan, Rosemary Willatt, Rasmus Tonboe, Stefan Hendricks, Robert Ricker, James Mead, Robbie Mallett, Marcus Huntemann, Polona Itkin, Martin Schneebeli, Daniela Krampe, Gunnar Spreen, Jeremy Wilkinson, Ilkka Matero, Mario Hoppmann, and Michel Tsamados
The Cryosphere, 14, 4405–4426, https://doi.org/10.5194/tc-14-4405-2020, https://doi.org/10.5194/tc-14-4405-2020, 2020
Short summary
Short summary
This study provides a first look at the data collected by a new dual-frequency Ka- and Ku-band in situ radar over winter sea ice in the Arctic Ocean. The instrument shows potential for using both bands to retrieve snow depth over sea ice, as well as sensitivity of the measurements to changing snow and atmospheric conditions.
Jacinta Edebeli, Jürg C. Trachsel, Sven E. Avak, Markus Ammann, Martin Schneebeli, Anja Eichler, and Thorsten Bartels-Rausch
Atmos. Chem. Phys., 20, 13443–13454, https://doi.org/10.5194/acp-20-13443-2020, https://doi.org/10.5194/acp-20-13443-2020, 2020
Short summary
Short summary
Earth’s snow cover is very dynamic and can change its physical properties within hours, as is well known by skiers. Snow is also a well-known host of chemical reactions – the products of which impact air composition and quality. Here, we present laboratory experiments that show how the dynamics of snow make snow essentially inert with respect to gas-phase ozone with time despite its content of reactive chemicals. Impacts on polar atmospheric chemistry are discussed.
Cited articles
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado,
G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp,
A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M.,
Levenberg, J., Mane, D., Monga, R., Moore, S., Murray, D., Olah, C.,
Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P.,
Vanhoucke, V., Vasudevan, V., Viegas, F., Vinyals, O., Warden, P.,
Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X.: TensorFlow:
Large-Scale Machine Learning on Heterogeneous Distributed
Systems, arXiv [preprint], https://doi.org/10.48550/arXiv.1603.04467, 2016. a
Bahdanau, D., Cho, K., and Bengio, Y.: Neural Machine Translation by Jointly
Learning to Align and Translate, arXiv [preprint], https://doi.org/10.48550/ARXIV.1409.0473, 2014. a
Breiman, L.: Random forests, Mach. Learn., 45, 5–32,
https://doi.org/10.1023/A:1010933404324, 2001. a
Calonne, N., Richter, B., Löwe, H., Cetti, C., ter Schure, J., Van Herwijnen, A., Fierz, C., Jaggi, M., and Schneebeli, M.: The RHOSSA campaign: multi-resolution monitoring of the seasonal evolution of the structure and mechanical stability of an alpine snowpack, The Cryosphere, 14, 1829–1848, https://doi.org/10.5194/tc-14-1829-2020, 2020. a
Chao, C., Liaw, A., and Breiman, L.: Using random forest to learn imbalanced
data, Tech. Reports 666, University of California, Dep. Statistics,
Berkeley, https://statistics.berkeley.edu/tech-reports/666 (last access: 3 August 2023),
2004. a
Chollet, F. et al.: Keras, GitHub, https://github.com/fchollet/keras (last access: 3 August 2023), 2015. a
Colbeck, S.: A review of the metamorphism and classification of seasonal snow
cover crystals, IAHS Publication, 162, 3–24,
https://iahs.info/uploads/dms/6807.3-34-162-Colbeck.pdf,
1987. a
Coléou, C., Lesaffre, B., Brzoska, J.-B., Ludwig, W., and Boller, E.:
Three-dimensional snow images by X-ray microtomography, Ann.
Glaciol., 32, 75–81, https://doi.org/10.3189/172756401781819418, 2001. a
Cortes, C. and Vapnik, V.: Support-vector networks, Mach. Learn., 20,
273–297, https://doi.org/10.1007/BF00994018, 1995. a
Cover, T. and Hart, P.: Nearest neighbor pattern classification, IEEE
Transactions on Information Theory, 13, 21–27,
https://doi.org/10.1109/TIT.1967.1053964, 1967. a
CyberZHG: Keras Self-Attention, GitHub,
https://github.com/CyberZHG/keras-self-attention (last access: 3 August 2023), 2020. a
Domine, F., Picard, G., Morin, S., Barrere, M., Madore, J.-B., and Langlois,
A.: Major Issues in Simulating Some Arctic Snowpack Properties
Using Current Detailed Snow Physics Models: Consequences for
the Thermal Regime and Water Budget of Permafrost, J.
Adv. Model. Earth Syst., 11, 34–44, https://doi.org/10.1029/2018MS001445,
2019. a
Douville, H., Royer, J. F., and Mahfouf, J. F.: A new snow parameterization for
the Météo-France climate model, Clim. Dynam., 12, 21–35,
https://doi.org/10.1007/BF00208760, 1995. a
Fierz, C., Armstrong, R., Durand, Y., Etchevers, P., Greene, E., Mcclung,
D. M., Nishimura, K., Satyawali, P., and Sokratov, S.: The international
classification for seasonal snow on the ground, Tech. rep., UNESCO-IHP,
Paris, Paris, publication Title: IHP-VII Technical Documents in Hydrology
No. 83, IACS Contribution No. 1, 2009. a, b, c, d, e, f, g, h, i, j, k
Fix, E. and Hodges, J. L.: Discriminatory Analysis - Nonparametric
Discrimination: Small Sample Performance, Tech. rep., California
University Berkeley,
https://apps.dtic.mil/sti/citations/ADA800391 (last access: 3 August 2023), section:
Technical Reports, 1952. a
Forgy, E. W.: Cluster analysis of multivariate data: efficiency versus
interpretability of classifications, Biometrics, 21, 768–769, 1965. a
Ghahramani, Z.: Unsupervised Learning, pp. 72–112, Springer Berlin Heidelberg,
Berlin, Heidelberg, https://doi.org/10.1007/978-3-540-28650-9_5, 2004. a
Han, J., Kamber, M., and Pei, J.: 9 – Classification: Advanced Methods, in:
Data Mining (Third Edition), edited by: Han, J., Kamber, M., and Pei, J., The
Morgan Kaufmann Series in Data Management Systems, pp. 393–442, Morgan
Kaufmann, Boston, third edition edn.,
https://doi.org/10.1016/B978-0-12-381479-1.00009-5, 2012. a
Havens, S., Marshall, H.-P., Steiner, N., and Tedesco, M.: Snow micro
penetrometer and near infrared photography for grain type classification, in:
2010 International Snow Science Workshop, pp. 465–469,
https://arc.lib.montana.edu/snow-science/objects/ISSW_P-029.pdf (last access: 3 August 2023),
2010. a, b
Herla, F., Horton, S., Mair, P., and Haegeli, P.: Snow profile alignment and similarity assessment for aggregating, clustering, and evaluating snowpack model output for avalanche forecasting, Geosci. Model Dev., 14, 239–258, https://doi.org/10.5194/gmd-14-239-2021, 2021. a
Ho, T. K.: Random decision forests, in: Proceedings of 3rd international
conference on document analysis and recognition, vol. 1, pp. 278–282, IEEE,
1995. a
Hochreiter, S. and Schmidhuber, J.: Long short-term memory,
Neural Computat.,
9, 1735–1780, 1997. a
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., and Muller, P.-A.:
Deep learning for time series classification: a review, Data Min. Knowl. Disc., 33, 917–963, https://doi.org/10.1007/s10618-019-00619-1, 2019. a
Johnson, J. B. and Schneebeli, M.: Snow strength penetrometer,
https://patents.google.com/patent/US5831161/en (last access: 3 August 2023), 1998. a
Kaltenborn, J. and vclay: liellnima/snowdragon: Snowdragon Release 1.0.0 (v1.0.0), Zenodo [code], https://doi.org/10.5281/zenodo.7335813, 2022. a
Kaltenborn, J., Clay, V., Macfarlane, A. R., and Schneebeli, M.: Machine
Learning for Snow Stratigraphy Classification, in: NeurIPS 2021 Workshop on
Tackling Climate Change with Machine Learning,
https://www.climatechange.ai/papers/neurips2021/48 (last access: 3 August 2023), 2021. a
Kaltenborn, J., Macfarlane, A. R., Clay, V., and Schneebeli, M.: Pre-trained
Models for SMP Classification and Segmentation, Zenodo [code], https://doi.org/10.5281/zenodo.7063521,
2022. a
King, J., Kelly, R., Kasurak, A., Duguay, C., Gunn, G., Rutter, N., Watts, T.,
and Derksen, C.: Spatio-temporal influence of tundra snow properties on
Ku-band (17.2 GHz) backscatter, J. Glaciol., 61, 267–279,
https://doi.org/10.3189/2015JoG14J020, 2015. a, b
King, J., Howell, S., Brady, M., Toose, P., Derksen, C., Haas, C., and Beckers, J.: Local-scale variability of snow density on Arctic sea ice, The Cryosphere, 14, 4323–4339, https://doi.org/10.5194/tc-14-4323-2020, 2020a. a, b, c, d
King, J., Howell, S., Brady, M., Toose, P., Derksen, C., Haas, C., and Beckers,
J.: SnowMicroPen Measurements on Sea Ice 2016–2017, Zenodo,
https://doi.org/10.5281/zenodo.4068349, 2020b. a
Knust, R.: Polar Research and Supply Vessel POLARSTERN Operated by
the Alfred-Wegener-Institute, Journal of Large-Scale Research
Facilities, 3, A119–A119, https://doi.org/10.17815/jlsrf-3-163, 2017. a
Lemaître, G., Nogueira, F., and Aridas, C. K.: Imbalanced-learn: A python
toolbox to tackle the curse of imbalanced datasets in machine learning,
J. Mach. Learn. Res., 18, 559–563,
https://www.jmlr.org/papers/volume18/16-365/16-365.pdf (last access: 3 August 2023), 2017. a
Li, D., Hasanaj, E., and Li, S.: 3 – Baselines,
https://blog.ml.cmu.edu/2020/08/31/3-baselines/ (last access:
4 March 2021), 2020. a
Light, B., Perovich, D. K., Webster, M. A., Polashenski, C., and Dadic, R.:
Optical properties of melting first-year Arctic sea ice, J.
Geophys. Res.-Oceans, 120, 7657–7675, https://doi.org/10.1002/2015JC011163,
2015. a
Liu, X.-Y., Wu, J., and Zhou, Z.-H.: Exploratory undersampling for
class-imbalance learning, IEEE Transactions on Systems, Man, and Cybernetics,
Part B (Cybernetics), 39, 539–550, https://doi.org/10.1109/TSMCB.2008.2007853, 2008. a
Lloyd, S.: Least squares quantization in PCM, IEEE Transactions on Information
Theory, 28, 129–137, https://doi.org/10.1109/TIT.1982.1056489, 1982. a
Löwe, H. and Van Herwijnen, A.: A Poisson shot noise model for
micro-penetration of snow, Cold Reg. Sci. Technol., 70, 62–70,
https://doi.org/10.1016/j.coldregions.2011.09.001, 2012. a
Lutz, E., Birkeland, K. W., Kronholm, K., Hansen, K., and Aspinall, R.: Surface
hoar characteristics derived from a snow micropenetrometer using moving
window statistical operations, Cold Reg. Sci. Technol., 47,
118–133, https://doi.org/10.1016/j.coldregions.2006.08.021, 2007. a
Macfarlane, A., Schneebeli, M., Dadic, R., Tavri, A., Immerz, A., Polashenski,
C., Krampe, D., Clemens-Sewall, D., Wagner, D., Perovich, D., Henna-Reetta,
H., Raphael, I., Matero, I., Regnery, J., Smith, M., Nicolaus, M., Jaggi, M.,
Oggier, M., Webster, M., Lehning, M., Kolabutin, N., Itkin, P., Naderpour,
R., Pirazzini, R., Hammerle, S., Arndt, S., and Fons, S.: A Database of Snow
on Sea Ice in the Central Arctic Collected during the MOSAiC expedition,
Scientific Data, 10, 398, https://doi.org/10.1038/s41597-023-02273-1, 2023. a
Macfarlane, A. R., Schneebeli, M., Dadic, R., Wagner, D. N., Arndt,
S., Clemens-Sewall, D., Hämmerle, S., Hannula, H.-R., Jaggi, M.,
Kolabutin, N., Krampe, D., Lehning, M., Matero, I., Nicolaus, M.,
Oggier, M., Pirazzini, R., Polashenski, C., Raphael, I., Regnery,
J., Shimanchuck, E., Smith, M. M., and Tavri, A.: Snowpit SnowMicroPen
(SMP) force profiles collected during the MOSAiC expedition, PANGAEA [data set],
https://doi.org/10.1594/PANGAEA.935554, 2021. a, b, c
Matzl, M. and Schneebeli, M.: Measuring specific surface area of snow by
near-infrared photography, J. Glaciol., 52, 558–564,
https://doi.org/10.3189/172756506781828412, 2006. a
Ménard, C. B., Essery, R., Barr, A., Bartlett, P., Derry, J., Dumont, M., Fierz, C., Kim, H., Kontu, A., Lejeune, Y., Marks, D., Niwano, M., Raleigh, M., Wang, L., and Wever, N.: Meteorological and evaluation datasets for snow modelling at 10 reference sites: description of in situ and bias-corrected reanalysis data, Earth Syst. Sci. Data, 11, 865–880, https://doi.org/10.5194/essd-11-865-2019, 2019. a
Merkouriadi, I., Gallet, J.-C., Graham, R. M., Liston, G. E., Polashenski, C.,
Rösel, A., and Gerland, S.: Winter snow conditions on Arctic sea ice
north of Svalbard during the Norwegian young sea ICE (N-ICE2015) expedition,
J. Geophys. Res.-Atmos., 122, 10–837,
https://doi.org/10.1002/2016JD026035, 2017. a
Nguyen, N. and Guo, Y.: Comparisons of sequence labeling algorithms and
extensions, in: Proceedings of the 24th International Conference on Machine
Learning, pp. 681–688, https://doi.org/10.1145/1273496.1273582, 2007. a
Nicolaus, M., Perovich, D. K., Spreen, G., Granskog, M. A., von Albedyll, L.,
Angelopoulos, M., Anhaus, P., Arndt, S., Belter, H. J., Bessonov, V.,
Birnbaum, G., Brauchle, J., Calmer, R., Cardellach, E., Cheng, B.,
Clemens-Sewall, D., Dadic, R., Damm, E., de Boer, G., Demir, O., Dethloff,
K., Divine, D. V., Fong, A. A., Fons, S., Frey, M. M., Fuchs, N., Gabarró,
C., Gerland, S., Goessling, H. F., Gradinger, R., Haapala, J., Haas, C.,
Hamilton, J., Hannula, H.-R., Hendricks, S., Herber, A., Heuzé, C.,
Hoppmann, M., Høyland, K. V., Huntemann, M., Hutchings, J. K., Hwang, B.,
Itkin, P., Jacobi, H.-W., Jaggi, M., Jutila, A., Kaleschke, L., Katlein, C.,
Kolabutin, N., Krampe, D., Kristensen, S. S., Krumpen, T., Kurtz, N.,
Lampert, A., Lange, B. A., Lei, R., Light, B., Linhardt, F., Liston, G. E.,
Loose, B., Macfarlane, A. R., Mahmud, M., Matero, I. O., Maus, S.,
Morgenstern, A., Naderpour, R., Nandan, V., Niubom, A., Oggier, M., Oppelt,
N., Pätzold, F., Perron, C., Petrovsky, T., Pirazzini, R., Polashenski, C.,
Rabe, B., Raphael, I. A., Regnery, J., Rex, M., Ricker, R., Riemann-Campe,
K., Rinke, A., Rohde, J., Salganik, E., Scharien, R. K., Schiller, M.,
Schneebeli, M., Semmling, M., Shimanchuk, E., Shupe, M. D., Smith, M. M.,
Smolyanitsky, V., Sokolov, V., Stanton, T., Stroeve, J., Thielke, L.,
Timofeeva, A., Tonboe, R. T., Tavri, A., Tsamados, M., Wagner, D. N.,
Watkins, D., Webster, M., and Wendisch, M.: Overview of the MOSAiC
expedition: Snow and sea ice, Elementa: Science of the Anthropocene, 10,
https://doi.org/10.1525/elementa.2021.000046, 2022. a
Nixdorf, U., Dethloff, K., Rex, M., Shupe, M., Sommerfeld, A., Perovich, D. K.,
Nicolaus, M., Heuzé, C., Rabe, B., Loose, B., Damm, E., Gradinger, R., Fong,
A., Maslowski, W., Rinke, A., Kwok, R., Spreen, G., Wendisch, M., Herber, A.,
Hirsekorn, M., Mohaupt, V., Frickenhaus, S., Immerz, A., Weiss-Tuider, K.,
König, B., Mengedoht, D., Regnery, J., Gerchow, P., Ransby, D., Krumpen, T.,
Morgenstern, A., Haas, C., Kanzow, T., Rack, F. R., Saitzev, V., Sokolov, V.,
Makarov, A., Schwarze, S., Wunderlich, T., Wurr, K., and Boetius, A.: MOSAiC
Extended Acknowledgement, Zenodo, https://doi.org/10.5281/zenodo.5541624, 2021. a
IPCC: The Ocean and Cryosphere in a Changing
Climate: Special Report of the Intergovernmental Panel on Climate
Change, Cambridge University Press, Cambridge, https://doi.org/10.1017/9781009157964,
2022. a
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel,
O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J.,
Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Édouard
Duchesnay: Scikit-learn: Machine Learning in Python, J. Mach.
Learn. Res., 12, 2825–2830,
http://jmlr.org/papers/v12/pedregosa11a.html (last access: 3 August 2023), 2011. a, b, c
Pfeffer, W. T. and Mrugala, R.: Temperature gradient and initial snow density
as controlling factors in the formation and structure of hard depth hoar,
J. Glaciol., 48, 485–494, https://doi.org/10.3189/172756502781831098, 2002. a
Proksch, M., Löwe, H., and Schneebeli, M.: Density, specific surface area,
and correlation length of snow measured by high-resolution penetrometry,
J. Geophys. Res.-Ea. Surf., 120, 346–362,
https://doi.org/10.1002/2014JF003266, 2015. a
Rinke, A., Cassano, J. J., Cassano, E. N., Jaiser, R., and Handorf, D.:
Meteorological conditions during the MOSAiC expedition: Normal or
anomalous?, Elementa: Science of the Anthropocene, 9, 00023,
https://doi.org/10.1525/elementa.2021.00023, 2021. a
Russell, S. J. and Norvig, P.: Artificial intelligence: a modern approach,
Pearson series in artificial intelligence, Pearson, Hoboken, fourth edition
edn., 1136 pp., ISBN 978-0-13-461099-3, 2021. a
Sandells, M., Rutter, N., Wivell, K., Essery, R., Fox, S., Harlow, C., Picard, G., Roy, A., Royer, A., and Toose, P.: Simulation of Arctic snow microwave emission in surface-sensitive atmosphere channels, EGUsphere [preprint], https://doi.org/10.5194/egusphere-2023-696, 2023. a
Schneebeli, M., Pielmeier, C., and Johnson, J. B.: Measuring snow
microstructure and hardness using a high resolution penetrometer, Cold
Reg. Sci. Technol., 30, 101–114,
https://doi.org/10.1016/S0165-232X(99)00030-0, 1999. a
Schölkopf, B. and Smola, A. J.: Learning with kernels:
support vector machines, regularization, optimization, and beyond, MIT press, 626 pp.,
ISBN 0-262-19475-9,
2002. a
Schuster, M. and Paliwal, K. K.: Bidirectional recurrent neural networks, IEEE
transactions on Signal Processing, 45, 2673–2681, https://doi.org/10.1109/78.650093,
1997. a
Soni, R. and Mathai, K. J.: Improved Twitter Sentiment Prediction through
Cluster-then-Predict Model, arXiv [preprint],
https://doi.org/10.48550/arXiv.1509.02437, 2015. a
Steger, C., Kotlarski, S., Jonas, T., and Schär, C.: Alpine snow cover in a
changing climate: a regional climate model perspective, Clim. Dynam., 41,
735–754, https://doi.org/10.1007/s00382-012-1545-3, 2013. a
Stone, M.: Cross-validatory choice and assessment of statistical predictions,
J. R. Stat. Soc. B, 36,
111–133, https://doi.org/10.1111/j.2517-6161.1974.tb00994.x, 1974. a
Sturm, M. and Liston, G. E.: Revisiting the Global Seasonal Snow
Classification: An Updated Dataset for Earth System
Applications, J. Hydrometeorol., 22, 2917–2938,
https://doi.org/10.1175/JHM-D-21-0070.1, 2021. a
Sturm, M. and Massom, R. A.: Snow in the sea ice system: friend or foe?, in:
Sea Ice, John Wiley & Sons, Ltd, pp. 65–109, section: 3,
https://doi.org/10.1002/9781118778371.ch3, 2017. a
Theodorou, T., Mporas, I., and Fakotakis, N.: An Overview of Automatic Audio
Segmentation, International Journal of Information Technology and Computer
Science, 6, 1–9, https://doi.org/10.5815/ijitcs.2014.11.01, 2014. a
Trivedi, S., Pardos, Z. A., and Heffernan, N. T.: The Utility of Clustering
in Prediction Tasks, arXiv [preprint], https://doi.org/10.48550/arXiv.1509.06163, 2015. a
Vionnet, V., Brun, E., Morin, S., Boone, A., Faroux, S., Le Moigne, P., Martin, E., and Willemet, J.-M.: The detailed snowpack scheme Crocus and its implementation in SURFEX v7.2, Geosci. Model Dev., 5, 773–791, https://doi.org/10.5194/gmd-5-773-2012, 2012. a
Wever, N., Keenan, E., Kausch, T., and Lehning, M.: SnowMicroPen measurements
and manual snowpits from Dronning Maud Land, East Antarctica, EnviDat,
https://doi.org/10.16904/envidat.331, 2022. a
Wu, X., Kumar, V., Ross Quinlan, J., Ghosh, J., Yang, Q., Motoda, H., McLachlan, G. J., Ng, A., Liu, B., Yu, P. S., Zhou, Z.-H., Steinbach, M., Hand, D. J., and Steinberg, D.: Top 10 algorithms in data
mining, Knowl. Inf. Syst., 14, 1–37,
https://doi.org/10.1007/s10115-007-0114-2, 2008.
a
Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised
methods, in: 33rd annual meeting of the association for computational
linguistics, pp. 189–196, https://doi.org/10.3115/981658.981684, 1995. a
Yoshua, B., Olivier, D., and Nicolas Le, R.: 192193Label Propagation and
Quadratic Criterion, in: Semi-Supervised Learning, The MIT Press,
https://doi.org/10.7551/mitpress/9780262033589.003.0011, 2006. a
Zhou, D., Bousquet, O., Lal, T., Weston, J., and Schölkopf, B.: Learning with
Local and Global Consistency, in: Advances in Neural Information
Processing Systems, edited by: Thrun, S., Saul, L., and Schölkopf, B.,
vol. 16, pp. 321–328, MIT Press,
https://proceedings.neurips.cc/paper_files/paper/2003/file/87682805257e619d49b8e0dfdc14affa-Paper.pdf (last access: 3 August 2023),
2003. a
Zhu, X. and Ghahramani, Z.: Learning from labeled and unlabeled data with label
propagation, Tech. rep., Carnegie Mellon University,
https://mlg.eng.cam.ac.uk/zoubin/papers/CMU-CALD-02-107.pdf (last access: 3 August 2023),
2002. a
Short summary
Snow layer segmentation and snow grain classification are essential diagnostic tasks for cryospheric applications. A SnowMicroPen (SMP) can be used to that end; however, the manual classification of its profiles becomes infeasible for large datasets. Here, we evaluate how well machine learning models automate this task. Of the 14 models trained on the MOSAiC SMP dataset, the long short-term memory model performed the best. The findings presented here facilitate and accelerate SMP data analysis.
Snow layer segmentation and snow grain classification are essential diagnostic tasks for...