Articles | Volume 12, issue 3
https://doi.org/10.5194/esurf-12-801-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/esurf-12-801-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
10 Jun 2024
Research article |
| 10 Jun 2024
| 10 Jun 2024
A machine learning approach to the geomorphometric detection of ribbed moraines in Norway
Thomas J. Barnes
CORRESPONDING AUTHOR
Department of Geosciences, University of Oslo, 0316 Oslo, Norway
Thomas V. Schuler
Department of Geosciences, University of Oslo, 0316 Oslo, Norway
Simon Filhol
Department of Geosciences, University of Oslo, 0316 Oslo, Norway
Karianne S. Lilleøren
Department of Geosciences, University of Oslo, 0316 Oslo, Norway
Related authors
No articles found.
Henning Åkesson, Kamilla Hauknes Sjursen, Thomas Vikhamar Schuler, Thorben Dunse, Liss Marie Andreassen, Mette Kusk Gillespie, Benjamin Aubrey Robson, Thomas Schellenberger, and Jacob Clement Yde
The Cryosphere, 19, 5871–5902, https://doi.org/10.5194/tc-19-5871-2025, https://doi.org/10.5194/tc-19-5871-2025, 2025
Short summary
Short summary
We model the historical and future evolution of the Jostedalsbreen ice cap in Norway, projecting substantial and largely irreversible mass loss for the 21st century, and that the ice cap will split into three parts. Further mass loss is in the pipeline, with a disappearance during the 22nd century under high emissions. Our study demonstrates an approach to model complex ice masses, highlights uncertainties due to precipitation, and calls for further research on long-term future glacier change.
Alexandru Onaca, Flavius Sîrbu, Valentin Poncoş, Christin Hilbich, Tazio Strozzi, Petru Urdea, Răzvan Popescu, Oana Berzescu, Bernd Etzelmüller, Alfred Vespremeanu-Stroe, Mirela Vasile, Delia Teleagă, Dan Birtaş, Iosif Lopătiţă, Simon Filhol, Alexandru Hegyi, and Florina Ardelean
Earth Surf. Dynam., 13, 981–1001, https://doi.org/10.5194/esurf-13-981-2025, https://doi.org/10.5194/esurf-13-981-2025, 2025
Short summary
Short summary
This study establishes a methodology for the study of slow-moving rock glaciers in marginal permafrost and provides the basic knowledge for understanding rock glaciers in South East Europe. By using a combination of different methods (remote sensing, geophysical survey, thermal measurements), we found out that, on the transitional rock glaciers, low ground ice content (i.e. below 20 %) produces horizontal displacements of up to 3 cm per year.
Thomas James Barnes, Thomas Vikhamar Schuler, Karianne Staalesen Lilleøren, and Louise Steffensen Schmidt
EGUsphere, https://doi.org/10.5194/egusphere-2025-108, https://doi.org/10.5194/egusphere-2025-108, 2025
Preprint archived
Short summary
Short summary
Ribbed moraines are a common, but poorly understood landform within formerly glaciated regions. There are many competing theories for their formation. As such, this paper addresses some of these theories by taking modelled ice conditions and physical characteristics of the landscapes in which they form and, then comparing them to the location of ribbed moraines. Using this we can identify conditions where ribbed moraines are more often present, and therefore we identify the most likely theories.
Coline Bouchayer, Ugo Nanni, Pierre-Marie Lefeuvre, John Hult, Louise Steffensen Schmidt, Jack Kohler, François Renard, and Thomas V. Schuler
The Cryosphere, 18, 2939–2968, https://doi.org/10.5194/tc-18-2939-2024, https://doi.org/10.5194/tc-18-2939-2024, 2024
Short summary
Short summary
We explore the interplay between surface runoff and subglacial conditions. We focus on Kongsvegen glacier in Svalbard. We drilled 350 m down to the glacier base to measure water pressure, till strength, seismic noise, and glacier surface velocity. In the low-melt season, the drainage system adapted gradually, while the high-melt season led to a transient response, exceeding drainage capacity and enhancing sliding. Our findings contribute to discussions on subglacial hydro-mechanical processes.
Andrea Spolaor, Federico Scoto, Catherine Larose, Elena Barbaro, Francois Burgay, Mats P. Bjorkman, David Cappelletti, Federico Dallo, Fabrizio de Blasi, Dmitry Divine, Giuliano Dreossi, Jacopo Gabrieli, Elisabeth Isaksson, Jack Kohler, Tonu Martma, Louise S. Schmidt, Thomas V. Schuler, Barbara Stenni, Clara Turetta, Bartłomiej Luks, Mathieu Casado, and Jean-Charles Gallet
The Cryosphere, 18, 307–320, https://doi.org/10.5194/tc-18-307-2024, https://doi.org/10.5194/tc-18-307-2024, 2024
Short summary
Short summary
We evaluate the impact of the increased snowmelt on the preservation of the oxygen isotope (δ18O) signal in firn records recovered from the top of the Holtedahlfonna ice field located in the Svalbard archipelago. Thanks to a multidisciplinary approach we demonstrate a progressive deterioration of the isotope signal in the firn core. We link the degradation of the δ18O signal to the increased occurrence and intensity of melt events associated with the rapid warming occurring in the archipelago.
Louise Steffensen Schmidt, Thomas Vikhamar Schuler, Erin Emily Thomas, and Sebastian Westermann
The Cryosphere, 17, 2941–2963, https://doi.org/10.5194/tc-17-2941-2023, https://doi.org/10.5194/tc-17-2941-2023, 2023
Short summary
Short summary
Here, we present high-resolution simulations of glacier mass balance (the gain and loss of ice over a year) and runoff on Svalbard from 1991–2022, one of the fastest warming regions in the Arctic. The simulations are created using the CryoGrid community model. We find a small overall loss of mass over the simulation period of −0.08 m yr−1 but with no statistically significant trend. The average runoff was found to be 41 Gt yr−1, with a significant increasing trend of 6.3 Gt per decade.
Sebastian Westermann, Thomas Ingeman-Nielsen, Johanna Scheer, Kristoffer Aalstad, Juditha Aga, Nitin Chaudhary, Bernd Etzelmüller, Simon Filhol, Andreas Kääb, Cas Renette, Louise Steffensen Schmidt, Thomas Vikhamar Schuler, Robin B. Zweigel, Léo Martin, Sarah Morard, Matan Ben-Asher, Michael Angelopoulos, Julia Boike, Brian Groenke, Frederieke Miesner, Jan Nitzbon, Paul Overduin, Simone M. Stuenzi, and Moritz Langer
Geosci. Model Dev., 16, 2607–2647, https://doi.org/10.5194/gmd-16-2607-2023, https://doi.org/10.5194/gmd-16-2607-2023, 2023
Short summary
Short summary
The CryoGrid community model is a new tool for simulating ground temperatures and the water and ice balance in cold regions. It is a modular design, which makes it possible to test different schemes to simulate, for example, permafrost ground in an efficient way. The model contains tools to simulate frozen and unfrozen ground, snow, glaciers, and other massive ice bodies, as well as water bodies.
Cas Renette, Kristoffer Aalstad, Juditha Aga, Robin Benjamin Zweigel, Bernd Etzelmüller, Karianne Staalesen Lilleøren, Ketil Isaksen, and Sebastian Westermann
Earth Surf. Dynam., 11, 33–50, https://doi.org/10.5194/esurf-11-33-2023, https://doi.org/10.5194/esurf-11-33-2023, 2023
Short summary
Short summary
One of the reasons for lower ground temperatures in coarse, blocky terrain is a low or varying soil moisture content, which most permafrost modelling studies did not take into account. We used the CryoGrid community model to successfully simulate this effect and found markedly lower temperatures in well-drained, blocky deposits compared to other set-ups. The inclusion of this drainage effect is another step towards a better model representation of blocky mountain terrain in permafrost regions.
Anirudha Mahagaonkar, Geir Moholdt, and Thomas V. Schuler
The Cryosphere Discuss., https://doi.org/10.5194/tc-2023-4, https://doi.org/10.5194/tc-2023-4, 2023
Revised manuscript not accepted
Short summary
Short summary
Surface meltwater lakes along the margins of the Antarctic Ice Sheet can be important for ice shelf dynamics and stability. We used optical satellite imagery to study seasonal evolution of meltwater lakes in Dronning Maud Land. We found large interannual variability in lake extents, but with consistent seasonal patterns. Although correlation with summer air temperature was strong locally, other climatic and environmental factors need to be considered to explain the large regional variability.
Karianne S. Lilleøren, Bernd Etzelmüller, Line Rouyet, Trond Eiken, Gaute Slinde, and Christin Hilbich
Earth Surf. Dynam., 10, 975–996, https://doi.org/10.5194/esurf-10-975-2022, https://doi.org/10.5194/esurf-10-975-2022, 2022
Short summary
Short summary
In northern Norway we have observed several rock glaciers at sea level. Rock glaciers are landforms that only form under the influence of permafrost, which is frozen ground. Our investigations show that the rock glaciers are probably not active under the current climate but most likely were active in the recent past. This shows how the Arctic now changes due to climate changes and also how similar areas in currently colder climates will change in the future.
Aldo Bertone, Chloé Barboux, Xavier Bodin, Tobias Bolch, Francesco Brardinoni, Rafael Caduff, Hanne H. Christiansen, Margaret M. Darrow, Reynald Delaloye, Bernd Etzelmüller, Ole Humlum, Christophe Lambiel, Karianne S. Lilleøren, Volkmar Mair, Gabriel Pellegrinon, Line Rouyet, Lucas Ruiz, and Tazio Strozzi
The Cryosphere, 16, 2769–2792, https://doi.org/10.5194/tc-16-2769-2022, https://doi.org/10.5194/tc-16-2769-2022, 2022
Short summary
Short summary
We present the guidelines developed by the IPA Action Group and within the ESA Permafrost CCI project to include InSAR-based kinematic information in rock glacier inventories. Nine operators applied these guidelines to 11 regions worldwide; more than 3600 rock glaciers are classified according to their kinematics. We test and demonstrate the feasibility of applying common rules to produce homogeneous kinematic inventories at global scale, useful for hydrological and climate change purposes.
Cited articles
Aario, R.: Classification and terminology of morainic landforms in Finland, Boreas, 6, 87–100, https://doi.org/10.1111/j.1502-3885.1977.tb00338.x, 1977.
Ali, A., Dunlop, P., Coleman, S., Kerr, D., McNabb, R. W., and Noormets, R.: Glacier area changes in the Arctic and high latitudes using satellite remote sensing, J. Maps, 19, 1–7, https://doi.org/10.1080/17445647.2023.2247416, 2023.
Aydda, A., Althuwaynee, O. F., and Pokharel, B.: An easy method for barchan dunes automatic extraction from multispectral satellite data, IOP Conf. Ser. Earth Environ. Sci., 419, 012015, https://doi.org/10.1088/1755-1315/419/1/012015, 2020.
Barnes, R.: RichDEM: terrain Analysis Software, GitHub [code], https://github.com/r-barnes/richdem (last access: 3 June 2023), 2016.
Barnes, T. and Filhol, S.: Aeteia/Ribbed-Moraine: Release ver.8.3 for ribbed moraines detection script, Zenodo [code and data set], https://doi.org/10.5281/zenodo.7991094, 2023.
Bhattacharjee, A., Murugan, R., and Goel, T.: A hybrid approach for lung cancer diagnosis using optimized random forest classification and K-means visualization algorithm, Health Technol. (Berl)., 12, 787–800, https://doi.org/10.1007/s12553-022-00679-2, 2022.
Böhner, J., Köthe, R., Conrad, O., Gross, J., Ringeler, A., and Selige, T.: Soil regionalisation by means of terrain analysis and process parameterisation, Eur. Soil Bur., 213–222, https://esdac.jrc.ec.europa.eu/ESDB_Archive/eusoils_docs/esb_rr/n07_ESBResRep07/601Bohner.pdf (last access: 5 June 2023), 2001.
Boulton, G. S. and Clark, C. D.: The Laurentide ice sheet through the last glacial cycle: the topology of drift lineations as a key to the dynamic behaviour of former ice sheets, T. Roy. Soc. Edinburgh, 81, 327–347, https://doi.org/10.1017/S0263593300020836, 1990.
Bradski, G.: The OpenCV Library, Dr. Dobb's J. Softw. Tools, GitHub [code], https://github.com/opencv/opencv (last access: 12 April 2022), 2000.
Breiman, L.: Random Forests, Mach. Learn., 45, 5–32, https://doi.org/10.1023/A:1010933404324, 2001.
Brodersen, K. H., Ong, C. S., Stephan, K. E., and Buhmann, J. M.: The balanced accuracy and its posterior distribution, in: 20th International Conference on Pattern Recognition, 23–26 August 2010, Istanbul, Turkey, 3121–3124, https://doi.org/10.1109/ICPR.2010.764, 2010.
Burney, S. M. A. and Tariq, H.: K-means Cluster Analysis for Image Segmentation, Int. J. Comput. Appl., 96, 1–8, https://doi.org/10.5120/16779-6360, 2014.
Butcher, F. E. G., Hughes, A. L. C., Ely, J. C., Christopher, D., Lewington, E. L. M., Boyes, B. M., Scoffield, A. C., Howcutt, S., and Dowling, T. P. F.: A new, multi-scale mapping approach for reconstructing the flow evolution of the Fennoscandian Ice Sheet using high-resolution digital elevation models, EGU General Assembly Conference Abstracts, EGU22, 4765 pp., https://doi.org/10.5194/egusphere-egu22-4765, 2021.
Clubb, F. J., Bookhagen, B., and Rheinwalt, A.: Clustering River Profiles to Classify Geomorphic Domains, J. Geophys. Res.-Earth, 124, 1417–1439, https://doi.org/10.1029/2019JF005025, 2019.
Conrad, O., Bechtel, B., Bock, M., Dietrich, H., Fischer, E., Gerlitz, L., Wehberg, J., Wichmann, V., and Böhner, J.: System for Automated Geoscientific Analyses (SAGA) v. 2.1.4, Geosci. Model Dev., 8, 1991–2007, https://doi.org/10.5194/gmd-8-1991-2015, 2015.
Corr, D., Leeson, A., McMillan, M., Zhang, C., and Barnes, T.: An inventory of supraglacial lakes and channels across the West Antarctic Ice Sheet, Earth Syst. Sci. Data, 14, 209–228, https://doi.org/10.5194/essd-14-209-2022, 2022.
Cowan, W.: Ribbed moraine: till fabric analysis and origin, Can. J. Earth Sci., 5, 1145–1159, 1968.
Dirscherl, M., Dietz, A. J., Kneisel, C., and Kuenzer, C.: Automated mapping of antarctic supraglacial lakes using a machine learning approach, Remote Sens., 12, 1–27, https://doi.org/10.3390/rs12071203, 2020.
Dunlop, P. and Clark, C. D.: The morphological characteristics of ribbed moraine, Quaternary Sci. Rev., 25, 1668–1691, https://doi.org/10.1016/j.quascirev.2006.01.002, 2006.
Dunlop, P., Clark, C. D., and Hindmarsh, R. C. A.: Bed ribbing instability explanation: Testing a numerical model of Ribbed moraine formation arising from couple flow of ice and subglacial sediment, J. Geophys. Res.-Earth, 113, 1–15, https://doi.org/10.1029/2007JF000954, 2008.
Eisank, C., Smith, M., and Hillier, J.: Assessment of multiresolution segmentation for delimiting drumlins in digital elevation models, Geomorphology, 214, 452–464, https://doi.org/10.1016/j.geomorph.2014.02.028, 2014.
Ely, J. C., Clark, C. D., Spagnolo, M., Stokes, C. R., Greenwood, S. L., Hughes, A. L. C., Dunlop, P., and Hess, D.: Do subglacial bedforms comprise a size and shape continuum?, Geomorphology, 257, 108–119, https://doi.org/10.1016/j.geomorph.2016.01.001, 2016.
Evans, I. S.: Geomorphometry and landform mapping: What is a landform?, Geomorphology, 137, 94–106, https://doi.org/10.1016/j.geomorph.2010.09.029, 2012.
Finlayson, A. G. and Bradwell, T.: Morphological characteristics, formation and glaciological significance of Rogen moraine in northern Scotland, Geomorphology, 101, 607–617, https://doi.org/10.1016/j.geomorph.2008.02.013, 2008.
Fisher, T. G. and Shaw, J.: A depositional model for Rogen moraine with examples from the Avalon Peninsula, Newfoundland, Can. J. Earth Sci., 29, 669–686, https://doi.org/10.1139/e92-058, 1992.
Fredin, O., Bergstrøm, B., Eilertsen, R., Hansen, L., Longva, O., Nesje, A., and Sveian, H.: Glacial landforms and Quaternary landscape development in Norway, Quat. Geol. Norw. Geol. Surv. Norw. Spec. Publ., 13, 5–25, 2013.
Frödin, G.: De sista skedena av Centraljämtlands glaciala historia, Geogr. Uppsala Univ., 24, 1–251, 1954.
Gentleman, R. and Carey, V.: Unsupervised Machine Learning, in: Bioconductor Case Studies, Cambridge, 137–157, https://doi.org/10.1007/978-0-387-77240-0, 2008.
Giaccone, E., Oriane, F., Tonini, M., Lambiel, C., and Mariéthoz, G.: Using data-driven algorithms for semi-automated geomorphological mapping, Stoch. Environ. Res. Risk A., 36, 2115–2131, https://doi.org/10.1007/s00477-021-02062-5, 2022.
GISCO: Countries, 2020 – Administrative Units – Dataset, https://gisco-services.ec.europa.eu/distribution/v2/countries/ (last access: 20 August 2023), 2020.
Guisan, A., Weiss, S. B., and Weiss, A. D.: GLM versus CCA Spatial Modeling of Plant Species Distribution Author (s): Reviewed work (s): GLM versus CCA spatial modeling of plant species distribution, Plant Ecol., 143, 107–122, 1999.
Guitet, S., Cornu, J. F., Brunaux, O., Betbeder, J., Carozza, J. M., and Richard-Hansen, C.: Landform and landscape mapping, French Guiana (South America), J. Maps, 9, 325–335, https://doi.org/10.1080/17445647.2013.785371, 2013.
Hättestrand, C. and Kleman, J.: Ribbed moraine formation, Quaternary Sci. Rev., 18, 43–61, 1999.
Hjort, J., Ujanen, J., Parviainen, M., Tolgensbakk, M., and Etzelmüller, B.: Transferability of geomorphological distribution models: Evaluation using solifluction features in subarctic and Arctic regions, J. Geomorphol., 204, 165–176, https://doi.org/10.1016/j.geomorph.2013.08.002, 2014.
Hoppe, G.: Glacial Morphology and inland icec recession in northern Sweden, Geogr. Ann., 41, 193–212, 1952.
Hong, C. S. and Oh, T. G.: TPR–TNR plot for confusion matrix, Commun. Stat. Appl. Meth., 28, 161–169, https://doi.org/10.29220/CSAM.2021.28.2.161, 2021.
Horn, B. K. P.: Hill shading and the reflectance map, Proc. IEEE, 69, 14–47, https://doi.org/10.1109/PROC.1981.11918, 1981.
Iwahashi, J., Kamiya, I., Matsuoka, M., and Yamazaki, D.: Global terrain classification using 280 m DEMs: segmentation, clustering, and reclassification, Prog. Earth Planet. Sci., 5, 1–31, https://doi.org/10.1186/s40645-017-0157-2, 2018.
Kartverket: Norge i Bilder, Norwegian mapping authority, Geovekst og kommunene (Nasjonal data), http://opencache.statkart.no/gatekeeper/gk/gk.open_nib_utm33_wmts_v2?SERVICE=WMTS&REQUEST=GetCapabilities (last access: 21 August 2023), 2021a.
Kartverket: Høydemodell DTM 1 m, https://hoydedata.no/LaserInnsyn2/ (last access: 5 January 2022), 2021b.
Kartverket: Norge I bilder WMS – Ortofoto, Trond Ola Ulvolden, http://data.europa.eu/88u/dataset/dcee8bf4-fdf3-4433-a91b-209c7d9b0b0f (last access: 21 August 2023), 2021c.
Kong, Y., Zeng, J., Wang, J., and Fang, Y.: A basin recognition method by landform classification and geometrical feature discrimination, AIP Adv., 11, 015305-1–015305-7, https://doi.org/10.1063/5.0031695, 2021.
Likas, A., Vlassis, N., and Verbeek, J.: The global k-means clustering algorithm, Pattern Recognit., 36, 451–461, https://doi.org/10.1016/S0031-3203(02)00060-2, 2003.
Lindén, M., Möller, P., and Adrielsson, L.: Ribbed moraine formed by subglacial folding, thrust stacking and lee-side cavity infill, Boreas, 37, 102–131, https://doi.org/10.1111/j.1502-3885.2007.00002.x, 2008.
Liu, C., Gu, Z., and Wang, J.: A Hybrid Intrusion Detection System Based on Scalable K-Means+ Random Forest and Deep Learning, IEEE Access, 9, 75729–75740, https://doi.org/10.1109/ACCESS.2021.3082147, 2021.
Lundqvist, J.: Problems of the So-called Rogen Moraine, Series C, Swedish Geol. Surv., 32 pp. , https://resource.sgu.se/dokument/publikation/c/c648rapport/c648-rapport.pdf (last access: 11 June 2022), 1969.
Lundqvist, J.: Rogen (ribbed) moraine-identification and possible origin, Sediment. Geol., 62, 281–292, https://doi.org/10.1016/0037-0738(89)90119-X, 1989.
Lundqvist, J.: Rogen moraine – An example of two-step formation of glacial landscapes, Sediment. Geol., 111, 27–40, https://doi.org/10.1016/S0037-0738(97)00004-3, 1997.
Lv, Z., Liu, T., Shi, C., Benediktsson, J. A., and Du, H.: Novel Land Cover Change Detection Method Based on k-Means Clustering and Adaptive Majority Voting Using Bitemporal Remote Sensing Images, IEEE Access, 7, 34425–34437, https://doi.org/10.1109/ACCESS.2019.2892648, 2019.
Marutho, D., Hendra Handaka, S., Wijaya, E., and Muljono: The Determination of Cluster Number at k-mean Using Elbow Method and Purity Evaluation on Headline News, in: Proc. – 2018 Int. Semin. Appl. Technol. Inf. Commun. Creat. Technol. Hum. Life, iSemantic 2018, 21–22 September 2018, Semarang, Indonesia, 533–538, https://doi.org/10.1109/ISEMANTIC.2018.8549751, 2018.
Möller, P.: Melt-out till and ribbed moraine formation, a case study from south Sweden, Sediment. Geol., 232, 161–180, https://doi.org/10.1016/j.sedgeo.2009.11.003, 2010.
Möller, P. and Dowling, T. P. F.: Equifinality in glacial geomorphology: instability theory examined via ribbed moraine and drumlins in Sweden, GFF, 140, 106–135, https://doi.org/10.1080/11035897.2018.1441903, 2018.
Moradi Fard, M., Thonet, T., and Gaussier, E.: Deep k-means: Jointly clustering with k-means and learning representations, Pattern Recognit. Lett., 138, 185–192, https://doi.org/10.1016/j.patrec.2020.07.028, 2020.
Ng, H. P., Ong, S. H., Foong, K. W. C., Goh, P. S., and Nowinski, W. L., Medical image segmentation using K–means clustering and improved watershed algorithm, in: P. IEEE Southwest Symp. Image Anal. Interpret., 26–28 March 2006, Denver, CO, USA, 61–65, https://doi.org/10.1109/ssiai.2006.1633722, 2006.
NGU: løsmasse, https://geo.ngu.no/kart/losmass_mobil/ (last acces: 1 August 2022), 2022.
NVE: Innsjødatabase, https://www.nve.no/kart/kartdata/vassdragsdata/innsjodatabase/ (last access: 1 January 2023), 2023.
Patton, H., Hubbard, A., Andreassen, K., Winsborrow, M., and Stroeven, A. P.: The build-up, configuration, and dynamical sensitivity of the Eurasian ice-sheet complex to Late Weichselian climatic and oceanic forcing, Quaternary Sci. Rev., 153, 97–121, https://doi.org/10.1016/j.quascirev.2016.10.009, 2016.
Patton, H., Hubbard, A., Andreassen, K., Auriac, A., Whitehouse, P. L., Stroeven, A. P., Shackleton, C., Winsborrow, M., Heyman, J., and Hall, A. M.: Deglaciation of the Eurasian ice sheet complex, Quaternary Sci. Rev., 169, 148–172, https://doi.org/10.1016/j.quascirev.2017.05.019, 2017.
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 Duchesnay, É.: Scikit-learn: Machine Learning in Python, J. Mach. Learn. Res., 12, 2826–2830, 2011.
Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, in: MICCAI 2015, Lecture Notes in Computer Science, vol. 9351, Springer, Cham, https://doi.org/10.1007/978-3-319-24574-4_28, 2015.
Saha, K., Wells, N. A., and Munro-Stasiuk, M.: An object-oriented approach to automated landform mapping: A case study of drumlins, Comput. Geosci., 37, 1324–1336, https://doi.org/10.1016/j.cageo.2011.04.001, 2011.
Sarala, P.: Ribbed moraine stratigraphy and formation in southern Finnish Lapland, J. Quatern. Sci., 21, 387–398, https://doi.org/10.1002/jqs.995, 2006.
Smith, M. J. and Clark, C. D.: Methods for the visualization of digital elevation models for landform mapping, Earth Surf. Proc. Land., 30, 885–900, https://doi.org/10.1002/esp.1210, 2005.
Sokolova, M., Japkowicz, N., and Szpakowicz, S.: Beyond Accuracy, F-Score and ROC: A Family of Disciminant Measures for Performance Evaluation, Adv. Artif. Intel., 4304, 1015–1021, 2006.
Sollid, J. L. and Sorbel, L.: Distribution of Glacial Landforms in Southern Norway in Relation to the Thermal Regime of the Last Continental Ice Sheet, Geogr. Ann. A, 76, 25–35, https://doi.org/10.2307/521317, 1994.
Sommerkorn, J.: Distribution of ribbed moraines and their connection to subglacial water in the Oppland region of Norway, Universitetet i Oslo, Oslo, http://urn.nb.no/URN:NBN:no-82891 (last access: 1 September 2023), 2020.
Strøm, K. M.: The Geomorphology of Norway, Geogr. J., 112, 19–23, 1948.
UKEA – United Kingdom Environment Agency: LiDAR Composite DTM 2022 – 1 m, https://www.data.gov.uk/dataset/01b3ee39-da3f-47b6-83da-dc98e73a461f/lidar-composite-dtm-2022-1m (last access: 20 March 2023), 2023.
Verstappen, H. T.: Chapter Two – Old and New Trends in Geomorphological and Landform Mapping, Dev. Earth Surf. Process., 15, 13–38, https://doi.org/10.1016/B978-0-444-53446-0.00002-1, 2011.
Zevenbergen, W. L. and Thorne, R. C.: Quantitative analysis of land surface topography, Earth Surf. Proc. Land., 12, 47–56, 1987.
Short summary
In this paper, we use machine learning to automatically outline landforms based on their characteristics. We test several methods to identify the most accurate and then proceed to develop the most accurate to improve its accuracy further. We manage to outline landforms with 65 %–75 % accuracy, at a resolution of 10 m, thanks to high-quality/high-resolution elevation data. We find that it is possible to run this method at a country scale to quickly produce landform inventories for future studies.
In this paper, we use machine learning to automatically outline landforms based on their...
