Articles | Volume 19, issue 4
https://doi.org/10.5194/tc-19-1675-2025
© Author(s) 2025. 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-19-1675-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
24 Apr 2025
Research article |
| 24 Apr 2025
| 24 Apr 2025
Automated snow cover detection on mountain glaciers using spaceborne imagery and machine learning
Rainey Aberle
CORRESPONDING AUTHOR
Department of Geosciences, Boise State University, Boise, ID 83725, USA
Ellyn Enderlin
Department of Geosciences, Boise State University, Boise, ID 83725, USA
Shad O'Neel
Cold Regions Research and Engineering Laboratory, U.S. Army Corps of Engineers, Hanover, NH 03755, USA
Caitlyn Florentine
U.S. Geological Survey, Northern Rocky Mountains Science Center, West Glacier, MT 59717, USA
Louis Sass
U.S. Geological Survey, Alaska Science Center, Anchorage, AK 99508, USA
Adam Dickson
Department of Geosciences, Boise State University, Boise, ID 83725, USA
Hans-Peter Marshall
Department of Geosciences, Boise State University, Boise, ID 83725, USA
Alejandro Flores
Department of Geosciences, Boise State University, Boise, ID 83725, USA
Related authors
Jukes Liu, Madeline Gendreau, Ellyn Mary Enderlin, and Rainey Aberle
The Cryosphere, 18, 3571–3590, https://doi.org/10.5194/tc-18-3571-2024, https://doi.org/10.5194/tc-18-3571-2024, 2024
Short summary
Short summary
There are sometimes gaps in global glacier velocity records produced using satellite image feature-tracking algorithms during times of rapid glacier acceleration, which hinders the study of glacier flow processes. We present an open-source pipeline for customizing the feature-tracking parameters and for including images from an additional source. We applied it to five glaciers and found that it produced accurate velocity data that supplemented their velocity records during rapid acceleration.
Aman KC, Ellyn M. Enderlin, Dominik Fahrner, Twila Moon, and Dustin Carroll
The Cryosphere, 19, 3089–3106, https://doi.org/10.5194/tc-19-3089-2025, https://doi.org/10.5194/tc-19-3089-2025, 2025
Short summary
Short summary
The sum of ice flowing towards a glacier’s terminus and changes in the position of the terminus over time collectively makes up terminus ablation. We found that terminus ablation has more seasonal variability than previously concluded from flux-based estimates of ice discharge. The findings are of importance in understanding the timing and location of the freshwater input to the fjords and surrounding ocean basins affecting local and regional ecosystems and ocean properties.
Kajsa Holland-Goon, Randall Bonnell, Daniel McGrath, W. Brad Baxter, Tate Meehan, Ryan Webb, Chris Larsen, Hans-Peter Marshall, Megan Mason, and Carrie Vuyovich
EGUsphere, https://doi.org/10.5194/egusphere-2025-2435, https://doi.org/10.5194/egusphere-2025-2435, 2025
This preprint is open for discussion and under review for The Cryosphere (TC).
Short summary
Short summary
As part of the NASA SnowEx23 campaign, we conducted detailed snowpack experiments in Alaska’s boreal forests and Arctic tundra. We collected ground-penetrating radar measurements of snow depth along 44 short transects. We then excavated the snowpack from below the transects and measured snow depth, noting any vegetation and void spaces. We used the detailed in situ measurements to evaluate uncertainties in ground-penetrating radar and airborne lidar methods for snow depth retrieval.
Kachinga Silwimba, Alejandro N. Flores, Irene Cionni, Sharon A. Billings, Pamela L. Sullivan, Hoori Ajami, Daniel R. Hirmas, and Li Li
EGUsphere, https://doi.org/10.5194/egusphere-2025-713, https://doi.org/10.5194/egusphere-2025-713, 2025
Short summary
Short summary
This study evaluates the influence of soil hydraulic parameterizations on soil moisture simulations in CLM5 across the CONUS (1980–2010) using Empirical Orthogonal Function (EOF) analysis. Results reveal significant regional discrepancies, particularly in the Great Plains, where parameter uncertainty drives biases in soil moisture variability. Comparisons with ERA5-Land highlight seasonal mismatches, underscoring the need for improved soil parameterization to enhance land surface model accuracy.
Lena Wang, Sharon Billings, Li Li, Daniel Hirmas, Keira Johnson, Devon Kerins, Julio Pachon, Curtis Beutler, Karla Jarecke, Vaishnavi Varikuti, Micah Unruh, Hoori Ajami, Holly Barnard, Alejandro Flores, Kenneth Williams, and Pamela Sullivan
EGUsphere, https://doi.org/10.5194/egusphere-2025-70, https://doi.org/10.5194/egusphere-2025-70, 2025
Short summary
Short summary
Our study looked at how different forest types and conditions affected soil microbes, and soil carbon and stability. Aspen organic matter led to higher microbial activity, smaller soil aggregates, and more stable soil carbon, possibly reducing dissolved organic carbon movement from hillslopes to streams. This shows the importance of models like the Microbial Efficiency – Matrix Stabilization framework for predicting CO2 release, soil carbon stability, and carbon movement.
Zachary Fair, Carrie Vuyovich, Thomas Neumann, Justin Pflug, David Shean, Ellyn M. Enderlin, Karina Zikan, Hannah Besso, Jessica Lundquist, Cesar Deschamps-Berger, and Désirée Treichler
EGUsphere, https://doi.org/10.5194/egusphere-2024-3992, https://doi.org/10.5194/egusphere-2024-3992, 2025
Short summary
Short summary
Lidar is commonly used to measure snow over global water reservoirs. However, ground-based and airborne lidar surveys are expensive, so satellite-based methods are needed. In this review, we outline the latest research using satellite-based lidar to monitor snow. Best practices for lidar-based snow monitoring are given, as is a discussion on challenges in this field of research.
Zachary Hoppinen, Ross T. Palomaki, George Brencher, Devon Dunmire, Eric Gagliano, Adrian Marziliano, Jack Tarricone, and Hans-Peter Marshall
The Cryosphere, 18, 5407–5430, https://doi.org/10.5194/tc-18-5407-2024, https://doi.org/10.5194/tc-18-5407-2024, 2024
Short summary
Short summary
This study uses radar imagery from the Sentinel-1 satellite to derive snow depth from increases in the returning energy. These retrieved depths are then compared to nine lidar-derived snow depths across the western United State to assess the ability of this technique to be used to monitor global snow distributions. We also qualitatively compare the changes in underlying Sentinel-1 amplitudes against both the total lidar snow depths and nine automated snow monitoring stations.
Randall Bonnell, Daniel McGrath, Jack Tarricone, Hans-Peter Marshall, Ella Bump, Caroline Duncan, Stephanie Kampf, Yunling Lou, Alex Olsen-Mikitowicz, Megan Sears, Keith Williams, Lucas Zeller, and Yang Zheng
The Cryosphere, 18, 3765–3785, https://doi.org/10.5194/tc-18-3765-2024, https://doi.org/10.5194/tc-18-3765-2024, 2024
Short summary
Short summary
Snow provides water for billions of people, but the amount of snow is difficult to detect remotely. During the 2020 and 2021 winters, a radar was flown over mountains in Colorado, USA, to measure the amount of snow on the ground, while our team collected ground observations to test the radar technique’s capabilities. The technique yielded accurate measurements of the snowpack that had good correlation with ground measurements, making it a promising application for the upcoming NISAR satellite.
Jukes Liu, Madeline Gendreau, Ellyn Mary Enderlin, and Rainey Aberle
The Cryosphere, 18, 3571–3590, https://doi.org/10.5194/tc-18-3571-2024, https://doi.org/10.5194/tc-18-3571-2024, 2024
Short summary
Short summary
There are sometimes gaps in global glacier velocity records produced using satellite image feature-tracking algorithms during times of rapid glacier acceleration, which hinders the study of glacier flow processes. We present an open-source pipeline for customizing the feature-tracking parameters and for including images from an additional source. We applied it to five glaciers and found that it produced accurate velocity data that supplemented their velocity records during rapid acceleration.
Tate G. Meehan, Ahmad Hojatimalekshah, Hans-Peter Marshall, Elias J. Deeb, Shad O'Neel, Daniel McGrath, Ryan W. Webb, Randall Bonnell, Mark S. Raleigh, Christopher Hiemstra, and Kelly Elder
The Cryosphere, 18, 3253–3276, https://doi.org/10.5194/tc-18-3253-2024, https://doi.org/10.5194/tc-18-3253-2024, 2024
Short summary
Short summary
Snow water equivalent (SWE) is a critical parameter for yearly water supply forecasting and can be calculated by multiplying the snow depth by the snow density. We combined high-spatial-resolution snow depth information with ground-based radar measurements to solve for snow density. Extrapolated density estimates over our study area resolved detailed patterns that agree with the known interactions of snow with wind, terrain, and vegetation and were utilized in the calculation of SWE.
Livia Piermattei, Michael Zemp, Christian Sommer, Fanny Brun, Matthias H. Braun, Liss M. Andreassen, Joaquín M. C. Belart, Etienne Berthier, Atanu Bhattacharya, Laura Boehm Vock, Tobias Bolch, Amaury Dehecq, Inés Dussaillant, Daniel Falaschi, Caitlyn Florentine, Dana Floricioiu, Christian Ginzler, Gregoire Guillet, Romain Hugonnet, Matthias Huss, Andreas Kääb, Owen King, Christoph Klug, Friedrich Knuth, Lukas Krieger, Jeff La Frenierre, Robert McNabb, Christopher McNeil, Rainer Prinz, Louis Sass, Thorsten Seehaus, David Shean, Désirée Treichler, Anja Wendt, and Ruitang Yang
The Cryosphere, 18, 3195–3230, https://doi.org/10.5194/tc-18-3195-2024, https://doi.org/10.5194/tc-18-3195-2024, 2024
Short summary
Short summary
Satellites have made it possible to observe glacier elevation changes from all around the world. In the present study, we compared the results produced from two different types of satellite data between different research groups and against validation measurements from aeroplanes. We found a large spread between individual results but showed that the group ensemble can be used to reliably estimate glacier elevation changes and related errors from satellite data.
Isis Brangers, Hans-Peter Marshall, Gabrielle De Lannoy, Devon Dunmire, Christian Mätzler, and Hans Lievens
The Cryosphere, 18, 3177–3193, https://doi.org/10.5194/tc-18-3177-2024, https://doi.org/10.5194/tc-18-3177-2024, 2024
Short summary
Short summary
To better understand the interactions between C-band radar waves and snow, a tower-based experiment was set up in the Idaho Rocky Mountains. The reflections were collected in the time domain to measure the backscatter profile from the various snowpack and ground surface layers. The results demonstrate that C-band radar is sensitive to seasonal patterns in snow accumulation but that changes in microstructure, stratigraphy and snow wetness may complicate satellite-based snow depth retrievals.
Ian E. McDowell, Kaitlin M. Keegan, S. McKenzie Skiles, Christopher P. Donahue, Erich C. Osterberg, Robert L. Hawley, and Hans-Peter Marshall
The Cryosphere, 18, 1925–1946, https://doi.org/10.5194/tc-18-1925-2024, https://doi.org/10.5194/tc-18-1925-2024, 2024
Short summary
Short summary
Accurate knowledge of firn grain size is crucial for many ice sheet research applications. Unfortunately, collecting detailed measurements of firn grain size is difficult. We demonstrate that scanning firn cores with a near-infrared imager can quickly produce high-resolution maps of both grain size and ice layer distributions. We map grain size and ice layer stratigraphy in 14 firn cores from Greenland and document changes to grain size and ice layer content from the extreme melt summer of 2012.
Brian Menounos, Alex Gardner, Caitlyn Florentine, and Andrew Fountain
The Cryosphere, 18, 889–894, https://doi.org/10.5194/tc-18-889-2024, https://doi.org/10.5194/tc-18-889-2024, 2024
Short summary
Short summary
Glaciers in western North American outside of Alaska are often overlooked in global studies because their potential to contribute to changes in sea level is small. Nonetheless, these glaciers represent important sources of freshwater, especially during times of drought. We show that these glaciers lost mass at a rate of about 12 Gt yr-1 for about the period 2013–2021; the rate of mass loss over the period 2018–2022 was similar.
Shadi Oveisgharan, Robert Zinke, Zachary Hoppinen, and Hans Peter Marshall
The Cryosphere, 18, 559–574, https://doi.org/10.5194/tc-18-559-2024, https://doi.org/10.5194/tc-18-559-2024, 2024
Short summary
Short summary
The seasonal snowpack provides water resources to billions of people worldwide. Large-scale mapping of snow water equivalent (SWE) with high resolution is critical for many scientific and economics fields. In this work we used the radar remote sensing interferometric synthetic aperture radar (InSAR) to estimate the SWE change between 2 d. The error in the estimated SWE change is less than 2 cm for in situ stations. Additionally, the retrieved SWE using InSAR is correlated with lidar snow depth.
Zachary Hoppinen, Shadi Oveisgharan, Hans-Peter Marshall, Ross Mower, Kelly Elder, and Carrie Vuyovich
The Cryosphere, 18, 575–592, https://doi.org/10.5194/tc-18-575-2024, https://doi.org/10.5194/tc-18-575-2024, 2024
Short summary
Short summary
We used changes in radar echo travel time from multiple airborne flights to estimate changes in snow depths across Idaho for two winters. We compared our radar-derived retrievals to snow pits, weather stations, and a 100 m resolution numerical snow model. We had a strong Pearson correlation and root mean squared error of 10 cm relative to in situ measurements. Our retrievals also correlated well with our model, especially in regions of dry snow and low tree coverage.
Dominik Fahrner, Donald Slater, Aman KC, Claudia Cenedese, David A. Sutherland, Ellyn Enderlin, Femke de Jong, Kristian K. Kjeldsen, Michael Wood, Peter Nienow, Sophie Nowicki, and Till Wagner
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2023-411, https://doi.org/10.5194/essd-2023-411, 2023
Preprint withdrawn
Short summary
Short summary
Marine-terminating glaciers can lose mass through frontal ablation, which comprises submarine and surface melting, and iceberg calving. We estimate frontal ablation for 49 marine-terminating glaciers in Greenland by combining existing, satellite derived data and calculating volume change near the glacier front over time. The dataset offers exciting opportunities to study the influence of climate forcings on marine-terminating glaciers in Greenland over multi-decadal timescales.
William Rudisill, Alejandro Flores, and Rosemary Carroll
Geosci. Model Dev., 16, 6531–6552, https://doi.org/10.5194/gmd-16-6531-2023, https://doi.org/10.5194/gmd-16-6531-2023, 2023
Short summary
Short summary
It is important to know how well atmospheric models do in mountains, but there are not very many weather stations. We evaluate rain and snow from a model from 1987–2020 in the Upper Colorado River basin against the available data. The model works rather well, but there are still some uncertainties in remote locations. We then use snow maps collected by aircraft, streamflow measurements, and some advanced statistics to help identify how well the model works in ways we could not do before.
Chris Miele, Timothy C. Bartholomaus, and Ellyn M. Enderlin
The Cryosphere, 17, 2701–2704, https://doi.org/10.5194/tc-17-2701-2023, https://doi.org/10.5194/tc-17-2701-2023, 2023
Short summary
Short summary
Vertical shear stress (the stress orientation usually associated with vertical gradients in horizontal velocities) is a key component of the stress balance of ice shelves. However, partly due to historical assumptions, vertical shear is often misspoken of today as
negligiblein ice shelf models. We address this miscommunication, providing conceptual guidance regarding this often misrepresented stress. Fundamentally, vertical shear is required to balance thickness gradients in ice shelves.
Jack Tarricone, Ryan W. Webb, Hans-Peter Marshall, Anne W. Nolin, and Franz J. Meyer
The Cryosphere, 17, 1997–2019, https://doi.org/10.5194/tc-17-1997-2023, https://doi.org/10.5194/tc-17-1997-2023, 2023
Short summary
Short summary
Mountain snowmelt provides water for billions of people across the globe. Despite its importance, we cannot currently measure the amount of water in mountain snowpacks from satellites. In this research, we test the ability of an experimental snow remote sensing technique from an airplane in preparation for the same sensor being launched on a future NASA satellite. We found that the method worked better than expected for estimating important snowpack properties.
Leung Tsang, Michael Durand, Chris Derksen, Ana P. Barros, Do-Hyuk Kang, Hans Lievens, Hans-Peter Marshall, Jiyue Zhu, Joel Johnson, Joshua King, Juha Lemmetyinen, Melody Sandells, Nick Rutter, Paul Siqueira, Anne Nolin, Batu Osmanoglu, Carrie Vuyovich, Edward Kim, Drew Taylor, Ioanna Merkouriadi, Ludovic Brucker, Mahdi Navari, Marie Dumont, Richard Kelly, Rhae Sung Kim, Tien-Hao Liao, Firoz Borah, and Xiaolan Xu
The Cryosphere, 16, 3531–3573, https://doi.org/10.5194/tc-16-3531-2022, https://doi.org/10.5194/tc-16-3531-2022, 2022
Short summary
Short summary
Snow water equivalent (SWE) is of fundamental importance to water, energy, and geochemical cycles but is poorly observed globally. Synthetic aperture radar (SAR) measurements at X- and Ku-band can address this gap. This review serves to inform the broad snow research, monitoring, and application communities about the progress made in recent decades to move towards a new satellite mission capable of addressing the needs of the geoscience researchers and users.
Juha Lemmetyinen, Juval Cohen, Anna Kontu, Juho Vehviläinen, Henna-Reetta Hannula, Ioanna Merkouriadi, Stefan Scheiblauer, Helmut Rott, Thomas Nagler, Elisabeth Ripper, Kelly Elder, Hans-Peter Marshall, Reinhard Fromm, Marc Adams, Chris Derksen, Joshua King, Adriano Meta, Alex Coccia, Nick Rutter, Melody Sandells, Giovanni Macelloni, Emanuele Santi, Marion Leduc-Leballeur, Richard Essery, Cecile Menard, and Michael Kern
Earth Syst. Sci. Data, 14, 3915–3945, https://doi.org/10.5194/essd-14-3915-2022, https://doi.org/10.5194/essd-14-3915-2022, 2022
Short summary
Short summary
The manuscript describes airborne, dual-polarised X and Ku band synthetic aperture radar (SAR) data collected over several campaigns over snow-covered terrain in Finland, Austria and Canada. Colocated snow and meteorological observations are also presented. The data are meant for science users interested in investigating X/Ku band radar signatures from natural environments in winter conditions.
Hans Lievens, Isis Brangers, Hans-Peter Marshall, Tobias Jonas, Marc Olefs, and Gabriëlle De Lannoy
The Cryosphere, 16, 159–177, https://doi.org/10.5194/tc-16-159-2022, https://doi.org/10.5194/tc-16-159-2022, 2022
Short summary
Short summary
Snow depth observations at high spatial resolution from the Sentinel-1 satellite mission are presented over the European Alps. The novel observations can improve our knowledge of seasonal snow mass in areas with complex topography, where satellite-based estimates are currently lacking, and benefit a number of applications including water resource management, flood forecasting, and numerical weather prediction.
Ahmad Hojatimalekshah, Zachary Uhlmann, Nancy F. Glenn, Christopher A. Hiemstra, Christopher J. Tennant, Jake D. Graham, Lucas Spaete, Arthur Gelvin, Hans-Peter Marshall, James P. McNamara, and Josh Enterkine
The Cryosphere, 15, 2187–2209, https://doi.org/10.5194/tc-15-2187-2021, https://doi.org/10.5194/tc-15-2187-2021, 2021
Short summary
Short summary
We describe the relationships between snow depth, vegetation canopy, and local-scale processes during the snow accumulation period using terrestrial laser scanning (TLS). In addition to topography and wind, our findings suggest the importance of fine-scale tree structure, species type, and distributions on snow depth. Snow depth increases from the canopy edge toward the open areas, but wind and topographic controls may affect this trend. TLS data are complementary to wide-area lidar surveys.
Karun Pandit, Hamid Dashti, Andrew T. Hudak, Nancy F. Glenn, Alejandro N. Flores, and Douglas J. Shinneman
Biogeosciences, 18, 2027–2045, https://doi.org/10.5194/bg-18-2027-2021, https://doi.org/10.5194/bg-18-2027-2021, 2021
Short summary
Short summary
A dynamic global vegetation model, Ecosystem Demography (EDv2.2), is used to understand spatiotemporal dynamics of a semi-arid shrub ecosystem under alternative fire regimes. Multi-decadal point simulations suggest shrub dominance for a non-fire scenario and a contrasting phase of shrub and C3 grass growth for a fire scenario. Regional gross primary productivity (GPP) simulations indicate moderate agreement with MODIS GPP and a GPP reduction in fire-affected areas before showing some recovery.
Rhae Sung Kim, Sujay Kumar, Carrie Vuyovich, Paul Houser, Jessica Lundquist, Lawrence Mudryk, Michael Durand, Ana Barros, Edward J. Kim, Barton A. Forman, Ethan D. Gutmann, Melissa L. Wrzesien, Camille Garnaud, Melody Sandells, Hans-Peter Marshall, Nicoleta Cristea, Justin M. Pflug, Jeremy Johnston, Yueqian Cao, David Mocko, and Shugong Wang
The Cryosphere, 15, 771–791, https://doi.org/10.5194/tc-15-771-2021, https://doi.org/10.5194/tc-15-771-2021, 2021
Short summary
Short summary
High SWE uncertainty is observed in mountainous and forested regions, highlighting the need for high-resolution snow observations in these regions. Substantial uncertainty in snow water storage in Tundra regions and the dominance of water storage in these regions points to the need for high-accuracy snow estimation. Finally, snow measurements during the melt season are most needed at high latitudes, whereas observations at near peak snow accumulations are most beneficial over the midlatitudes.
Ellyn M. Enderlin and Timothy C. Bartholomaus
The Cryosphere, 14, 4121–4133, https://doi.org/10.5194/tc-14-4121-2020, https://doi.org/10.5194/tc-14-4121-2020, 2020
Short summary
Short summary
Accurate predictions of future changes in glacier flow require the realistic simulation of glacier terminus position change in numerical models. We use crevasse observations for 19 Greenland glaciers to explore whether the two commonly used crevasse depth models match observations. The models cannot reproduce spatial patterns, and we largely attribute discrepancies between modeled and observed depths to the models' inability to account for advection.
Miguel A. Aguayo, Alejandro N. Flores, James P. McNamara, Hans-Peter Marshall, and Jodi Mead
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2020-451, https://doi.org/10.5194/hess-2020-451, 2020
Manuscript not accepted for further review
Cited articles
Aberle, R., Enderlin, E., O'Neel, S., Florentine, C., Sass, L., Dickson, A., Marshall, H.-P., and Flores, A.: Dataset for Automated Snow Cover Detection on Mountain Glaciers Using Space-Borne Imagery, CryoGARS Glaciology Data [data set], https://doi.org/10.18122/cryogars_data.4.boisestate, 2024a.
Aberle, R., Enderlin, E., and Liu, J.: RaineyAbe/glacier-snow-cover-mapping: Second release (v0.2), Zenodo [code], https://doi.org/10.5281/zenodo.10616385, 2024b.
Anderson, B. T., McNamara, J. P., Marshall, H.-P., and Flores, A. N.: Insights into the physical processes controlling correlations between snow distribution and terrain properties, Water Resour. Res., 50, 4545–4563, https://doi.org/10.1002/2013WR013714, 2014.
Bahadur K. C., K.: Improving Landsat and IRS Image Classification: Evaluation of Unsupervised and Supervised Classification through Band Ratios and DEM in a Mountainous Landscape in Nepal, Remote Sens., 1, 1257–1272, https://doi.org/10.3390/rs1041257, 2009.
Berman, E. E., Bolton, D. K., Coops, N. C., Mityok, Z. K., Stenhouse, G. B., and Moore, R. D. (Dan): Daily estimates of Landsat fractional snow cover driven by MODIS and dynamic time-warping, Remote Sens. Environ., 216, 635–646, https://doi.org/10.1016/j.rse.2018.07.029, 2018.
Boori, M. S., Paringer, R., Choudhary, K., and Kupriyanov, A.: Supervised and unsupervised classification for obtaining land use/cover classes from hyperspectral and multi-spectral imagery, Proc. SPIE 10773, Sixth International Conference on Remote Sensing and Geoinformation of the Environment, RSCy2018, https://doi.org/10.1117/12.2322624, 2018.
Callegari, M., Carturan, L., Marin, C., Notarnicola, C., Rastner, P., Seppi, R., and Zucca, F.: A Pol-SAR Analysis for Alpine Glacier Classification and Snowline Altitude Retrieval, IEEE J. Select. Top. Appl. Earth Observ. Remote Sens., 9, 3106–3121, https://doi.org/10.1109/JSTARS.2016.2587819, 2016.
Campbell, J. B. and Wynne, R. H.: Introduction to Remote Sensing, Fifth Edition, Guilford Publications, New York, UNITED STATES, ISBN 978-1-60918-176-5, 2011.
Cannistra, A. F., Shean, D. E., and Cristea, N. C.: High-resolution CubeSat imagery and machine learning for detailed snow-covered area, Remote Sens. Environ., 258, 112399, https://doi.org/10.1016/J.RSE.2021.112399, 2021.
Cochran, W. G.: Sampling techniques, John Wiley & Sons, Ltd, New York, ISBN 0-471-16240-X 978-0-471-16240-7, 1977.
Cohen, J.: A Coefficient of Agreement for Nominal Scales, Educ. Psychol. Meas., 20, 37–46, https://doi.org/10.1177/001316446002000104, 1960.
Cuffey, K. M. and Paterson, W. S. B.: The Physics of Glaciers, 4th ed., Butterworth-Heinemann, Oxford, ISBN 978-0-12-369461-4, 2010.
European Space Agency: Sentinel-2 User Handbook, ESA Standard Document, 64, https://sentinel.esa.int/documents/247904/685211/Sentinel-2_User_Handbook (last access: 14 April 2025), 2015.
Florentine, C., Sass, L., McNeil, C., Baker, E., and O'Neel, S.: How to handle glacier area change in geodetic mass balance, J. Glaciol., 69, 2169–2175, https://doi.org/10.1017/jog.2023.86, 2023.
Gascoin, S., Grizonnet, M., Bouchet, M., Salgues, G., and Hagolle, O.: Theia Snow collection: high-resolution operational snow cover maps from Sentinel-2 and Landsat-8 data, Earth Syst. Sci. Data, 11, 493–514, https://doi.org/10.5194/essd-11-493-2019, 2019.
Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D., and Moore, R.: Google Earth Engine: Planetary-scale geospatial analysis for everyone, Remote Sens. Environ., 202, 18–27, https://doi.org/10.1016/j.rse.2017.06.031, 2017.
Hall, D. K. and Riggs, G. A.: Accuracy assessment of the MODIS snow products, Hydrol. Process., 21, 1534–1547, https://doi.org/10.1002/hyp.6715, 2007.
Hastie, T., Tibshirani, R., and Friedman, J.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edn., Springer-Verlag, 763 pp., 2009.
Huang, L., Li, Z., Tian, B., Chen, Q., and Zhou, J.: Monitoring glacier zones and snow/firn line changes in the Qinghai–Tibetan Plateau using C-band SAR imagery, Remote Sens. Environ., 137, 17–30, https://doi.org/10.1016/j.rse.2013.05.016, 2013.
Hugonnet, R., McNabb, R., Berthier, E., Menounos, B., Nuth, C., Girod, L., Farinotti, D., Huss, M., Dussaillant, I., Brun, F., and Kääb, A.: Accelerated global glacier mass loss in the early twenty-first century, Nature, 592, 726–731, 731A–731P, https://doi.org/10.1038/s41586-021-03436-z, 2021.
Huss, M., Zemp, M., Joerg, P. C., and Salzmann, N.: High uncertainty in 21st century runoff projections from glacierized basins, J. Hydrol., 510, 35–48, https://doi.org/10.1016/j.jhydrol.2013.12.017, 2014.
John, A., Cannistra, A. F., Yang, K., Tan, A., Shean, D., Hille Ris Lambers, J., and Cristea, N.: High-Resolution Snow-Covered Area Mapping in Forested Mountain Ecosystems Using PlanetScope Imagery, Remote Sens., 14, 3409, https://doi.org/10.3390/rs14143409, 2022.
Littell, J. S., McAfee, S. A., and Hayward, G. D.: Alaska Snowpack Response to Climate Change: Statewide Snowfall Equivalent and Snowpack Water Scenarios, Multidisciplinary Digital Publishing Institute, 668 pp., https://doi.org/10.3390/w10050668, 2018.
Lorensen, W. E. and Cline, H. E.: Marching cubes: A high resolution 3D surface construction algorithm, SIGGRAPH Comput. Graph., 21, 163–169, https://doi.org/10.1145/37402.37422, 1987.
Masek, J. G., Vermote, E. F., Saleous, N. E., Wolfe, R., Hall, F. G., Huemmrich, K. F., Gao, F., Kutler, J., and Lim, T.-K.: A Landsat surface reflectance dataset for North America, 1990–2000, IEEE Geosci. Remote Sens. Lett., 3, 68–72, https://doi.org/10.1109/LGRS.2005.857030, 2006.
Maxwell, A. E., Warner, T. A., and Fang, F.: Implementation of machine-learning classification in remote sensing: an applied review, Int. J. Remote Sens., 39, 2784–2817, https://doi.org/10.1080/01431161.2018.1433343, 2018.
McGrath, D., Sass, L., O'Neel, S., Arendt, A., and Kienholz, C.: Hypsometric control on glacier mass balance sensitivity in Alaska and northwest Canada, Earth's Fut., 5, 324–336, https://doi.org/10.1002/2016EF000479, 2017.
McGrath, D., Sass, L., O'Neel, S., McNeil, C., Candela, S. G., Baker, E. H., and Marshall, H.-P.: Interannual snow accumulation variability on glaciers derived from repeat, spatially extensive ground-penetrating radar surveys, The Cryosphere, 12, 3617–3633, https://doi.org/10.5194/tc-12-3617-2018, 2018.
Meier, M. F.: Research on South Cascade Glacier, The Mountaineer, The Mountaineer, 40–47 pp., 1958.
Musselman, K. N., Addor, N., Vano, J. A., and Molotch, N. P.: Winter melt trends portend widespread declines in snow water resources, Nat. Clim. Chang., 11, 418–424, https://doi.org/10.1038/s41558-021-01014-9, 2021.
NASA JPL: NASADEM Merged DEM Global 1 arc second V001, NASA EOSDIS Land Processes DAAC [data set], https://doi.org/10.5067/MEaSUREs/NASADEM/NASADEM, 2020.
O'Neel, S., McNeil, C., Sass, L. C., Florentine, C., Baker, E. H., Peitzsch, E., McGrath, D., Fountain, A. G., and Fagre, D.: Reanalysis of the US Geological Survey Benchmark Glaciers: long-term insight into climate forcing of glacier mass balance, J. Glaciol., 65, 850–866, https://doi.org/10.1017/jog.2019.66, 2019.
Otsu, N.: A Threshold Selection Method from Gray-Level Histograms, IEEE Transactions on Systems, Man, and Cybernetics, SMC-9, 62–66, https://doi.org/10.1109/TSMC.1979.4310076, 1979.
Painter, T. H., Rittger, K., McKenzie, C., Slaughter, P., Davis, R. E., and Dozier, J.: Retrieval of subpixel snow covered area, grain size, and albedo from MODIS, Remote Sens. Environ., 113, 868–879, https://doi.org/10.1016/j.rse.2009.01.001, 2009.
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, 2825–2830, 2011.
Planet Labs PBC: Planet imagery product specifications, Planet Labs PBC, https://assets.planet.com/docs/Planet_Combined_Imagery_Product_Specs_letter_screen.pdf (last access: 10 April 2025), 2022.
Planet Labs PBC: Planet Application Program Interface: In Space for Life on Earth, Planet, https://developers.planet.com/docs/apis/ (last access: 14 April 2025), 2024.
Prieur, C., Rabatel, A., Thomas, J.-B., Farup, I., and Chanussot, J.: Machine Learning Approaches to Automatically Detect Glacier Snow Lines on Multi-Spectral Satellite Images, Remote Sens., 14, 3868, https://doi.org/10.3390/rs14163868, 2022.
Rastner, P., Prinz, R., Notarnicola, C., Nicholson, L., Sailer, R., Schwaizer, G., and Paul, F.: On the Automated Mapping of Snow Cover on Glaciers and Calculation of Snow Line Altitudes from Multi-Temporal Landsat Data, Remote Sens., 11, 1410, https://doi.org/10.3390/rs11121410, 2019.
RGI Consortium: Randolph Glacier Inventory – A Dataset of Global Glacier Outlines, Version 6, Boulder, Colorado USA, NSIDC: National Snow and Ice Data Center, https://doi.org/10.7265/4m1f-gd79, 2017.
Riggs, G. A., Hall, D. K., and Salomonson, V. V.: A snow index for the Landsat Thematic Mapper and Moderate Resolution Imaging Spectroradiometer, in: Proceedings of IGARSS '94 – 1994 IEEE International Geoscience and Remote Sensing Symposium, Proceedings of IGARSS '94 – 1994 IEEE International Geoscience and Remote Sensing Symposium, 1942–1944 Vol. 4, https://doi.org/10.1109/IGARSS.1994.399618, 1994.
Rittger, K., Krock, M., Kleiber, W., Bair, E. H., Brodzik, M. J., Stephenson, T. R., Rajagopalan, B., Bormann, K. J., and Painter, T. H.: Multi-sensor fusion using random forests for daily fractional snow cover at 30 m, Remote Sens. Environ., 264, 112608, https://doi.org/10.1016/j.rse.2021.112608, 2021.
Shean, D. E., Alexandrov, O., Moratto, Z. M., Smith, B. E., Joughin, I. R., Porter, C., and Morin, P.: An automated, open-source pipeline for mass production of digital elevation models (DEMs) from very-high-resolution commercial stereo satellite imagery, ISPRS J. Photogramm. Remote Sens., 116, 101–117, https://doi.org/10.1016/j.isprsjprs.2016.03.012, 2016.
Siirila-Woodburn, E. R., Rhoades, A. M., Hatchett, B. J., Huning, L. S., Szinai, J., Tague, C., Nico, P. S., Feldman, D. R., Jones, A. D., Collins, W. D., and Kaatz, L.: A low-to-no snow future and its impacts on water resources in the western United States, Nat. Rev. Earth Environ., 2, 800–819, https://doi.org/10.1038/s43017-021-00219-y, 2021.
Thanh Noi, P. and Kappas, M.: Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery, Sensors, 18, 18, https://doi.org/10.3390/s18010018, 2018.
U.S. Geological Survey: Landsat – Earth observation satellites, Landat 8, U.S. Geological Survey Fact Sheet 2019–3008, 4, 2015–3081, https://doi.org/10.3133/fs20153081, 2013.
U.S. Geological Survey Benchmark Glacier Program: McNeil, C. J., Sass, L., Florentine, C. E., Baker, E. H., Peitzsch, E. H., Whorton, E. N., Miller, Z. S., Fagre, D. B., Clark, A. M., O'Neel, S. R., and Bollen, K. E.: Glacier-Wide Mass Balance and Compiled Data Inputs (8), https://doi.org/10.5066/F7HD7SRF, 2022.
Viering, T. and Loog, M.: The Shape of Learning Curves: A Review, IEEE T. Pattern Anal. Mach. Intell., 45, 7799–7819, https://doi.org/10.1109/TPAMI.2022.3220744, 2023.
Vincent, A.: Using Remote Sensing Data Fusion Modeling to Track Seasonal Snow Cover in a Mountain Watershed, Boise State University Theses and Dissertations, https://doi.org/10.18122/td.1810.boisestate, 2021.
Walt, S. van der, Schönberger, J. L., Nunez-Iglesias, J., Boulogne, F., Warner, J. D., Yager, N., Gouillart, E., and Yu, T.: scikit-image: image processing in Python, PeerJ, 2, e453, https://doi.org/10.7717/peerj.453, 2014.
Walters, R. D., Watson, K. A., Marshall, H.-P., McNamara, J. P., and Flores, A. N.: A physiographic approach to downscaling fractional snow cover data in mountainous regions, Remote Sens. Environ., 152, 413–425, https://doi.org/10.1016/j.rse.2014.07.001, 2014.
Wang, P., Fan, E., and Wang, P.: Comparative analysis of image classification algorithms based on traditional machine learning and deep learning, Pattern Recogn. Lett., 141, 61–67, https://doi.org/10.1016/j.patrec.2020.07.042, 2021.
Zeller, L., McGrath, D., Sass, L. C., Florentine, C. E., and Downs, J.: Equilibrium line altitudes, accumulation areas, and the vulnerability of glaciers in Alaska, J. Glaciol., 71, e28, https://doi.org/10.1017/jog.2024.65, 2025.
Short summary
Tracking seasonal snow on glaciers is critical for understanding glacier health. Yet previous work has not directly compared machine learning algorithms for snow classification across satellite image products. To address this, we developed a new automated workflow for tracking seasonal snow on glaciers using several image products and machine learning models. Applying this method can help provide insights into glacier health, water resources, and the effects of climate change on snow cover.
Tracking seasonal snow on glaciers is critical for understanding glacier health. Yet previous...
