Articles | Volume 17, issue 7
https://doi.org/10.5194/tc-17-2811-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/tc-17-2811-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
13 Jul 2023
Research article |
| 13 Jul 2023
| 13 Jul 2023
Modelling point mass balance for the glaciers of the Central European Alps using machine learning techniques
Ritu Anilkumar
CORRESPONDING AUTHOR
North Eastern Space Applications Centre, Department of Space, Umiam, Ri Bhoi, Meghalaya, India
Department of Civil Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India
Rishikesh Bharti
Department of Civil Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India
Dibyajyoti Chutia
North Eastern Space Applications Centre, Department of Space, Umiam, Ri Bhoi, Meghalaya, India
Shiv Prasad Aggarwal
North Eastern Space Applications Centre, Department of Space, Umiam, Ri Bhoi, Meghalaya, India
Related authors
No articles found.
Sandeep Kumar Mondal, Rishikesh Bharti, and Kristy F. Tiampo
EGUsphere, https://doi.org/10.5194/egusphere-2023-2253, https://doi.org/10.5194/egusphere-2023-2253, 2023
Short summary
Short summary
This study explains the capabilities of C-band Synthetic Aperture Radar (SAR) system in detection of glacial deformation due to earthquakes. Due to the remote location of the Himalayan glaciers associated with harsh weather conditions and rugged topography, the method of differential interferometric SAR (DInSAR) can be very useful in studying the impact of earthquakes in the glaciated regions where field-based seismological study is extremely tough to execute.
S. Bhattacharjee, K. Lekshmi, and R. Bharti
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2021, 31–37, https://doi.org/10.5194/isprs-archives-XLIII-B3-2021-31-2021, https://doi.org/10.5194/isprs-archives-XLIII-B3-2021-31-2021, 2021
P. L. N. Raju, D. Chutia, N. Nishant, J. Goswami, and R. Anil Kumar
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B5-2020, 29–34, https://doi.org/10.5194/isprs-archives-XLIII-B5-2020-29-2020, https://doi.org/10.5194/isprs-archives-XLIII-B5-2020-29-2020, 2020
Related subject area
Discipline: Glaciers | Subject: Alpine Glaciers
Brief communication: Recent estimates of glacier mass loss for western North America from laser altimetry
The Aneto glacier's (Central Pyrenees) evolution from 1981 to 2022: ice loss observed from historic aerial image photogrammetry and remote sensing techniques
Consistent histories of anthropogenic western European air pollution preserved in different Alpine ice cores
Brief communication: Non-linear sensitivity of glacier mass balance to climate attested by temperature-index models
Halving of Swiss glacier volume since 1931 observed from terrestrial image photogrammetry
Land- to lake-terminating transition triggers dynamic thinning of a Bhutanese glacier
Brief communication: A framework to classify glaciers for water resource evaluation and management in the Southern Andes
Strong acceleration of glacier area loss in the Greater Caucasus between 2000 and 2020
Ice volume and basal topography estimation using geostatistical methods and ground-penetrating radar measurements: application to the Tsanfleuron and Scex Rouge glaciers, Swiss Alps
Significant mass loss in the accumulation area of the Adamello glacier indicated by the chronology of a 46 m ice core
Brief communication: Do 1.0, 1.5, or 2.0 °C matter for the future evolution of Alpine glaciers?
A new automatic approach for extracting glacier centerlines based on Euclidean allocation
Spatially and temporally resolved ice loss in High Mountain Asia and the Gulf of Alaska observed by CryoSat-2 swath altimetry between 2010 and 2019
Crystallographic analysis of temperate ice on Rhonegletscher, Swiss Alps
Debris cover and the thinning of Kennicott Glacier, Alaska: in situ measurements, automated ice cliff delineation and distributed melt estimates
Small-scale spatial variability in bare-ice reflectance at Jamtalferner, Austria
Numerical modeling of the dynamics of the Mer de Glace glacier, French Alps: comparison with past observations and forecasting of near-future evolution
Monitoring the seasonal changes of an englacial conduit network using repeated ground-penetrating radar measurements
Possible biases in scaling-based estimates of glacier change: a case study in the Himalaya
Spatial and temporal variations in glacier aerodynamic surface roughness during the melting season, as estimated at the August-one ice cap, Qilian mountains, China
Strong changes in englacial temperatures despite insignificant changes in ice thickness at Dôme du Goûter glacier (Mont Blanc area)
Supra-glacial debris cover changes in the Greater Caucasus from 1986 to 2014
Glacier thickness estimations of alpine glaciers using data and modeling constraints
Unravelling the evolution of Zmuttgletscher and its debris cover since the end of the Little Ice Age
Modelling the future evolution of glaciers in the European Alps under the EURO-CORDEX RCM ensemble
Robust uncertainty assessment of the spatio-temporal transferability of glacier mass and energy balance models
Impacts of topographic shading on direct solar radiation for valley glaciers in complex topography
19th century glacier retreat in the Alps preceded the emergence of industrial black carbon deposition on high-alpine glaciers
Iron oxides in the cryoconite of glaciers on the Tibetan Plateau: abundance, speciation and implications
Numerical reconstructions of the flow and basal conditions of the Rhine glacier, European Central Alps, at the Last Glacial Maximum
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.
Ixeia Vidaller, Eñaut Izagirre, Luis Mariano del Rio, Esteban Alonso-González, Francisco Rojas-Heredia, Enrique Serrano, Ana Moreno, Juan Ignacio López-Moreno, and Jesús Revuelto
The Cryosphere, 17, 3177–3192, https://doi.org/10.5194/tc-17-3177-2023, https://doi.org/10.5194/tc-17-3177-2023, 2023
Short summary
Short summary
The Aneto glacier, the largest glacier in the Pyrenees, has shown continuous surface and ice thickness losses in the last decades. In this study, we examine changes in its surface and ice thickness for 1981–2022 and the remaining ice thickness in 2020. During these 41 years, the glacier has shrunk by 64.7 %, and the ice thickness has decreased by 30.5 m on average. The mean ice thickness in 2022 was 11.9 m, compared to 32.9 m in 1981. The results highlight the critical situation of the glacier.
Anja Eichler, Michel Legrand, Theo M. Jenk, Susanne Preunkert, Camilla Andersson, Sabine Eckhardt, Magnuz Engardt, Andreas Plach, and Margit Schwikowski
The Cryosphere, 17, 2119–2137, https://doi.org/10.5194/tc-17-2119-2023, https://doi.org/10.5194/tc-17-2119-2023, 2023
Short summary
Short summary
We investigate how a 250-year history of the emission of air pollutants (major inorganic aerosol constituents, black carbon, and trace species) is preserved in ice cores from four sites in the European Alps. The observed uniform timing in species-dependent longer-term concentration changes reveals that the different ice-core records provide a consistent, spatially representative signal of the pollution history from western European countries.
Christian Vincent and Emmanuel Thibert
The Cryosphere, 17, 1989–1995, https://doi.org/10.5194/tc-17-1989-2023, https://doi.org/10.5194/tc-17-1989-2023, 2023
Short summary
Short summary
Temperature-index models have been widely used for glacier mass projections in the future. The ability of these models to capture non-linear responses of glacier mass balance (MB) to high deviations in air temperature and solid precipitation has recently been questioned by mass balance simulations employing advanced machine-learning techniques. Here, we confirmed that temperature-index models are capable of detecting non-linear responses of glacier MB to temperature and precipitation changes.
Erik Schytt Mannerfelt, Amaury Dehecq, Romain Hugonnet, Elias Hodel, Matthias Huss, Andreas Bauder, and Daniel Farinotti
The Cryosphere, 16, 3249–3268, https://doi.org/10.5194/tc-16-3249-2022, https://doi.org/10.5194/tc-16-3249-2022, 2022
Short summary
Short summary
How glaciers have responded to climate change over the last 20 years is well-known, but earlier data are much more scarce. We change this in Switzerland by using 22 000 photographs taken from mountain tops between the world wars and find a halving of Swiss glacier volume since 1931. This was done through new automated processing techniques that we created. The data are interesting for more than just glaciers, such as mapping forest changes, landslides, and human impacts on the terrain.
Yota Sato, Koji Fujita, Hiroshi Inoue, Akiko Sakai, and Karma
The Cryosphere, 16, 2643–2654, https://doi.org/10.5194/tc-16-2643-2022, https://doi.org/10.5194/tc-16-2643-2022, 2022
Short summary
Short summary
We investigate fluctuations in Bhutanese lake-terminating glaciers focusing on the dynamics change before and after proglacial lake formation at Thorthormi Glacier (TG) based on photogrammetry, satellite, and GPS surveys. The thinning rate of TG became double compared to before proglacial lake formation, and the flow velocity has also sped up considerably. Those changes would be due to the reduction in longitudinal ice compression by the detachment of the glacier terminus from the end moraine.
Nicole Schaffer and Shelley MacDonell
The Cryosphere, 16, 1779–1791, https://doi.org/10.5194/tc-16-1779-2022, https://doi.org/10.5194/tc-16-1779-2022, 2022
Short summary
Short summary
Over the last 2 decades the importance of Andean glaciers, particularly as water resources, has been recognized in both scientific literature and the public sphere. This has led to the inclusion of glaciers in environmental impact assessment and the development of glacier protection laws. We propose three categories that group glaciers based on their environmental sensitivity to hopefully help facilitate the effective application of these measures and evaluation of water resources in general.
Levan G. Tielidze, Gennady A. Nosenko, Tatiana E. Khromova, and Frank Paul
The Cryosphere, 16, 489–504, https://doi.org/10.5194/tc-16-489-2022, https://doi.org/10.5194/tc-16-489-2022, 2022
Short summary
Short summary
The new Caucasus glacier inventory derived from manual delineation of glacier outlines based on medium-resolution (Landsat, Sentinel) and high-resolution (SPOT) satellite imagery shows the accelerated glacier area loss over the last 2 decades (2000–2020). This new glacier inventory will improve our understanding of climate change impacts at a regional scale and support related modelling studies by providing high-quality validation data.
Alexis Neven, Valentin Dall'Alba, Przemysław Juda, Julien Straubhaar, and Philippe Renard
The Cryosphere, 15, 5169–5186, https://doi.org/10.5194/tc-15-5169-2021, https://doi.org/10.5194/tc-15-5169-2021, 2021
Short summary
Short summary
We present and compare different geostatistical methods for underglacial bedrock interpolation. Variogram-based interpolations are compared with a multipoint statistics approach on both test cases and real glaciers. Using the modeled bedrock, the ice volume for the Scex Rouge and Tsanfleuron glaciers (Swiss Alps) was estimated to be 113.9 ± 1.6 million cubic meters. Complex karstic geomorphological features are reproduced and can be used to improve the precision of underglacial flow estimation.
Daniela Festi, Margit Schwikowski, Valter Maggi, Klaus Oeggl, and Theo Manuel Jenk
The Cryosphere, 15, 4135–4143, https://doi.org/10.5194/tc-15-4135-2021, https://doi.org/10.5194/tc-15-4135-2021, 2021
Short summary
Short summary
In our study we dated a 46 m deep ice core retrieved from the Adamello glacier (Central Italian Alps). We obtained a timescale combining the results of radionuclides 210Pb and 137Cs with annual layer counting derived from pollen and refractory black carbon concentrations. Our results indicate that the surface of the glacier is older than the drilling date of 2016 by about 20 years, therefore revealing that the glacier is at high risk of collapsing under current climate warming conditions.
Loris Compagno, Sarah Eggs, Matthias Huss, Harry Zekollari, and Daniel Farinotti
The Cryosphere, 15, 2593–2599, https://doi.org/10.5194/tc-15-2593-2021, https://doi.org/10.5194/tc-15-2593-2021, 2021
Short summary
Short summary
Recently, discussions have focused on the difference in limiting the increase in global average temperatures to below 1.0, 1.5, or 2.0 °C compared to preindustrial levels. Here, we assess the impacts that such different scenarios would have on both the future evolution of glaciers in the European Alps and the water resources they provide. Our results show that the different temperature targets have important implications for the changes predicted until 2100.
Dahong Zhang, Xiaojun Yao, Hongyu Duan, Shiyin Liu, Wanqin Guo, Meiping Sun, and Dazhi Li
The Cryosphere, 15, 1955–1973, https://doi.org/10.5194/tc-15-1955-2021, https://doi.org/10.5194/tc-15-1955-2021, 2021
Short summary
Short summary
Glacier centerlines are crucial input for many glaciological applications. We propose a new algorithm to derive glacier centerlines and implement the corresponding program in Python language. Application of this method to 48 571 glaciers in the second Chinese glacier inventory automatically yielded the corresponding glacier centerlines with an average computing time of 20.96 s, a success rate of 100 % and a comprehensive accuracy of 94.34 %.
Livia Jakob, Noel Gourmelen, Martin Ewart, and Stephen Plummer
The Cryosphere, 15, 1845–1862, https://doi.org/10.5194/tc-15-1845-2021, https://doi.org/10.5194/tc-15-1845-2021, 2021
Short summary
Short summary
Glaciers and ice caps are currently the largest contributor to sea level rise. Global monitoring of these regions is a challenging task, and significant differences remain between current estimates. This study looks at glacier changes in High Mountain Asia and the Gulf of Alaska using a new technique, which for the first time makes the use of satellite radar altimetry for mapping ice mass loss over mountain glacier regions possible.
Sebastian Hellmann, Johanna Kerch, Ilka Weikusat, Andreas Bauder, Melchior Grab, Guillaume Jouvet, Margit Schwikowski, and Hansruedi Maurer
The Cryosphere, 15, 677–694, https://doi.org/10.5194/tc-15-677-2021, https://doi.org/10.5194/tc-15-677-2021, 2021
Short summary
Short summary
We analyse the orientation of ice crystals in an Alpine glacier and compare this orientation with the ice flow direction. We found that the crystals orient in the direction of the largest stress which is in the flow direction in the upper parts of the glacier and in the vertical direction for deeper zones of the glacier. The grains cluster around this maximum stress direction, in particular four-point maxima, most likely as a result of recrystallisation under relatively warm conditions.
Leif S. Anderson, William H. Armstrong, Robert S. Anderson, and Pascal Buri
The Cryosphere, 15, 265–282, https://doi.org/10.5194/tc-15-265-2021, https://doi.org/10.5194/tc-15-265-2021, 2021
Short summary
Short summary
Many glaciers are thinning rapidly beneath debris cover (loose rock) that reduces melt, including Kennicott Glacier in Alaska. This contradiction has been explained by melt hotspots, such as ice cliffs, scattered within the debris cover. However, at Kennicott Glacier declining ice flow explains the rapid thinning. Through this study, Kennicott Glacier is now the first glacier in Alaska, and the largest glacier globally, where melt across its debris-covered tongue has been rigorously quantified.
Lea Hartl, Lucia Felbauer, Gabriele Schwaizer, and Andrea Fischer
The Cryosphere, 14, 4063–4081, https://doi.org/10.5194/tc-14-4063-2020, https://doi.org/10.5194/tc-14-4063-2020, 2020
Short summary
Short summary
When glaciers become snow-free in summer, darker glacier ice is exposed. The ice surface is darker than snow and absorbs more radiation, which increases ice melt. We measured how much radiation is reflected at different wavelengths in the ablation zone of Jamtalferner, Austria. Due to impurities and water on the ice surface there are large variations in reflectance. Landsat 8 and Sentinel-2 surface reflectance products do not capture the full range of reflectance found on the glacier.
Vincent Peyaud, Coline Bouchayer, Olivier Gagliardini, Christian Vincent, Fabien Gillet-Chaulet, Delphine Six, and Olivier Laarman
The Cryosphere, 14, 3979–3994, https://doi.org/10.5194/tc-14-3979-2020, https://doi.org/10.5194/tc-14-3979-2020, 2020
Short summary
Short summary
Alpine glaciers are retreating at an accelerating rate in a warming climate. Numerical models allow us to study and anticipate these changes, but the performance of a model is difficult to evaluate. So we compared an ice flow model with the long dataset of observations obtained between 1979 and 2015 on Mer de Glace (Mont Blanc area). The model accurately reconstructs the past evolution of the glacier. We simulate the future evolution of Mer de Glace; it could retreat by 2 to 6 km by 2050.
Gregory Church, Melchior Grab, Cédric Schmelzbach, Andreas Bauder, and Hansruedi Maurer
The Cryosphere, 14, 3269–3286, https://doi.org/10.5194/tc-14-3269-2020, https://doi.org/10.5194/tc-14-3269-2020, 2020
Short summary
Short summary
In this field study, we repeated ground-penetrating radar measurements over an active englacial channel network that transports meltwater through the glacier. We successfully imaged the englacial meltwater pathway and were able to delimitate the channel's shape. Meltwater from the glacier can impact the glacier's dynamics if it reaches the ice–bed interface, and therefore monitoring these englacial drainage networks is important to understand how these networks behave throughout a season.
Argha Banerjee, Disha Patil, and Ajinkya Jadhav
The Cryosphere, 14, 3235–3247, https://doi.org/10.5194/tc-14-3235-2020, https://doi.org/10.5194/tc-14-3235-2020, 2020
Short summary
Short summary
Simple models of glacier dynamics based on volume–area scaling underestimate climate sensitivity and response time of glaciers. Consequently, they may predict a faster response and a smaller long-term glacier loss. These biases in scaling models are established theoretically and are analysed in detail by simulating the step response of a set of 703 Himalayan glaciers separately by three different models: a scaling model, a 2-D shallow-ice approximation model, and a linear-response model.
Junfeng Liu, Rensheng Chen, and Chuntan Han
The Cryosphere, 14, 967–984, https://doi.org/10.5194/tc-14-967-2020, https://doi.org/10.5194/tc-14-967-2020, 2020
Short summary
Short summary
Glacier surface roughness during melting season was observed by manual and automatic photogrammetry. Surface roughness was larger at the snow and ice transition zone than in fully snow- or ice-covered areas. Persistent snowfall and rainfall both reduce surface roughness. High or rising turbulent heat as a component of surface energy balance tended to produce a smooth ice surface; low or decreasing turbulent heat tended to produce a rougher surface.
Christian Vincent, Adrien Gilbert, Bruno Jourdain, Luc Piard, Patrick Ginot, Vladimir Mikhalenko, Philippe Possenti, Emmanuel Le Meur, Olivier Laarman, and Delphine Six
The Cryosphere, 14, 925–934, https://doi.org/10.5194/tc-14-925-2020, https://doi.org/10.5194/tc-14-925-2020, 2020
Short summary
Short summary
We observed very low glacier thickness changes over the last decades at very-high-elevation glaciated areas on Mont Blanc. Conversely, measurements performed in deep boreholes since 1994 reveal strong changes in englacial temperature reaching 1.5 °C at a depth of 50 m. We conclude that at such very high elevations, current changes in climate do not lead to visible changes in glacier thickness but cause invisible changes within the glacier in terms of englacial temperatures.
Levan G. Tielidze, Tobias Bolch, Roger D. Wheate, Stanislav S. Kutuzov, Ivan I. Lavrentiev, and Michael Zemp
The Cryosphere, 14, 585–598, https://doi.org/10.5194/tc-14-585-2020, https://doi.org/10.5194/tc-14-585-2020, 2020
Short summary
Short summary
We present data of supra-glacial debris cover for 659 glaciers across the Greater Caucasus based on satellite images from the years 1986, 2000 and 2014. We combined semi-automated methods for mapping the clean ice with manual digitization of debris-covered glacier parts and calculated supra-glacial debris-covered area as the residual between these two maps. The distribution of the supra-glacial debris cover differs between northern and southern and between western, central and eastern Caucasus.
Lisbeth Langhammer, Melchior Grab, Andreas Bauder, and Hansruedi Maurer
The Cryosphere, 13, 2189–2202, https://doi.org/10.5194/tc-13-2189-2019, https://doi.org/10.5194/tc-13-2189-2019, 2019
Short summary
Short summary
We have developed a novel procedure for glacier thickness estimations that combines traditional glaciological modeling constraints with ground-truth data, for example, those obtained with ground-penetrating radar (GPR) measurements. This procedure is very useful for determining ice volume when only limited data are available. Furthermore, we outline a strategy for acquiring GPR data on glaciers, such that the cost/benefit ratio is optimized.
Nico Mölg, Tobias Bolch, Andrea Walter, and Andreas Vieli
The Cryosphere, 13, 1889–1909, https://doi.org/10.5194/tc-13-1889-2019, https://doi.org/10.5194/tc-13-1889-2019, 2019
Short summary
Short summary
Debris can partly protect glaciers from melting. But many debris-covered glaciers change similar to debris-free glaciers. To better understand the debris influence we investigated 150 years of evolution of Zmutt Glacier in Switzerland. We found an increase in debris extent over time and a link to glacier flow velocity changes. We also found an influence of debris on the melt locally, but only a small volume change reduction over the whole glacier, also because of the influence of ice cliffs.
Harry Zekollari, Matthias Huss, and Daniel Farinotti
The Cryosphere, 13, 1125–1146, https://doi.org/10.5194/tc-13-1125-2019, https://doi.org/10.5194/tc-13-1125-2019, 2019
Short summary
Short summary
Glaciers in the European Alps play an important role in the hydrological cycle, act as a source for hydroelectricity and have a large touristic importance. We model the future evolution of all glaciers in the Alps with a novel model that combines both ice flow and melt processes. We find that under a limited warming scenario about one-third of the present-day ice volume will still be present by the end of the century, while under strong warming more than 90 % of the volume will be lost by 2100.
Tobias Zolles, Fabien Maussion, Stephan Peter Galos, Wolfgang Gurgiser, and Lindsey Nicholson
The Cryosphere, 13, 469–489, https://doi.org/10.5194/tc-13-469-2019, https://doi.org/10.5194/tc-13-469-2019, 2019
Short summary
Short summary
A mass and energy balance model was subjected to sensitivity and uncertainty analysis on two different Alpine glaciers. The global sensitivity analysis allowed for a mass balance measurement independent assessment of the model sensitivity and functioned as a reduction of the model free parameter space. A novel approach of a multi-objective optimization estimates the uncertainty of the simulated mass balance and the energy fluxes. The final model uncertainty is up to 1300 kg m−3 per year.
Matthew Olson and Summer Rupper
The Cryosphere, 13, 29–40, https://doi.org/10.5194/tc-13-29-2019, https://doi.org/10.5194/tc-13-29-2019, 2019
Short summary
Short summary
Solar radiation is the largest energy input for most alpine glaciers. However, many models oversimplify the influence of topographic shading. Also, no systematic studies have explored the variable impact of shading on glacier ice. We find that shading can significantly impact modeled solar radiation, particularly at low elevations, at high latitudes, and for glaciers with a north/south orientation. Excluding the effects of shading will overestimate modeled solar radiation for alpine glaciers.
Michael Sigl, Nerilie J. Abram, Jacopo Gabrieli, Theo M. Jenk, Dimitri Osmont, and Margit Schwikowski
The Cryosphere, 12, 3311–3331, https://doi.org/10.5194/tc-12-3311-2018, https://doi.org/10.5194/tc-12-3311-2018, 2018
Short summary
Short summary
The fast retreat of Alpine glaciers since the mid-19th century documented in photographs is used as a symbol for the human impact on global climate, yet the key driving forces remain elusive. Here we argue that not industrial soot but volcanic eruptions were responsible for an apparently accelerated deglaciation starting in the 1850s. Our findings support a negligible role of human activity in forcing glacier recession at the end of the Little Ice Age, highlighting the role of natural drivers.
Zhiyuan Cong, Shaopeng Gao, Wancang Zhao, Xin Wang, Guangming Wu, Yulan Zhang, Shichang Kang, Yongqin Liu, and Junfeng Ji
The Cryosphere, 12, 3177–3186, https://doi.org/10.5194/tc-12-3177-2018, https://doi.org/10.5194/tc-12-3177-2018, 2018
Short summary
Short summary
Cryoconites from glaciers on the Tibetan Plateau and surrounding area were studied for iron oxides. We found that goethite is the predominant iron oxide form. Using the abundance, speciation and optical properties of iron oxides, the total light absorption was quantitatively attributed to goethite, hematite, black carbon and organic matter. Such findings are essential to understand the relative significance of anthropogenic and natural impacts.
Denis Cohen, Fabien Gillet-Chaulet, Wilfried Haeberli, Horst Machguth, and Urs H. Fischer
The Cryosphere, 12, 2515–2544, https://doi.org/10.5194/tc-12-2515-2018, https://doi.org/10.5194/tc-12-2515-2018, 2018
Short summary
Short summary
As part of an integrative study about the safety of repositories for radioactive waste under ice age conditions in Switzerland, we modeled the flow of ice of the Rhine glacier at the Last Glacial Maximum to determine conditions at the ice–bed interface. Results indicate that portions of the ice lobes were at the melting temperature and ice was sliding, two conditions necessary for erosion by glacier. Conditions at the bed of the ice lobes were affected by climate and also by topography.
Cited articles
Altmann, A., Toloşi, L., Sander, O., and Lengauer, T.: Permutation
importance: a corrected feature importance measure, Bioinformatics, 26,
1340–1347, https://doi.org/10.1093/bioinformatics/btq134, 2010. a, b
Anilkumar, R., Bharti, R., and Chutia, D.: Point Mass Balance Regression using Deep Neural Networks: A Transfer Learning Approach, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-5317, https://doi.org/10.5194/egusphere-egu22-5317, 2022. a
Bair, E. H., Abreu Calfa, A., Rittger, K., and Dozier, J.: Using machine learning for real-time estimates of snow water equivalent in the watersheds of Afghanistan, The Cryosphere, 12, 1579–1594, https://doi.org/10.5194/tc-12-1579-2018, 2018. a
Bash, E. A., Moorman, B. J., and Gunther, A.: Detecting Short-Term Surface Melt
on an Arctic Glacier Using UAV Surveys, Remote Sensing, 10, 1547,
https://doi.org/10.3390/rs10101547, 2018. a
Bolibar, J., Rabatel, A., Gouttevin, I., Galiez, C., Condom, T., and Sauquet, E.: Deep learning applied to glacier evolution modelling, The Cryosphere, 14, 565–584, https://doi.org/10.5194/tc-14-565-2020, 2020. a, b, c, d
Bolibar, J., Rabatel, A., Gouttevin, I., Zekollari, H., and Galiez, C.:
Nonlinear sensitivity of glacier mass balance to future climate change
unveiled by deep learning, Nat. Commun., 13, 409,
https://doi.org/10.1038/s41467-022-28033-0, 2022. a, b
Braithwaite, R. J.: Can the Mass Balance of a Glacier be Estimated from its
Equilibrium-Line Altitude?, J. Glaciol., 30, 364–368,
https://doi.org/10.3189/S0022143000006237, 1984. a
Breiman, L.: Bagging predictors, Machine Learning, 24, 123–140,
https://doi.org/10.1007/BF00058655, 1996. a
Breiman, L.: Random forests, Machine Learning, 45, 5–32,
https://doi.org/10.1023/A:1010933404324, 2001. a
Carturan, L., Cazorzi, F., and Dalla Fontana, G.: Enhanced estimation of
glacier mass balance in unsampled areas by means of topographic data, Ann. Glaciol., 50, 37–46, https://doi.org/10.3189/172756409787769519, 2009. a
Chen, Y., Sharma, S., Zhou, X., Yang, K., Li, X., Niu, X., Hu, X., and Khadka,
N.: Spatial performance of multiple reanalysis precipitation datasets on the
southern slope of central Himalaya, Atmos. Res., 250, 105365,
https://doi.org/10.1016/j.atmosres.2020.105365, 2021. a, b
Chi, J. and Kim, H.-C.: Prediction of Arctic Sea Ice Concentration Using a
Fully Data Driven Deep Neural Network, Remote Sensing, 9, 1305,
https://doi.org/10.3390/rs9121305, 2017. a
Cortes, C. and Vapnik, V.: Support-vector networks, Machine Learning, 20,
273–297, https://doi.org/10.1007/BF00994018, 1995. a
Cucchi, M., Weedon, G. P., Amici, A., Bellouin, N., Lange, S., Müller Schmied, H., Hersbach, H., and Buontempo, C.: WFDE5: bias-adjusted ERA5 reanalysis data for impact studies, Earth Syst. Sci. Data, 12, 2097–2120, https://doi.org/10.5194/essd-12-2097-2020, 2020. a
Dietterich, T. G.: An experimental comparison of three methods for constructing
ensembles of decision trees: Bagging, boosting, and randomization, Machine
Learning, 40, 139–157, https://doi.org/10.1023/A:1007607513941, 2000. a
Dobhal, D., Pratap, B., Bhambri, R., and Mehta, M.: Mass balance and
morphological changes of Dokriani Glacier (1992–2013), Garhwal Himalaya,
India, Quaternary Science Advances, 4, 100033,
https://doi.org/10.1016/j.qsa.2021.100033, 2021. a
Fernández-Delgado, M., Cernadas, E., Barro, S., and Amorim, D.: Do We Need
Hundreds of Classifiers to Solve Real World Classification Problems?, J.
Mach. Learn. Res., 15, 3133–3181, 2014. a
Friedman, J. H.: Greedy function approximation: a gradient boosting machine,
Ann. Stat., 29, 1189–1232, https://doi.org/10.1214/aos/1013203451, 2001. a
Gabbi, J., Carenzo, M., Pellicciotti, F., Bauder, A., and Funk, M.: A
comparison of empirical and physically based glacier surface melt models for
long-term simulations of glacier response, J. Glaciol., 60,
1140–1154, https://doi.org/10.3189/2014JoG14J011, 2014. a, b
Gerbaux, M., Genthon, C., Etchevers, P., Vincent, C., and Dedieu, J.: Surface
mass balance of glaciers in the French Alps: distributed modeling and
sensitivity to climate change, J. Glaciol., 51, 561–572,
https://doi.org/10.3189/172756505781829133, 2005. a
Grinsztajn, L., Oyallon, E., and Varoquaux, G.: Why do tree-based models still
outperform deep learning on tabular data?, in: Advances in Neural Information Processing Systems, edited by: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., and Oh, A., Curran Associates, Inc., vol. 35, 507–520, https://proceedings.neurips.cc/paper_files/paper/2022/file/0378c7692da36807bdec87ab043cdadc-Paper-Datasets_and_Benchmarks.pdf (last access: 7 July 2023), 2022. a, b
Guidicelli, M., Huss, M., Gabella, M., and Salzmann, N.: Spatio-temporal reconstruction of winter glacier mass balance in the Alps, Scandinavia, Central Asia and western Canada (1981–2019) using climate reanalyses and machine learning, The Cryosphere, 17, 977–1002, https://doi.org/10.5194/tc-17-977-2023, 2023. a
Guo, X., Chen, Y., Liu, X., and Zhao, Y.: Extraction of snow cover from
high-resolution remote sensing imagery using deep learning on a small
dataset, Remote Sens. Lett., 11, 66–75,
https://doi.org/10.1080/2150704X.2019.1686548, 2020. a
Haq, M. A., Jain, K., and Menon, K.: Modelling of Gangotri glacier thickness
and volume using an artificial neural network, Int. J.
Remote Sens., 35, 6035–6042, https://doi.org/10.1080/01431161.2014.943322, 2014. a
Haq, M. A., Azam, M. F., and Vincent, C.: Efficiency of artificial neural
networks for glacier ice-thickness estimation: a case study in western
Himalaya, India, J. Glaciol., 67, 671–684,
https://doi.org/10.1017/jog.2021.19, 2021. a
Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A.,
Muñoz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., Simmons,
A., Soci, C., Abdalla, S., Abellan, X., Balsamo, G., Bechtold, P., Biavati,
G., Bidlot, J., Bonavita, M., De Chiara, G., Dahlgren, P., Dee, D.,
Diamantakis, M., Dragani, R., Flemming, J., Forbes, R., Fuentes, M., Geer,
A., Haimberger, L., Healy, S., Hogan, R. J., Hólm, E., Janisková, M.,
Keeley, S., Laloyaux, P., Lopez, P., Lupu, C., Radnoti, G., de Rosnay, P.,
Rozum, I., Vamborg, F., Villaume, S., and Thépaut, J.-N.: The ERA5 global
reanalysis, Q. J. Roy. Meteor. Soc., 146,
1999–2049, https://doi.org/10.1002/qj.3803, 2020. a
Hoinkes, H. C.: Glacier Variation and Weather, J. Glaciol., 7,
3–18, https://doi.org/10.3189/S0022143000020384, 1968. a, b
Hornik, K.: Approximation capabilities of multilayer feedforward networks,
Neural Networks, 4, 251–257,
https://doi.org/10.1016/0893-6080(91)90009-T, 1991. a
Huss, M., Farinotti, D., Bauder, A., and Funk, M.: Modelling runoff from highly
glacierized alpine drainage basins in a changing climate, Hydrol.
Process., 22, 3888–3902, https://doi.org/10.1002/hyp.7055, 2008. a
Ismail, M. F., Bogacki, W., Disse, M., Schäfer, M., and Kirschbauer, L.: Estimating degree-day factors of snow based on energy flux components, The Cryosphere, 17, 211–231, https://doi.org/10.5194/tc-17-211-2023, 2023. a, b
Jouvet, G., Cordonnier, G., Kim, B., Lüthi, M., Vieli, A., and Aschwanden, A.:
Deep learning speeds up ice flow modelling by several orders of magnitude,
J. Glaciol., 68, 651–664, https://doi.org/10.1017/jog.2021.120, 2021. a
Kan, X., Zhang, Y., Zhu, L., Xiao, L., Wang, J., Tian, W., and Tan, H.: Snow
cover mapping for mountainous areas by fusion of MODIS L1B and geographic
data based on stacked denoising auto-encoders, Computers, Materials & Continua, 57, 49–68, https://doi.org/10.32604/cmc.2018.02376, 2018. a
King, F., Erler, A. R., Frey, S. K., and Fletcher, C. G.: Application of machine learning techniques for regional bias correction of snow water equivalent estimates in Ontario, Canada, Hydrol. Earth Syst. Sci., 24, 4887–4902, https://doi.org/10.5194/hess-24-4887-2020, 2020. a
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, arXiv
[preprint], https://doi.org/10.48550/arxiv.1412.6980, 22 December 2014. a
Kuhn, M., Dreiseitl, E., Hofinger, S., Markl, G., Span, N., and Kaser, G.:
Measurements and models of the mass balance of hintereisferner, Geogr.
Ann. A, 81, 659–670,
https://onlinelibrary.wiley.com/doi/abs/10.1111/1468-0459.00094 (last access: 7 July 2023), 1999. a
Lefauconnier, B. and Hagen, J.: Glaciers and Climate in Svalbard: Statistical
Analysis and Reconstruction of the Brøggerbreen Mass Balance for the Last 77
Years, Ann. Glaciol., 14, 148–152, https://doi.org/10.3189/S0260305500008466,
1990. a
Le Meur, E., Gerbaux, M., Schäfer, M., and Vincent, C.: Disappearance of an
Alpine glacier over the 21st Century simulated from modeling its future
surface mass balance, Earth Planet. Sc. Lett., 261, 367–374,
https://doi.org/10.1016/j.epsl.2007.07.022, 2007. a
Li, J., Wang, C., Wang, S., Zhang, H., Fu, Q., and Wang, Y.: Gaofen-3 sea ice
detection based on deep learning, in: 2017 Progress in Electromagnetics
Research Symposium – Fall (PIERS – FALL), Nanyang Technological Univeiisty, Singapore, 19–22 November 2017, 933–939,
https://doi.org/10.1109/PIERS-FALL.2017.8293267, 2017. a
Liu, L.: A Review of Deep Learning for Cryospheric Studies, chap. 17,
John Wiley and Sons, Ltd, 258–268,
https://doi.org/10.1002/9781119646181.ch17, 2021. a
Lliboutry, L.: Multivariate Statistical Analysis of Glacier Annual Balances,
J. Glaciol., 13, 371–392, https://doi.org/10.3189/S0022143000023169, 1974. a
Lu, Y., Zhang, Z., Shangguan, D., and Yang, J.: Novel Machine Learning Method
Integrating Ensemble Learning and Deep Learning for Mapping Debris-Covered
Glaciers, Remote Sensing, 13, 2595, https://doi.org/10.3390/rs13132595, 2021. a
Manciati, C., Villacís, M., Taupin, J.-D., Cadier, E., Galárraga-Sánchez,
R., and Cáceres, B.: Empirical mass balance modelling of South American
tropical glaciers: case study of Antisana volcano, Ecuador, Hydrolog.
Sci. J., 59, 1519–1535, https://doi.org/10.1080/02626667.2014.888490, 2014. a
Masiokas, M. H., Christie, D. A., Le Quesne, C., Pitte, P., Ruiz, L., Villalba, R., Luckman, B. H., Berthier, E., Nussbaumer, S. U., González-Reyes, Á., McPhee, J., and Barcaza, G.: Reconstructing the annual mass balance of the Echaurren Norte glacier (Central Andes, 33.5∘ S) using local and regional hydroclimatic data, The Cryosphere, 10, 927–940, https://doi.org/10.5194/tc-10-927-2016, 2016. a
Mattews, T. and Hodgkins, R.: Interdecadal variability of degree-day factors on
Vestari Hagafellsjökull (Langjökull, Iceland) and the importance of
threshold air temperatures, J. Glaciol., 62, 310–322,
https://doi.org/10.1017/jog.2016.21, 2016. a
Maussion, F., Butenko, A., Champollion, N., Dusch, M., Eis, J., Fourteau, K., Gregor, P., Jarosch, A. H., Landmann, J., Oesterle, F., Recinos, B., Rothenpieler, T., Vlug, A., Wild, C. T., and Marzeion, B.: The Open Global Glacier Model (OGGM) v1.1, Geosci. Model Dev., 12, 909–931, https://doi.org/10.5194/gmd-12-909-2019, 2019. a
McCulloch, W. S. and Pitts, W.: A logical calculus of the ideas immanent in
nervous activity, B. Math. Biophys., 5, 115–133,
https://doi.org/10.1007/BF02478259, 1943. a
Mohajerani, Y., Jeong, S., Scheuchl, B., Velicogna, I., Rignot, E., and
Milillo, P.: Automatic delineation of glacier grounding lines in differential
interferometric synthetic-aperture radar data using deep learning, Scientific
Reports, 11, 4992, https://doi.org/10.1038/s41598-021-84309-3, 2021. a
Moya Quiroga, V., Mano, A., Asaoka, Y., Kure, S., Udo, K., and Mendoza, J.: Snow glacier melt estimation in tropical Andean glaciers using artificial neural networks, Hydrol. Earth Syst. Sci., 17, 1265–1280, https://doi.org/10.5194/hess-17-1265-2013, 2013. a
Muñoz Sabater, J.: ERA5-Land hourly data from 1950 to present, Copernicus Climate Change Service (C3S) Climate Data Store (CDS) [data set], https://doi.org/10.24381/cds.e2161bac, 2019. a, b, c
Muñoz-Sabater, J., Dutra, E., Agustí-Panareda, A., Albergel, C., Arduini, G., Balsamo, G., Boussetta, S., Choulga, M., Harrigan, S., Hersbach, H., Martens, B., Miralles, D. G., Piles, M., Rodríguez-Fernández, N. J., Zsoter, E., Buontempo, C., and Thépaut, J.-N.: ERA5-Land: a state-of-the-art global reanalysis dataset for land applications, Earth Syst. Sci. Data, 13, 4349–4383, https://doi.org/10.5194/essd-13-4349-2021, 2021. a
Natekin, A. and Knoll, A.: Gradient boosting machines, a tutorial, Front.
Neurorobotics, 7, 21, https://doi.org/10.3389/fnbot.2013.00021, 2013. a
Nijhawan, R., Das, J., and Raman, B.: A hybrid of deep learning and
hand-crafted features based approach for snow cover mapping, Int.
J. Remote Sens., 40, 759–773, https://doi.org/10.1080/01431161.2018.1519277,
2019. a
Pratap, B., Dobhal, D. P., Bhambri, R., Mehta, M., and Tewari, V. C.: Four
decades of glacier mass balance observations in the Indian Himalaya, Reg.
Environ. Change, 16, 643–658,
https://doi.org/10.1007/s10113-015-0791-4, 2016. a
Rabatel, A., Dedieu, J. P., and Vincent, C.: Spatio-temporal changes in
glacier-wide mass balance quantified by optical remote sensing on 30 glaciers
in the French Alps for the period 1983–2014, J. Glaciol., 62,
1153–1166, https://doi.org/10.1017/jog.2016.113, 2016. a
Radić, V. and Hock, R.: Regionally differentiated contribution of mountain
glaciers and ice caps to future sea-level rise, Nat. Geosci,, 4, 91–94,
https://doi.org/10.1038/ngeo1052, 2011. a
Radić, V., Bliss, A., Beedlow, A. C., Hock, R., Miles, E., and Cogley,
J. G.: Regional and global projections of twenty-first century glacier mass
changes in response to climate scenarios from global climate models, Clim.
Dynam., 42, 37–58, 2014. a
Rasouli, K., Hsieh, W. W., and Cannon, A. J.: Daily streamflow forecasting by
machine learning methods with weather and climate inputs, J.
Hydrol., 414-415, 284–293,
https://doi.org/10.1016/j.jhydrol.2011.10.039, 2012. a
Rasp, S., Pritchard, M. S., and Gentine, P.: Deep learning to represent subgrid
processes in climate models, P. Natl. Acad. Sci. USA,
115, 9684–9689, https://doi.org/10.1073/pnas.1810286115, 2018. a
RGI: Randolph Glacier Inventory (RGI) – A Dataset of Global Glacier Outlines:
Version 6.0. Technical Report, https://doi.org/10.7265/N5-RGI-60, 2017. a, b
Roberts, D. R., Bahn, V., Ciuti, S., Boyce, M. S., Elith, J., Guillera-Arroita,
G., Hauenstein, S., Lahoz-Monfort, J. J., Schröder, B., Thuiller, W.,
Warton, D. I., Wintle, B. A., Hartig, F., and Dormann, C. F.:
Cross-validation strategies for data with temporal, spatial, hierarchical, or
phylogenetic structure, Ecography, 40, 913–929,
https://doi.org/10.1111/ecog.02881, 2017. a
Sauter, T., Arndt, A., and Schneider, C.: COSIPY v1.3 – an open-source coupled snowpack and ice surface energy and mass balance model, Geosci. Model Dev., 13, 5645–5662, https://doi.org/10.5194/gmd-13-5645-2020, 2020. a
Schultz, M. G., Betancourt, C., Gong, B., Kleinert, F., Langguth, M., Leufen,
L. H., Mozaffari, A., and Stadtler, S.: Can deep learning beat numerical
weather prediction?, Philosophical Transactions of the Royal Society A:
Mathematical, Physical and Engineering Sciences, 379, 20200097,
https://doi.org/10.1098/rsta.2020.0097, 2021. a
Seidou, O., Ouarda, T. B. M. J., Bilodeau, L., Hessami, M., St-Hilaire, A., and
Bruneau, P.: Modeling ice growth on Canadian lakes using artificial neural
networks, Water Resour. Res., 42, W11407,
https://doi.org/10.1029/2005WR004622, 2006. a
Shean, D. E., Bhushan, S., Montesano, P., Rounce, D. R., Arendt, A., and
Osmanoglu, B.: A Systematic, Regional Assessment of High Mountain Asia
Glacier Mass Balance, Frontiers in Earth Science, 7, 363,
https://doi.org/10.3389/feart.2019.00363, 2020. a
Shwartz-Ziv, R. and Armon, A.: Tabular Data: Deep Learning is Not All You
Need, arXiv [preprint], https://doi.org/10.48550/arXiv.2106.03253,
6 June 2021. a, b
Steiner, D., Walter, A., and Zumbühl, H.: The application of a non-linear
back-propagation neural network to study the mass balance of Grosse
Aletschgletscher, Switzerland, J. Glaciol., 51, 313–323,
https://doi.org/10.3189/172756505781829421, 2005. a, b, c, d
Thibert, E., Blanc, R., Vincent, C., and Eckert, N.: Glaciological and
volumetric mass-balance measurements: error analysis over 51 years for
Glacier de Sarennes, French Alps, J. Glaciol., 54, 522–532,
https://doi.org/10.3189/002214308785837093, 2008. a
Trantow, T. and Herzfeld, U. C.: Spatiotemporal mapping of a large mountain
glacier from CryoSat-2 altimeter data: surface elevation and elevation change
of Bering Glacier during surge (2011–2014), Int. J. Remote
Sens., 37, 2962–2989, https://doi.org/10.1080/01431161.2016.1187318, 2016. a
Tshering, P. and Fujita, K.: First in situ record of decadal glacier mass
balance (2003–2014) from the Bhutan Himalaya, Ann. Glaciol., 57,
289–294, https://doi.org/10.3189/2016AoG71A036, 2016. a
Van Tricht, L., Huybrechts, P., Van Breedam, J., Vanhulle, A., Van Oost, K., and Zekollari, H.: Estimating surface mass balance patterns from unoccupied aerial vehicle measurements in the ablation area of the Morteratsch–Pers glacier complex (Switzerland), The Cryosphere, 15, 4445–4464, https://doi.org/10.5194/tc-15-4445-2021, 2021. a
Vapnik, V.: The Nature of Statistical Learning Theory, Springer Science &
Business Media, https://doi.org/10.1007/978-1-4757-2440-0, 1999. a
Vincent, C., Soruco, A., Azam, M. F., Basantes-Serrano, R., Jackson, M.,
Kjøllmoen, B., Thibert, E., Wagnon, P., Six, D., Rabatel, A., Ramanathan,
A., Berthier, E., Cusicanqui, D., Vincent, P., and Mandal, A.: A Nonlinear
Statistical Model for Extracting a Climatic Signal From Glacier Mass Balance
Measurements, J. Geophys. Res.-Earth, 123,
2228–2242, https://doi.org/10.1029/2018JF004702, 2018. a
Wang, J., Yuan, Q., Shen, H., Liu, T., Li, T., Yue, L., Shi, X., and Zhang, L.:
Estimating snow depth by combining satellite data and ground-based
observations over Alaska: A deep learning approach, J. Hydrol.,
585, 124828, https://doi.org/10.1016/j.jhydrol.2020.124828, 2020. a
Werder, M. A., Huss, M., Paul, F., Dehecq, A., and Farinotti, D.: A Bayesian
ice thickness estimation model for large-scale applications, J.
Glaciol., 66, 137–152, https://doi.org/10.1017/jog.2019.93, 2020. a
White, I. D., Harrison, S. J., and Mottershead, D. N.: Environmental systems:
an introductory text, Psychology Press, ISBN 9780748740819, 1998. a
World Glacier Monitoring Service (WGMS): Fluctuations of Glaciers Database, World Glacier Monitoring Service (WGMS) [data set], https://doi.org/10.5904/wgms-fog-2021-05, 2021. a, b, c
Wu, K., Liu, S., Jiang, Z., Xu, J., Wei, J., and Guo, W.: Recent glacier mass balance and area changes in the Kangri Karpo Mountains from DEMs and glacier inventories, The Cryosphere, 12, 103–121, https://doi.org/10.5194/tc-12-103-2018, 2018. a
Wu, X., Su, J., Ren, W., Lü, H., and Yuan, F.: Statistical comparison and
hydrological utility evaluation of ERA5-Land and IMERG precipitation products
on the Tibetan Plateau, J. Hydrol., 620, 129384,
https://doi.org/10.1016/j.jhydrol.2023.129384, 2023. a
Xie, Z., Asari, V. K., and Haritashya, U. K.: Evaluating deep-learning models
for debris-covered glacier mapping, Applied Computing and Geosciences, 12,
100071, https://doi.org/10.1016/j.acags.2021.100071, 2021. a
Zandler, H., Haag, I., and Samimi, C.: Evaluation needs and temporal
performance differences of gridded precipitation products in peripheral
mountain regions, Scientific Reports, 9, 15118, https://doi.org/10.1038/s41598-019-51666-z, 2019. a
Zemp, M., Thibert, E., Huss, M., Stumm, D., Rolstad Denby, C., Nuth, C., Nussbaumer, S. U., Moholdt, G., Mercer, A., Mayer, C., Joerg, P. C., Jansson, P., Hynek, B., Fischer, A., Escher-Vetter, H., Elvehøy, H., and Andreassen, L. M.: Reanalysing glacier mass balance measurement series, The Cryosphere, 7, 1227–1245, https://doi.org/10.5194/tc-7-1227-2013, 2013. a
Zemp, M., Nussbaumer, S. U., Gärtner-Roer, I., Bannwart, J., Paul, F., and
Hoelzle, M.: Global Glacier Change Bulletin Nr. 4 (2018-2019), Tech. Rep.,
World Glacier Monitoring Service, Zürich,
https://doi.org/10.5167/uzh-209777, 2021. a, b
Zhang, E., Liu, L., and Huang, L.: Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach, The Cryosphere, 13, 1729–1741, https://doi.org/10.5194/tc-13-1729-2019, 2019. a
Zhao, P. and He, Z.: A First Evaluation of ERA5-Land Reanalysis Temperature
Product Over the Chinese Qilian Mountains, Frontiers in Earth Science, 10, 907730,
https://doi.org/10.3389/feart.2022.907730, 2022. a
Zhu, L., Zhang, Y., Wang, J., Tian, W., Liu, Q., Ma, G., Kan, X., and Chu, Y.:
Downscaling Snow Depth Mapping by Fusion of Microwave and Optical
Remote-Sensing Data Based on Deep Learning, Remote Sensing, 13, 584,
https://doi.org/10.3390/rs13040584, 2021. a
Short summary
Our analysis demonstrates the capability of machine learning models in estimating glacier mass balance in terms of performance metrics and dataset availability. Feature importance analysis suggests that ablation features are significant. This is in agreement with the predominantly negative mass balance observations. We show that ensemble tree models typically depict the best performance. However, neural network models are preferable for biased inputs and kernel-based models for smaller datasets.
Our analysis demonstrates the capability of machine learning models in estimating glacier mass...
