Articles | Volume 19, issue 10
https://doi.org/10.5194/tc-19-4759-2025
© 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-19-4759-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
21 Oct 2025
Research article |
| 21 Oct 2025
| 21 Oct 2025
Learning to filter: snow data assimilation using a Long Short-Term Memory network
Giulia Blandini
CORRESPONDING AUTHOR
CIMA Research Foundation, Savona, Italy
DIBRIS, University of Genoa, Genova, Italy
Francesco Avanzi
CIMA Research Foundation, Savona, Italy
Lorenzo Campo
CIMA Research Foundation, Savona, Italy
Simone Gabellani
CIMA Research Foundation, Savona, Italy
Kristoffer Aalstad
Department of Geosciences, University of Oslo, Oslo, Norway
Manuela Girotto
Department of Environmental Science, Policy, and Management, University of California, Berkeley, Berkeley, CA, United States of America
Satoru Yamaguchi
Snow and Ice Research Center, National Research Institute for Earth Science and Disaster Resilience, Nagaoka, Japan
Hiroyuki Hirashima
Snow and Ice Research Center, National Research Institute for Earth Science and Disaster Resilience, Nagaoka, Japan
Luca Ferraris
CIMA Research Foundation, Savona, Italy
DIBRIS, University of Genoa, Genova, Italy
Related authors
Giulia Blandini, Francesco Avanzi, Simone Gabellani, Denise Ponziani, Hervé Stevenin, Sara Ratto, Luca Ferraris, and Alberto Viglione
The Cryosphere, 17, 5317–5333, https://doi.org/10.5194/tc-17-5317-2023, https://doi.org/10.5194/tc-17-5317-2023, 2023
Short summary
Short summary
Automatic snow depth data are a valuable source of information for hydrologists, but they also tend to be noisy. To maximize the value of these measurements for real-world applications, we developed an automatic procedure to differentiate snow cover from grass or bare ground data, as well as to detect random errors. This procedure can enhance snow data quality, thus providing more reliable data for snow models.
Anna-Maria Virkkala, Isabel Wargowsky, Judith Vogt, McKenzie A. Kuhn, Simran Madaan, Richard O'Keefe, Tiffany Windholz, Kyle A. Arndt, Brendan M. Rogers, Jennifer D. Watts, Kelcy Kent, Mathias Göckede, David Olefeldt, Gerard Rocher-Ros, Edward A. G. Schuur, David Bastviken, Kristoffer Aalstad, Kelly Aho, Joonatan Ala-Könni, Haley Alcock, Inge Althuizen, Christopher D. Arp, Jun Asanuma, Katrin Attermeyer, Mika Aurela, Sivakiruthika Balathandayuthabani, Alan Barr, Maialen Barret, Ochirbat Batkhishig, Christina Biasi, Mats P. Björkman, Andrew Black, Elena Blanc-Betes, Pascal Bodmer, Julia Boike, Abdullah Bolek, Frédéric Bouchard, Ingeborg Bussmann, Lea Cabrol, Eleonora Canfora, Sean Carey, Karel Castro-Morales, Namyi Chae, Andres Christen, Torben R. Christensen, Casper T. Christiansen, Housen Chu, Graham Clark, Francois Clayer, Patrick Crill, Christopher Cunada, Scott J. Davidson, Joshua F. Dean, Sigrid Dengel, Matteo Detto, Catherine Dieleman, Florent Domine, Egor Dyukarev, Colin Edgar, Bo Elberling, Craig A. Emmerton, Eugenie Euskirchen, Grant Falvo, Thomas Friborg, Michelle Garneau, Mariasilvia Giamberini, Mikhail V. Glagolev, Miquel A. Gonzalez-Meler, Gustaf Granath, Jón Guðmundsson, Konsta Happonen, Yoshinobu Harazono, Lorna Harris, Josh Hashemi, Nicholas Hasson, Janna Heerah, Liam Heffernan, Manuel Helbig, Warren Helgason, Michal Heliasz, Greg Henry, Geert Hensgens, Tetsuya Hiyama, Macall Hock, David Holl, Beth Holmes, Jutta Holst, Thomas Holst, Gabriel Hould-Gosselin, Elyn Humphreys, Jacqueline Hung, Jussi Huotari, Hiroki Ikawa, Danil V. Ilyasov, Mamoru Ishikawa, Go Iwahana, Hiroki Iwata, Marcin Antoni Jackowicz-Korczynski, Joachim Jansen, Järvi Järveoja, Vincent E. J. Jassey, Rasmus Jensen, Katharina Jentzsch, Robert G. Jespersen, Carl-Fredrik Johannesson, Chersity P. Jones, Anders Jonsson, Ji Young Jung, Sari Juutinen, Evan Kane, Jan Karlsson, Sergey Karsanaev, Kuno Kasak, Julia Kelly, Kasha Kempton, Marcus Klaus, George W. Kling, Natacha Kljun, Jacqueline Knutson, Hideki Kobayashi, John Kochendorfer, Kukka-Maaria Kohonen, Pasi Kolari, Mika Korkiakoski, Aino Korrensalo, Pirkko Kortelainen, Egle Koster, Kajar Koster, Ayumi Kotani, Praveena Krishnan, Juliya Kurbatova, Lars Kutzbach, Min Jung Kwon, Ethan D. Kyzivat, Jessica Lagroix, Theodore Langhorst, Elena Lapshina, Tuula Larmola, Klaus S. Larsen, Isabelle Laurion, Justin Ledman, Hanna Lee, A. Joshua Leffler, Lance Lesack, Anders Lindroth, David Lipson, Annalea Lohila, Efrén López-Blanco, Vincent L. St. Louis, Erik Lundin, Misha Luoto, Takashi Machimura, Marta Magnani, Avni Malhotra, Marja Maljanen, Ivan Mammarella, Elisa Männistö, Luca Belelli Marchesini, Phil Marsh, Pertti J. Martkainen, Maija E. Marushchak, Mikhail Mastepanov, Alex Mavrovic, Trofim Maximov, Christina Minions, Marco Montemayor, Tomoaki Morishita, Patrick Murphy, Daniel F. Nadeau, Erin Nicholls, Mats B. Nilsson, Anastasia Niyazova, Jenni Nordén, Koffi Dodji Noumonvi, Hannu Nykanen, Walter Oechel, Anne Ojala, Tomohiro Okadera, Sujan Pal, Alexey V. Panov, Tim Papakyriakou, Dario Papale, Sang-Jong Park, Frans-Jan W. Parmentier, Gilberto Pastorello, Mike Peacock, Matthias Peichl, Roman Petrov, Kyra St. Pierre, Norbert Pirk, Jessica Plein, Vilmantas Preskienis, Anatoly Prokushkin, Jukka Pumpanen, Hilary A. Rains, Niklas Rakos, Aleski Räsänen, Helena Rautakoski, Riika Rinnan, Janne Rinne, Adrian Rocha, Nigel Roulet, Alexandre Roy, Anna Rutgersson, Aleksandr F. Sabrekov, Torsten Sachs, Erik Sahlée, Alejandro Salazar, Henrique Oliveira Sawakuchi, Christopher Schulze, Roger Seco, Armando Sepulveda-Jauregui, Svetlana Serikova, Abbey Serrone, Hanna M. Silvennoinen, Sofie Sjogersten, June Skeeter, Jo Snöälv, Sebastian Sobek, Oliver Sonnentag, Emily H. Stanley, Maria Strack, Lena Strom, Patrick Sullivan, Ryan Sullivan, Anna Sytiuk, Torbern Tagesson, Pierre Taillardat, Julie Talbot, Suzanne E. Tank, Mario Tenuta, Irina Terenteva, Frederic Thalasso, Antoine Thiboult, Halldor Thorgeirsson, Fenix Garcia Tigreros, Margaret Torn, Amy Townsend-Small, Claire Treat, Alain Tremblay, Carlo Trotta, Eeva-Stiina Tuittila, Merritt Turetsky, Masahito Ueyama, Muhammad Umair, Aki Vähä, Lona van Delden, Maarten van Hardenbroek, Andrej Varlagin, Ruth K. Varner, Elena Veretennikova, Timo Vesala, Tarmo Virtanen, Carolina Voigt, Jorien E. Vonk, Robert Wagner, Katey Walter Anthony, Qinxue Wang, Masataka Watanabe, Hailey Webb, Jeffrey M. Welker, Andreas Westergaard-Nielsen, Sebastian Westermann, Jeffrey R. White, Christian Wille, Scott N. Williamson, Scott Zolkos, Donatella Zona, and Susan M. Natali
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2025-585, https://doi.org/10.5194/essd-2025-585, 2025
Preprint under review for ESSD
Short summary
Short summary
This dataset includes monthly measurements of carbon dioxide and methane exchange between land, water, and the atmosphere from over 1,000 sites in Arctic and boreal regions. It combines measurements from a variety of ecosystems, including wetlands, forests, tundra, lakes, and rivers, gathered by over 260 researchers from 1984–2024. This dataset can be used to improve and reduce uncertainty in carbon budgets in order to strengthen our understanding of climate feedbacks in a warming world.
Domenico De Santis, Silvia Barbetta, Sumit Sen, Viviana Maggioni, Farhad Bahmanpouri, Ashutosh Sharma, Ankit Agarwal, Sagar Gupta, Francesco Avanzi, and Christian Massari
EGUsphere, https://doi.org/10.5194/egusphere-2025-4933, https://doi.org/10.5194/egusphere-2025-4933, 2025
This preprint is open for discussion and under review for Natural Hazards and Earth System Sciences (NHESS).
Short summary
Short summary
A conceptual, semi-distributed hydrological model was tailored to simulate high flows in monsoon-dominated, glacier-influenced and flood-prone Himalayan basins. Multi-data calibration using satellite-based glacier mass loss and evapotranspiration estimates improved process realism in data-scarce environments. The proposed modelling approach captured key streamflow features despite significant input uncertainties, proving to be a useful tool for exploring the local hydrological response dynamics.
Paolo Filippucci, Luca Brocca, Luca Ciabatta, Hamidreza Mosaffa, Francesco Avanzi, and Christian Massari
Earth Syst. Sci. Data, 17, 5221–5258, https://doi.org/10.5194/essd-17-5221-2025, https://doi.org/10.5194/essd-17-5221-2025, 2025
Short summary
Short summary
Accurate rainfall data is essential, yet measuring daily precipitation worldwide is challenging. This research presents HYdroclimatic PERformance-enhanced Precipitation (HYPER-P), a dataset combining satellite, ground, and reanalysis data to estimate precipitation at a 1 km scale from 2000 to 2022. HYPER-P improves accuracy, especially in areas with few rain gauges. This dataset supports scientists and decision-makers in understanding and managing water resources more effectively.
Martina Leone, Francesco Avanzi, Umberto Morra Di Cella, Simone Gabellani, Edoardo Cremonese, Michel Isabellon, Paolo Pogliotti, Riccardo Scotti, Andrea Monti, Luca Ferraris, and Roberto Colombo
EGUsphere, https://doi.org/10.5194/egusphere-2025-3705, https://doi.org/10.5194/egusphere-2025-3705, 2025
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
We investigated how glaciers helped sustain summer river flow during the severe snow shortages of 2022 and 2023 in the Italian Alps. Using high-resolution modeling and long-term data, we found that glacier melt contributed up to three times more than in average years. This enhanced melt partly compensated for low snow and precipitation, showing the critical role of glaciers in supporting water resources during droughts.
Sofia Ortenzi, Lucio Di Matteo, Daniela Valigi, Marco Donnini, Marco Dionigi, Davide Fronzi, Josie Geris, Fabio Guadagnano, Ivan Marchesini, Paolo Filippucci, Francesco Avanzi, Daniele Penna, and Christian Massari
EGUsphere, https://doi.org/10.5194/egusphere-2025-4368, https://doi.org/10.5194/egusphere-2025-4368, 2025
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
This study investigates groundwater–surface water interactions in the Ussita catchment (Italy), using hydrological, hydrochemical–isotopic, thermal drone, and satellite data. Results show that fractured limestone aquifers sustain streamflow, with snowmelt contributing ~20% to recharge. The integrated approach supports water management, climate adaptation, and ecosystem sustainability in Mediterranean mountain regions.
Clarissa Willmes, Kristoffer Aalstad, and Sebastian Westermann
EGUsphere, https://doi.org/10.5194/egusphere-2025-3142, https://doi.org/10.5194/egusphere-2025-3142, 2025
This preprint is open for discussion and under review for The Cryosphere (TC).
Short summary
Short summary
In permafrost areas, the spatial variability of the snow cover significantly affects the ground thermal regime. This study presents an algorithm that integrates satellite data into a permafrost model to enhance the spatial detail of ground temperature simulations. At a site on Svalbard, the algorithm improves simulations of ground temperatures especially for wind-blown ridges with little snow, as well as snow-drift sites.
Marco Mazzolini, Kristoffer Aalstad, Esteban Alonso-González, Sebastian Westermann, and Désirée Treichler
The Cryosphere, 19, 3831–3848, https://doi.org/10.5194/tc-19-3831-2025, https://doi.org/10.5194/tc-19-3831-2025, 2025
Short summary
Short summary
In this work, we showcase the use the satellite laser altimeter ICESat-2, which is able to retrieve snow depth in areas where snow amounts are still poorly estimated despite the importance of these water resources. We can update snow models with these observations through algorithms that spatially propagate the information beyond the satellite profiles. The positive results show the potential of the approach to improve snow simulations, in terms of average snow depth and spatial distribution.
Alouette van Hove, Kristoffer Aalstad, Vibeke Lind, Claudia Arndt, Vincent Odongo, Rodolfo Ceriani, Francesco Fava, John Hulth, and Norbert Pirk
Biogeosciences, 22, 4163–4186, https://doi.org/10.5194/bg-22-4163-2025, https://doi.org/10.5194/bg-22-4163-2025, 2025
Short summary
Short summary
Research on methane emissions from African livestock is limited. We used a probabilistic method fusing drone and flux tower observations with an atmospheric model to estimate emissions from various herds. This approach proved robust under non-stationary wind conditions and effective in estimating emissions as low as 100 g h-1. We also detected spectral anomalies in satellite data associated with the herds. Our method can be used for diverse point sources, thereby improving emission inventories.
Esteban Alonso-González, Adrian Harpold, Jessica D. Lundquist, Cara Piske, Laura Sourp, Kristoffer Aalstad, and Simon Gascoin
EGUsphere, https://doi.org/10.5194/egusphere-2025-2347, https://doi.org/10.5194/egusphere-2025-2347, 2025
Short summary
Short summary
Simulating the snowpack is challenging, as there are several sources of uncertainty due to e.g. the meteorological forcing. Using data assimilation techniques, it is possible to improve the simulations by fusing models and snow observations. However in forests, observations are difficult to obtain, because they cannot be retrieved through the canopy. Here, we explore the possibility of propagating the information obtained in forest clearings to areas covered by the canopy.
Juditha Aga, Livia Piermattei, Luc Girod, Kristoffer Aalstad, Trond Eiken, Andreas Kääb, and Sebastian Westermann
Earth Surf. Dynam., 12, 1049–1070, https://doi.org/10.5194/esurf-12-1049-2024, https://doi.org/10.5194/esurf-12-1049-2024, 2024
Short summary
Short summary
Coastal rock cliffs on Svalbard are considered to be fairly stable; however, long-term trends in coastal-retreat rates remain unknown. This study examines changes in the coastline position along Brøggerhalvøya, Svalbard, using aerial images from 1970, 1990, 2010, and 2021. Our analysis shows that coastal-retreat rates accelerate during the period 2010–2021, which coincides with increasing storminess and retreating sea ice.
Fatemeh Zakeri, Gregoire Mariethoz, and Manuela Girotto
EGUsphere, https://doi.org/10.5194/egusphere-2024-1943, https://doi.org/10.5194/egusphere-2024-1943, 2024
Short summary
Short summary
This study introduces a method for estimating High-Resolution Snow Water Equivalent (HR-SWE) using Low-Resolution Climate Data (LR-CD). By applying a data-driven approach, we utilize historical weather patterns from LR-CD to estimate HR-SWE maps. Our approach uses statistical relationships between LR-CD and HR-SWE data to provide HR-SWE estimates for dates when HR-SWE data is unavailable. This method improves water resource management and climate impact assessments in regions with limited data.
Lorenzo Alfieri, Andrea Libertino, Lorenzo Campo, Francesco Dottori, Simone Gabellani, Tatiana Ghizzoni, Alessandro Masoero, Lauro Rossi, Roberto Rudari, Nicola Testa, Eva Trasforini, Ahmed Amdihun, Jully Ouma, Luca Rossi, Yves Tramblay, Huan Wu, and Marco Massabò
Nat. Hazards Earth Syst. Sci., 24, 199–224, https://doi.org/10.5194/nhess-24-199-2024, https://doi.org/10.5194/nhess-24-199-2024, 2024
Short summary
Short summary
This work describes Flood-PROOFS East Africa, an impact-based flood forecasting system for the Greater Horn of Africa. It is based on hydrological simulations, inundation mapping, and estimation of population and assets exposed to upcoming river floods. The system supports duty officers in African institutions in the daily monitoring of hydro-meteorological disasters. A first evaluation shows the system performance for the catastrophic floods in the Nile River basin in summer 2020.
Francesca Munerol, Francesco Avanzi, Eleonora Panizza, Marco Altamura, Simone Gabellani, Lara Polo, Marina Mantini, Barbara Alessandri, and Luca Ferraris
Geosci. Commun., 7, 1–15, https://doi.org/10.5194/gc-7-1-2024, https://doi.org/10.5194/gc-7-1-2024, 2024
Short summary
Short summary
To contribute to advancing education in a warming climate and prepare the next generations to play their role in future societies, we designed “Water and Us”, a three-module initiative focusing on the natural and anthropogenic water cycle, climate change, and conflicts. This study aims to introduce the initiative's educational objectives, methods, and early results.
Esteban Alonso-González, Kristoffer Aalstad, Norbert Pirk, Marco Mazzolini, Désirée Treichler, Paul Leclercq, Sebastian Westermann, Juan Ignacio López-Moreno, and Simon Gascoin
Hydrol. Earth Syst. Sci., 27, 4637–4659, https://doi.org/10.5194/hess-27-4637-2023, https://doi.org/10.5194/hess-27-4637-2023, 2023
Short summary
Short summary
Here we explore how to improve hyper-resolution (5 m) distributed snowpack simulations using sparse observations, which do not provide information from all the areas of the simulation domain. We propose a new way of propagating information throughout the simulations adapted to the hyper-resolution, which could also be used to improve simulations of other nature. The method has been implemented in an open-source data assimilation tool that is readily accessible to everyone.
Giulia Blandini, Francesco Avanzi, Simone Gabellani, Denise Ponziani, Hervé Stevenin, Sara Ratto, Luca Ferraris, and Alberto Viglione
The Cryosphere, 17, 5317–5333, https://doi.org/10.5194/tc-17-5317-2023, https://doi.org/10.5194/tc-17-5317-2023, 2023
Short summary
Short summary
Automatic snow depth data are a valuable source of information for hydrologists, but they also tend to be noisy. To maximize the value of these measurements for real-world applications, we developed an automatic procedure to differentiate snow cover from grass or bare ground data, as well as to detect random errors. This procedure can enhance snow data quality, thus providing more reliable data for snow models.
Motoshi Nishimura, Teruo Aoki, Masashi Niwano, Sumito Matoba, Tomonori Tanikawa, Tetsuhide Yamasaki, Satoru Yamaguchi, and Koji Fujita
Earth Syst. Sci. Data, 15, 5207–5226, https://doi.org/10.5194/essd-15-5207-2023, https://doi.org/10.5194/essd-15-5207-2023, 2023
Short summary
Short summary
We presented the method of data quality checks and the dataset for two ground weather observations in northwest Greenland. We found that the warm and clear weather conditions in the 2015, 2019, and 2020 summers caused the snowmelt and the decline in surface reflectance of solar radiation at a low-elevated site (SIGMA-B; 944 m), but those were not seen at the high-elevated site (SIGMA-A; 1490 m). We hope that our data management method and findings will help climate scientists.
Norbert Pirk, Kristoffer Aalstad, Yeliz A. Yilmaz, Astrid Vatne, Andrea L. Popp, Peter Horvath, Anders Bryn, Ane Victoria Vollsnes, Sebastian Westermann, Terje Koren Berntsen, Frode Stordal, and Lena Merete Tallaksen
Biogeosciences, 20, 2031–2047, https://doi.org/10.5194/bg-20-2031-2023, https://doi.org/10.5194/bg-20-2031-2023, 2023
Short summary
Short summary
We measured the land–atmosphere exchange of CO2 and water vapor in alpine Norway over 3 years. The extremely snow-rich conditions in 2020 reduced the total annual evapotranspiration to 50 % and reduced the growing-season carbon assimilation to turn the ecosystem from a moderate annual carbon sink to an even stronger source. Our analysis suggests that snow cover anomalies are driving the most consequential short-term responses in this ecosystem’s functioning.
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.
Elias C. Massoud, Lauren Andrews, Rolf Reichle, Andrea Molod, Jongmin Park, Sophie Ruehr, and Manuela Girotto
Earth Syst. Dynam., 14, 147–171, https://doi.org/10.5194/esd-14-147-2023, https://doi.org/10.5194/esd-14-147-2023, 2023
Short summary
Short summary
In this study, we benchmark the forecast skill of the NASA’s Goddard Earth Observing System subseasonal-to-seasonal (GEOS-S2S version 2) hydrometeorological forecasts in the High Mountain Asia (HMA) region. Hydrometeorological forecast skill is dependent on the forecast lead time, the memory of the variable within the physical system, and the validation dataset used. Overall, these results benchmark the GEOS-S2S system’s ability to forecast HMA hydrometeorology on the seasonal timescale.
Francesco Avanzi, Simone Gabellani, Fabio Delogu, Francesco Silvestro, Flavio Pignone, Giulia Bruno, Luca Pulvirenti, Giuseppe Squicciarino, Elisabetta Fiori, Lauro Rossi, Silvia Puca, Alexander Toniazzo, Pietro Giordano, Marco Falzacappa, Sara Ratto, Hervè Stevenin, Antonio Cardillo, Matteo Fioletti, Orietta Cazzuli, Edoardo Cremonese, Umberto Morra di Cella, and Luca Ferraris
Earth Syst. Sci. Data, 15, 639–660, https://doi.org/10.5194/essd-15-639-2023, https://doi.org/10.5194/essd-15-639-2023, 2023
Short summary
Short summary
Snow cover has profound implications for worldwide water supply and security, but knowledge of its amount and distribution across the landscape is still elusive. We present IT-SNOW, a reanalysis comprising daily maps of snow amount and distribution across Italy for 11 snow seasons from September 2010 to August 2021. The reanalysis was validated using satellite images and snow measurements and will provide highly needed data to manage snow water resources in a warming climate.
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.
Esteban Alonso-González, Kristoffer Aalstad, Mohamed Wassim Baba, Jesús Revuelto, Juan Ignacio López-Moreno, Joel Fiddes, Richard Essery, and Simon Gascoin
Geosci. Model Dev., 15, 9127–9155, https://doi.org/10.5194/gmd-15-9127-2022, https://doi.org/10.5194/gmd-15-9127-2022, 2022
Short summary
Short summary
Snow cover plays an important role in many processes, but its monitoring is a challenging task. The alternative is usually to simulate the snowpack, and to improve these simulations one of the most promising options is to fuse simulations with available observations (data assimilation). In this paper we present MuSA, a data assimilation tool which facilitates the implementation of snow monitoring initiatives, allowing the assimilation of a wide variety of remotely sensed snow cover information.
Norbert Pirk, Kristoffer Aalstad, Sebastian Westermann, Astrid Vatne, Alouette van Hove, Lena Merete Tallaksen, Massimo Cassiani, and Gabriel Katul
Atmos. Meas. Tech., 15, 7293–7314, https://doi.org/10.5194/amt-15-7293-2022, https://doi.org/10.5194/amt-15-7293-2022, 2022
Short summary
Short summary
In this study, we show how sparse and noisy drone measurements can be combined with an ensemble of turbulence-resolving wind simulations to estimate uncertainty-aware surface energy exchange. We demonstrate the feasibility of this drone data assimilation framework in a series of synthetic and real-world experiments. This new framework can, in future, be applied to estimate energy and gas exchange in heterogeneous landscapes more representatively than conventional methods.
Giulia Bruno, Doris Duethmann, Francesco Avanzi, Lorenzo Alfieri, Andrea Libertino, and Simone Gabellani
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2022-416, https://doi.org/10.5194/hess-2022-416, 2022
Manuscript not accepted for further review
Short summary
Short summary
Hydrological models often have issues during droughts. We used the distributed Continuum model over the Po river basin and independent datasets of streamflow (Q), evapotranspiration (ET), and storage. Continuum simulated Q well during wet years and moderate droughts. Performances declined for a severe drought and we explained this drop with an increased uncertainty in ET anomalies in human-affected croplands. These findings provide guidelines for assessments of model robustness during droughts.
Andrea Taramelli, Margherita Righini, Emiliana Valentini, Lorenzo Alfieri, Ignacio Gatti, and Simone Gabellani
Nat. Hazards Earth Syst. Sci., 22, 3543–3569, https://doi.org/10.5194/nhess-22-3543-2022, https://doi.org/10.5194/nhess-22-3543-2022, 2022
Short summary
Short summary
This work aims to support decision-making processes to prioritize effective interventions for flood risk reduction and mitigation for the implementation of flood risk management concepts in urban areas. Our findings provide new insights into vulnerability spatialization of urban flood events for the residential sector, demonstrating that the nature of flood pathways varies spatially and is influenced by landscape characteristics, as well as building features.
Lorenzo Alfieri, Francesco Avanzi, Fabio Delogu, Simone Gabellani, Giulia Bruno, Lorenzo Campo, Andrea Libertino, Christian Massari, Angelica Tarpanelli, Dominik Rains, Diego G. Miralles, Raphael Quast, Mariette Vreugdenhil, Huan Wu, and Luca Brocca
Hydrol. Earth Syst. Sci., 26, 3921–3939, https://doi.org/10.5194/hess-26-3921-2022, https://doi.org/10.5194/hess-26-3921-2022, 2022
Short summary
Short summary
This work shows advances in high-resolution satellite data for hydrology. We performed hydrological simulations for the Po River basin using various satellite products, including precipitation, evaporation, soil moisture, and snow depth. Evaporation and snow depth improved a simulation based on high-quality ground observations. Interestingly, a model calibration relying on satellite data skillfully reproduces observed discharges, paving the way to satellite-driven hydrological applications.
Francesco Avanzi, Simone Gabellani, Fabio Delogu, Francesco Silvestro, Edoardo Cremonese, Umberto Morra di Cella, Sara Ratto, and Hervé Stevenin
Geosci. Model Dev., 15, 4853–4879, https://doi.org/10.5194/gmd-15-4853-2022, https://doi.org/10.5194/gmd-15-4853-2022, 2022
Short summary
Short summary
Knowing in real time how much snow and glacier ice has accumulated across the landscape has significant implications for water-resource management and flood control. This paper presents a computer model – S3M – allowing scientists and decision makers to predict snow and ice accumulation during winter and the subsequent melt during spring and summer. S3M has been employed for real-world flood forecasting since the early 2000s but is here being made open source for the first time.
Christian Massari, Francesco Avanzi, Giulia Bruno, Simone Gabellani, Daniele Penna, and Stefania Camici
Hydrol. Earth Syst. Sci., 26, 1527–1543, https://doi.org/10.5194/hess-26-1527-2022, https://doi.org/10.5194/hess-26-1527-2022, 2022
Short summary
Short summary
Droughts are a creeping disaster, meaning that their onset, duration and recovery are challenging to monitor and forecast. Here, we provide further evidence of an additional challenge of droughts, i.e. the fact that the deficit in water supply during droughts is generally much more than expected based on the observed decline in precipitation. At a European scale we explain this with enhanced evapotranspiration, sustained by higher atmospheric demand for moisture during such dry periods.
Joel Fiddes, Kristoffer Aalstad, and Michael Lehning
Geosci. Model Dev., 15, 1753–1768, https://doi.org/10.5194/gmd-15-1753-2022, https://doi.org/10.5194/gmd-15-1753-2022, 2022
Short summary
Short summary
This study describes and evaluates a new downscaling scheme that addresses the need for hillslope-scale atmospheric forcing time series for modelling the local impact of regional climate change on the land surface in mountain areas. The method has a global scope and is able to generate all model forcing variables required for hydrological and land surface modelling. This is important, as impact models require high-resolution forcings such as those generated here to produce meaningful results.
Tessa Maurer, Francesco Avanzi, Steven D. Glaser, and Roger C. Bales
Hydrol. Earth Syst. Sci., 26, 589–607, https://doi.org/10.5194/hess-26-589-2022, https://doi.org/10.5194/hess-26-589-2022, 2022
Short summary
Short summary
Predicting how much water will end up in rivers is more difficult during droughts because the relationship between precipitation and streamflow can change in unexpected ways. We differentiate between changes that are predictable based on the weather patterns and those harder to predict because they depend on the land and vegetation of a particular region. This work helps clarify why models are less accurate during droughts and helps predict how much water will be available for human use.
Esteban Alonso-González, Ethan Gutmann, Kristoffer Aalstad, Abbas Fayad, Marine Bouchet, and Simon Gascoin
Hydrol. Earth Syst. Sci., 25, 4455–4471, https://doi.org/10.5194/hess-25-4455-2021, https://doi.org/10.5194/hess-25-4455-2021, 2021
Short summary
Short summary
Snow water resources represent a key hydrological resource for the Mediterranean regions, where most of the precipitation falls during the winter months. This is the case for Lebanon, where snowpack represents 31 % of the spring flow. We have used models to generate snow information corrected by means of remote sensing snow cover retrievals. Our results highlight the high temporal variability in the snowpack in Lebanon and its sensitivity to further warming caused by its hypsography.
Francesco Avanzi, Giulia Ercolani, Simone Gabellani, Edoardo Cremonese, Paolo Pogliotti, Gianluca Filippa, Umberto Morra di Cella, Sara Ratto, Hervè Stevenin, Marco Cauduro, and Stefano Juglair
Hydrol. Earth Syst. Sci., 25, 2109–2131, https://doi.org/10.5194/hess-25-2109-2021, https://doi.org/10.5194/hess-25-2109-2021, 2021
Short summary
Short summary
Precipitation tends to increase with elevation, but the magnitude and distribution of this enhancement remain poorly understood. By leveraging over 11 000 spatially distributed, manual measurements of snow depth (snow courses) upstream of two reservoirs in the western European Alps, we show that these courses bear a characteristic signature of orographic precipitation. This opens a window of opportunity for improved modeling accuracy and, ultimately, our understanding of the water budget.
Cited articles
Aalstad, K., Westermann, S., Schuler, T. V., Boike, J., and Bertino, L.: Ensemble-based assimilation of fractional snow-covered area satellite retrievals to estimate the snow distribution at Arctic sites, The Cryosphere, 12, 247–270, https://doi.org/10.5194/tc-12-247-2018, 2018. a, b, c, d
Aalstad, K., Westermann, S., and Bertino, L.: Evaluating satellite retrieved fractional snow-covered area at a high-Arctic site using terrestrial photography, Remote Sensing of Environment, 239, 111618, https://doi.org/10.1016/j.rse.2019.111618, 2020. a
Adnan, R. M., Mo, W., Kisi, O., Heddam, S., Al-Janabi, A. M. S., and Zounemat-Kermani, M.: Harnessing Deep Learning and Snow Cover Data for Enhanced Runoff Prediction in Snow-Dominated Watersheds, Atmosphere, 15, 1407, https://doi.org/10.3390/atmos15121407, 2024. a
Alonso-González, E., Aalstad, K., Baba, M. W., Revuelto, J., López-Moreno, J. I., Fiddes, J., Essery, R., and Gascoin, S.: The Multiple Snow Data Assimilation System (MuSA v1.0), Geosci. Model Dev., 15, 9127–9155, https://doi.org/10.5194/gmd-15-9127-2022, 2022. a, b, c
Alonso-González, E., Gascoin, S., Arioli, S., and Picard, G.: Exploring the potential of thermal infrared remote sensing to improve a snowpack model through an observing system simulation experiment, The Cryosphere, 17, 3329–3342, https://doi.org/10.5194/tc-17-3329-2023, 2023. a
Andreadis, K. M. and Lettenmaier, D. P.: Assimilating remotely sensed snow observations into a macroscale hydrology model, Advances in Water Resources, 29, 872–886, https://doi.org/10.1016/j.advwatres.2005.08.004, 2006. a
Arcucci, R., Zhu, J., Hu, S., and Guo, Y.-K.: Deep data assimilation: integrating deep learning with data assimilation, Applied Sciences, 11, 1114, https://doi.org/10.3390/app11031114, 2021. a, b
Avanzi, F. and Delogu, F.: c-hydro/s3m-dev: (v5.1.0), Zenodo [code], https://doi.org/10.5281/zenodo.4663899, 2021. a
Avanzi, F., De Michele, C., Ghezzi, A., Jommi, C., and Pepe, M.: A processing–modeling routine to use SNOTEL hourly data in snowpack dynamic models, Advances in Water Resources, 73, 16–29, 2014. a
Avanzi, F., Johnson, R. C., Oroza, C. A., Hirashima, H., Maurer, T., and Yamaguchi, S.: Insights into preferential flow snowpack runoff using random forest, Water Resources Research, 55, 10727–10746, 2019. a
Avanzi, F., Gabellani, S., Delogu, F., Silvestro, F., Cremonese, E., Morra di Cella, U., Ratto, S., and Stevenin, H.: Snow Multidata Mapping and Modeling (S3M) 5.1: a distributed cryospheric model with dry and wet snow, data assimilation, glacier mass balance, and debris-driven melt, Geosci. Model Dev., 15, 4853–4879, https://doi.org/10.5194/gmd-15-4853-2022, 2022. a, b
Avanzi, F., Gabellani, S., Delogu, F., Silvestro, F., Pignone, F., Bruno, G., Pulvirenti, L., Squicciarino, G., Fiori, E., Rossi, L., Puca, S., Toniazzo, A., Giordano, P., Falzacappa, M., Ratto, S., Stevenin, H., Cardillo, A., Fioletti, M., Cazzuli, O., Cremonese, E., Morra di Cella, U., and Ferraris, L.: IT-SNOW: a snow reanalysis for Italy blending modeling, in situ data, and satellite observations (2010–2021), Earth Syst. Sci. Data, 15, 639–660, https://doi.org/10.5194/essd-15-639-2023, 2023. a
Avanzi, F., Munerol, F., Milelli, M., Gabellani, S., Massari, C., Girotto, M., Cremonese, E., Galvagno, M., Bruno, G., Morra di Cella, U. , Rossi, L., Altamura, M., and Ferraris, L.: Winter snow deficit was a harbinger of summer 2022 socio-hydrologic drought in the Po Basin, Italy, Communications Earth & Environment, 5, 64, https://doi.org/10.1038/s43247-024-01222-z , 2024. a
Bales, R. C., Molotch, N. P., Painter, T. H., Dettinger, M. D., Rice, R., and Dozier, J.: Mountain hydrology of the western United States, Water Resources Research, 42, https://doi.org/10.1029/2005WR004387, 2006. a
Beven, K.: Causal models as multiple working hypotheses about environmental processes, Comptes Rendus Geoscience, 344, 77–88, 2012. a
Bishop, C. M. and Bishop, H.: Deep learning: Foundations and concepts, Springer Nature, ISBN 978-3031454677, 2023. a
Blöschl, G.: Scaling issues in snow hydrology, Hydrological processes, 13, 2149–2175, 1999. a
Boni, G., Castelli, F., Gabellani, S., Machiavello, G., and Rudari, R.: Assimilation of MODIS snow cover and real time snow depth point data in a snow dynamic model, in: 2010 IEEE International Geoscience and Remote Sensing Symposium, 1788–1791, IEEE, https://doi.org/10.1109/IGARSS.2010.5648989, 2010. a
Boucher, M.-A., Quilty, J., and Adamowski, J.: Data Assimilation for Streamflow Forecasting Using Extreme Learning Machines and Multilayer Perceptrons, Water Resources Research, 56, e2019WR026226, https://doi.org/10.1029/2019WR026226, 2020. a
Carrassi, A., Bocquet, M., Bertino, L., and Evensen, G.: Data assimilation in the geosciences: An overview of methods, issues, and perspectives, Wiley Interdisciplinary Reviews: Climate Change, 9, e535, https://doi.org/10.1002/wcc.535, 2018. a, b
Casas, C. Q., Arcucci, R., Wu, P., Pain, C., and Guo, Y.-K.: A Reduced Order Deep Data Assimilation model, Physica D: Nonlinear Phenomena, 412, 132615, https://doi.org/10.1016/j.physd.2020.132615, 2020. a
Charbonneau, A., Deck, K., and Schneider, T.: A Physics-Constrained Neural Differential Equation Framework for Data-Driven Snowpack Simulation, arXiv [preprint], https://doi.org/10.48550/arXiv.2412.06819, 2024. a
Chen, S., Huang, J., and Huang, J.-C.: Improving daily streamflow simulations for data-scarce watersheds using the coupled SWAT-LSTM approach, Journal of Hydrology, 622, 129734, https://doi.org/10.1016/j.jhydrol.2023.129734, 2023. a
Cheng, C. and Zhang, G.-T.: Deep Learning Method Based on Physics Informed Neural Network with Resnet Block for Solving Fluid Flow Problems, Water, 13, https://doi.org/10.3390/w13040423, 2021. a
Cheng, S., Quilodrán-Casas, C., Ouala, S., Farchi, A., Liu, C., Tandeo, P., Fablet, R., Lucor, D., Iooss, B., Brajard, J., Xiao, D., Janjic, T., Ding, W., Guo, Y., Carrassi, A., Bocquet, M., and Arcucci, R.: Machine learning with data assimilation and uncertainty quantification for dynamical systems: a review, IEEE/CAA Journal of Automatica Sinica, 10, 1361–1387, 2023. a, b
Chollet, F.: Keras, https://keras.io (last access: 15 October 2025), 2015. a
Cluzet, B., Magnusson, J., Quéno, L., Mazzotti, G., Mott, R., and Jonas, T.: Exploring how Sentinel-1 wet-snow maps can inform fully distributed physically based snowpack models, The Cryosphere, 18, 5753–5767, https://doi.org/10.5194/tc-18-5753-2024, 2024. a
Cowherd, M., Mital, U., Rahimi, S., Girotto, M., Schwartz, A., and Feldman, D.: Climate change-resilient snowpack estimation in the Western United States, Commun. Earth Environ., 5, https://doi.org/10.1038/s43247-024-01496-3, 2024a. a
Cowherd, M., Mital, U., Rahimi, S., Girotto, M., Schwartz, A., and Feldman, D.: Climate change-resilient snowpack estimation in the Western United States, Communications Earth & Environment, 5, 337, https://doi.org/10.1038/s43247-024-01496-3, 2024b. a
Cui, G., Anderson, M., and Bales, R.: Mapping of snow water equivalent by a deep-learning model assimilating snow observations, Journal of Hydrology, 616, 128835, https://doi.org/10.1016/j.jhydrol.2022.128835, 2023. a, b
Daudt, R. C., Wulf, H., Hafner, E. D., Bühler, Y., Schindler, K., and Wegner, J. D.: Snow depth estimation at country-scale with high spatial and temporal resolution, ISPRS Journal of Photogrammetry and Remote Sensing, 197, 105–121, https://doi.org/10.1016/j.isprsjprs.2023.01.017, 2023. a
Dedieu, J.-P., Carlson, B. Z., Bigot, S., Sirguey, P., Vionnet, V., and Choler, P.: On the Importance of High-Resolution Time Series of Optical Imagery for Quantifying the Effects of Snow Cover Duration on Alpine Plant Habitat, Remote Sensing, 8, https://doi.org/10.3390/rs8060481, 2016. a
Deschamps-Berger, C., Gascoin, S., Shean, D., Besso, H., Guiot, A., and López-Moreno, J. I.: Evaluation of snow depth retrievals from ICESat-2 using airborne laser-scanning data, The Cryosphere, 17, 2779–2792, https://doi.org/10.5194/tc-17-2779-2023, 2023. a
Dhoni, P. S.: From Data to Decisions: Enhancing Retail with AI and Machine Learning, International Journal of Computing and Engineering, 5, 38–51, 2024. a
Durand, M. and Margulis, S. A.: Feasibility test of multifrequency radiometric data assimilation to estimate snow water equivalent, Journal of Hydrometeorology, 7, 443–457, 2006. a
Essery, R., Kontu, A., Lemmetyinen, J., Dumont, M., and Ménard, C. B.: A 7-year dataset for driving and evaluating snow models at an Arctic site (Sodankylä, Finland), Geoscientific Instrumentation, Methods and Data Systems, 5, 219–227, 2016. a
Fan, H., Jiang, M., Xu, L., Zhu, H., Cheng, J., and Jiang, J.: Comparison of long short term memory networks and the hydrological model in runoff simulation, Water, 12, 175, https://doi.org/10.3390/w12010175, 2020. a
Fiddes, J., Aalstad, K., and Westermann, S.: Hyper-resolution ensemble-based snow reanalysis in mountain regions using clustering, Hydrol. Earth Syst. Sci., 23, 4717–4736, https://doi.org/10.5194/hess-23-4717-2019, 2019. a
Filippa, G., Cremonese, E., Galvagno, M., Migliavacca, M., Morra di Cella, U., Petey, M., and Siniscalco, C.: Five years of phenological monitoring in a mountain grassland: inter-annual patterns and evaluation of the sampling protocol, International Journal of Biometeorology, 59, 1927–1937, 2015. a
Gascoin, S., Luojus, K., Nagler, T., Lievens, H., Masiokas, M., Jonas, T., Zheng, Z., and De Rosnay, P.: Remote sensing of mountain snow from space: status and recommendations, Frontiers in Earth Science, 12, 1381323, https://doi.org/10.3389/feart.2024.1381323, 2024. a
Gauch, M., Kratzert, F., Klotz, D., Nearing, G., Cohen, D., and Gilon, O.: How to deal w___ missing input data, EGUsphere [preprint], https://doi.org/10.5194/egusphere-2025-1224, 2025. a
Girotto, M., Formetta, G., Azimi, S., Bachand, C., Cowherd, M., De Lannoy, G., Lievens, H., Modanesi, S., Raleigh, M. S., Rigon, R., and Massari, C.: Identifying snowfall elevation patterns by assimilating satellite-based snow depth retrievals, Science of The Total Environment, 906, 167312, https://doi.org/10.1016/j.scitotenv.2023.167312, 2024. a
Gong, Y., Liu, G., Xue, Y., Li, R., and Meng, L.: A survey on dataset quality in machine learning, Information and Software Technology, 162, 107268, https://doi.org/10.1016/j.infsof.2023.107268, 2023. a
Guidicelli, M., Aalstad, K., Treichler, D., and Salzmann, N.: A combined data assimilation and deep learning approach for continuous spatio-temporal SWE reconstruction from sparse ground tracks, Journal of Hydrology X, 25, 100190, https://doi.org/10.1016/j.hydroa.2024.100190, 2024. a, b, c
Gupta, H. V., Kling, H., Yilmaz, K. K., and Martinez, G. F.: Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling, Journal of Hydrology, 377, 80–91, 2009. a
Harder, P. and Pomeroy, J. W.: Hydrological model uncertainty due to precipitation-phase partitioning methods, Hydrological Processes, 28, 4311–4327, 2014. a
Hartman, R. K., Rost, A. A., and Anderson, D. M.: Operational processing of multi-source snow data, Proceedings of the Western Snow Conference, 147, 151, https://www.weather.gov/owp/oh_hrl_dmip_2_OPPS (15 October 2025), 1995. a
He, T., Yu, S., Wang, Z., Li, J., and Chen, Z.: From Data Quality to Model Quality: An Exploratory Study on Deep Learning, in: Proceedings of the 11th Asia-Pacific Symposium on Internetware, Internetware '19, Association for Computing Machinery, New York, NY, USA, ISBN 9781450377010, https://doi.org/10.1145/3361242.3361260, 2019. a
Hock, R., Rasul, G., Adler, C., Cáceres, B., Gruber, S., Hirabayashi, Y., Jackson, M., Kääb, A., Kang, S., Kutuzov, S., Milner, A., Molau, U., Morin, S., Orlove, B., and Steltzer, H.: High Mountain Areas Supplementary Material, IPCC Special Report on the Ocean and Cryosphere in a Changing Climate, 2019. a
Houser, P. R., De Lannoy, G. J., and Walker, J. P.: Hydrologic data assimilation, Approaches to Managing Disaster-Assessing Hazards, Emergencies and Disaster Impacts, 41–64, https://doi.org/10.5772/31246, 2012. a
Huang, C., Newman, A. J., Clark, M. P., Wood, A. W., and Zheng, X.: Evaluation of snow data assimilation using the ensemble Kalman filter for seasonal streamflow prediction in the western United States, Hydrol. Earth Syst. Sci., 21, 635–650, https://doi.org/10.5194/hess-21-635-2017, 2017. a
Isik, F., Ozden, G., and Kuntalp, M.: Importance of data preprocessing for neural networks modeling: The case of estimating the compaction parameters of soils, Energy Educ. Sci. Technol. Part A: Energy Sci. Res., 29, 463–74, 2012. a
Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., and Yang, L.: Physics-informed machine learning, Nature Reviews Physics, 3, 422–440, 2021. a
Krajči, P., Kirnbauer, R., Parajka, J., Schöber, J., and Blöschl, G.: The Kühtai data set: 25 years of lysimetric, snow pillow, and meteorological measurements, Water Resources Research, 53, 5158–5165, 2017. a
Kratzert, F., Klotz, D., Brenner, C., Schulz, K., and Herrnegger, M.: Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks, Hydrol. Earth Syst. Sci., 22, 6005–6022, https://doi.org/10.5194/hess-22-6005-2018, 2018. a
Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., and Nearing, G.: Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets, Hydrol. Earth Syst. Sci., 23, 5089–5110, https://doi.org/10.5194/hess-23-5089-2019, 2019. a
Kratzert, F., Gauch, M., Klotz, D., and Nearing, G.: HESS Opinions: Never train a Long Short-Term Memory (LSTM) network on a single basin, Hydrol. Earth Syst. Sci., 28, 4187–4201, https://doi.org/10.5194/hess-28-4187-2024, 2024 a
Lannoy, G. J. M. D., Reichle, R. H., Houser, P. R., Arsenault, K. R., Verhoest, N. E. C., and Pauwels, V. R. N.: Satellite-Scale Snow Water Equivalent Assimilation into a High-Resolution Land Surface Model, Journal of Hydrometeorology, 11, 352–369, https://doi.org/10.1175/2009JHM1192.1, 2010. a
Largeron, C., Dumont, M., Morin, S., Boone, A., Lafaysse, M., Metref, S., Cosme, E., Jonas, T., Winstral, A., and Margulis, S. A.: Toward snow cover estimation in mountainous areas using modern data assimilation methods: A review, Frontiers in Earth Science, 8, 325, https://doi.org/10.3389/feart.2020.00325, 2020. a
Larsson Ivanov, O., Bärring, L., and Wilcke, R. A.: Climate change impact on snow loads in northern Europe, Structural Safety, 97, 102231, https://doi.org/10.1016/j.strusafe.2022.102231, 2022. a
Lejeune, Y., Dumont, M., Panel, J.-M., Lafaysse, M., Lapalus, P., Le Gac, E., Lesaffre, B., and Morin, S.: 57 years (1960–2017) of snow and meteorological observations from a mid-altitude mountain site (Col de Porte, France, 1325 m of altitude), Earth Syst. Sci. Data, 11, 71–88, https://doi.org/10.5194/essd-11-71-2019, 2019. a
Lievens, H., Brangers, I., Marshall, H.-P., Jonas, T., Olefs, M., and De Lannoy, G.: Sentinel-1 snow depth retrieval at sub-kilometer resolution over the European Alps, The Cryosphere, 16, 159–177, https://doi.org/10.5194/tc-16-159-2022, 2022. a
Magnusson, J., Gustafsson, D., Hüsler, F., and Jonas, T.: Assimilation of point SWE data into a distributed snow cover model comparing two contrasting methods, Water Resources Research, 50, 7816–7835, 2014. a
Malek, S. A., Avanzi, F., Brun-Laguna, K., Maurer, T., Oroza, C. A., Hartsough, P. C., Watteyne, T., and Glaser, S. D.: Real-Time Alpine Measurement System Using Wireless Sensor Networks, Sensors, 17, https://doi.org/10.3390/s17112583, 2017. a
Margulis, S. A., Cortés, G., Girotto, M., and Durand, M.: A Landsat-era Sierra Nevada snow reanalysis (1985–2015), Journal of Hydrometeorology, 17, 1203–1221, 2016. a
Mazzolini, M., Aalstad, K., Alonso-González, E., Westermann, S., and Treichler, D.: Spatio-temporal snow data assimilation with the ICESat-2 laser altimeter, The Cryosphere, 19, 3831–3848, https://doi.org/10.5194/tc-19-3831-2025, 2025. a
Metref, S., Cosme, E., Le Lay, M., and Gailhard, J.: Snow data assimilation for seasonal streamflow supply prediction in mountainous basins, Hydrol. Earth Syst. Sci., 27, 2283–2299, https://doi.org/10.5194/hess-27-2283-2023, 2023. a, b
Murphy, K. P.: Probabilistic Machine Learning: An introduction, MIT Press, http://probml.github.io/book1 (last access: 15 October 2025), 2022. a
Navari, M., Margulis, S. A., Tedesco, M., Fettweis, X., and Alexander, P. M.: Improving Greenland Surface Mass Balance Estimates Through the Assimilation of MODIS Albedo: A Case Study Along the K-Transect, Geophysical Research Letters, 45, 6549–6556, 2018. a
Oberrauch, M., Cluzet, B., Magnusson, J., and Jonas, T.: Improving Fully Distributed Snowpack Simulations by Mapping Perturbations of Meteorological Forcings Inferred From Particle Filter Assimilation of Snow Monitoring Data, Water Resources Research, 60, e2023WR036994, https://doi.org/10.1029/2023WR036994, 2024. a
Pagano, T. and Sorooshian, S.: Hydrologic cycle, University of Arizona, Tucson, AZ, USA, ISBN 0-471-97796-9, 2002. a
Pagano, T. C., Wood, A. W., Ramos, M.-H., Cloke, H. L., Pappenberger, F., Clark, M. P., Cranston, M., Kavetski, D., Mathevet, T., Sorooshian, S., and Verkade, J. S.: Challenges of operational river forecasting, Journal of Hydrometeorology, 15, 1692–1707, 2014. a
Pakdehi, M., Ahmadisharaf, E., Nazari, B., and Cho, E.: Transferability of machine-learning-based modeling frameworks across flood events for hindcasting maximum river water depths in coastal watersheds, Nat. Hazards Earth Syst. Sci., 24, 3537–3559, https://doi.org/10.5194/nhess-24-3537-2024, 2024. a
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E.: Scikit-learn: Machine Learning in Python, Journal of Machine Learning Research, 12, 2825–2830, 2011. a
Pirk, N., Aalstad, K., Mannerfelt, E. S., Clayer, F., de Wit, H., Christiansen, C. T., Althuizen, I., Lee, H., and Westermann, S.: Disaggregating the Carbon Exchange of Degrading Permafrost Peatlands Using Bayesian Deep Learning, Geophysical Research Letters, 51, e2024GL109283, https://doi.org/10.1029/2024GL109283, 2024. a, b
Prechelt, L.: Early stopping-but when?, in: Neural Networks: Tricks of the trade, Springer, 55–69, https://doi.org/10.1007/3-540-49430-8_3, 2002. a
Reba, M. L., Marks, D., Winstral, A., Link, T. E., and Kumar, M.: Sensitivity of the snowcover energetics in a mountain basin to variations in climate, Hydrological Processes, 25, 3312–3321, 2011. a
Reichle, R. H., Koster, R. D., Liu, P., Mahanama, S. P., Njoku, E. G., and Owe, M.: Comparison and assimilation of global soil moisture retrievals from the Advanced Microwave Scanning Radiometer for the Earth Observing System (AMSR-E) and the Scanning Multichannel Microwave Radiometer (SMMR), Journal of Geophysical Research: Atmospheres, 112, https://doi.org/10.1029/2006JD008033, 2007. a
Särkkä, S. and Svensson, L.: Bayesian Filtering and Smoothing, Cambridge University Press, 2 edn., https://doi.org/10.1017/9781108917407, 2023. a, b, c
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, Nature Reviews Earth & Environment, 2, 800–819, 2021. a
Sit, M., Demiray, B. Z., Xiang, Z., Ewing, G. J., Sermet, Y., and Demir, I.: A comprehensive review of deep learning applications in hydrology and water resources, Water Science and Technology, 82, 2635–2670, 2020. a
Smith, L. N.: Cyclical learning rates for training neural networks, arXiv [preprint], https://doi.org/10.48550/arXiv.1506.01186, 2015. a
Tsai, Y.-L. S., Dietz, A., Oppelt, N., and Kuenzer, C.: Remote Sensing of Snow Cover Using Spaceborne SAR: A Review, Remote Sensing, 11, https://doi.org/10.3390/rs11121456, 2019. a
Tsantekidis, A., Passalis, N., and Tefas, A.: Chapter 5 - Recurrent neural networks, in: Deep Learning for Robot Perception and Cognition, edited by Iosifidis, A. and Tefas, A., Academic Press, 101–115, ISBN 978-0-323-85787-1, https://doi.org/10.1016/B978-0-32-385787-1.00010-5, 2022. a
Van Leeuwen, P. J.: Representation errors and retrievals in linear and nonlinear data assimilation, Quarterly Journal of the Royal Meteorological Society, 141, 1612–1623, 2015. a
Wever, N.: Weissfluhjoch dataset for ESM-SnowMIP, EnviDat [data set], https://doi.org/10.16904/1, 2017. a
Xu, T. and Liang, F.: Machine learning for hydrologic sciences: An introductory overview, Wiley Interdisciplinary Reviews: Water, 8, e1533, https://doi.org/10.1002/wat2.1533, 2021. a
Zakeri, F., Mariethoz, G., and Girotto, M.: High-Resolution Snow Water Equivalent Estimation: A Data-Driven Method for Localized Downscaling of Climate Data, EGUsphere [preprint], https://doi.org/10.5194/egusphere-2024-1943, 2024. a
Short summary
Reliable snow water equivalent and snow depth estimates are key for water management in snow regions. To tackle computational challenges in data assimilation, we propose a Long Short-Term Memory neural network for operational use in snow hydrology. Once trained, it reduces computational cost by 70 percent compared to the Ensemble Kalman Filter, with a slight decrease in performances. This deep learning approach provides a scalable, efficient, and cost-effective modeling solution for hydrology.
Reliable snow water equivalent and snow depth estimates are key for water management in snow...
