[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122475-en":3,"doc-seo-122475-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122475,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine learning improves seasonal mass balance prediction for unmonitored glaciers","Glacier evolution models based on temperature-index methods are widely used to evaluate hydrological impacts of glacier change, but existing calibration frameworks struggle to transfer information from sparse, high-resolution observations between glaciers. This reduces the ability to resolve seasonal mass balance for unmonitored glaciers in large-scale applications. A data-driven Mass Balance Machine (MBM) using the XGBoost architecture is introduced, trained on ~4000 seasonal and annual point measurements from 32 Norwegian glaciers (1962–2021). Compared with regional-scale simulations from three glacier evolution models, MBM accurately predicts annual and seasonal point mass balance on independent test glaciers, improving seasonal performance across spatial scales and reducing RMSE up to 46% (winter) and 25% (summer).","The Cryosphere, 19, 5801–5826, 2025  \n[https://doi.org/10.5194/tc-19-5801-2025](https://doi.org/10.5194/tc-19-5801-2025)[ ](https://doi.org/10.5194/tc-19-5801-2025)© Author(s) 2025 . This work is distributed under the Creative Commons Attribution 4 .0 License.  \nMachine learning improves seasonal mass balance prediction for unmonitored glaciers  \nKamilla Hauknes Sjursen 1 , Jordi Bolibar2,3 , Marijn van der Meer4,5 , Liss Marie Andreassen6 ,  \nJulian Peter Biesheuvel3 , Thorben Dunse 1 , Matthias Huss4,5,7 , Fabien Maussion8,9 , David R. Rounce 10 , and Brandon Tober 10  \n1Department of Civil Engineering and Environmental Sciences, Western Norway University of Applied Sciences (HVL), Sogndal, Norway  \n2Univ. Grenoble Alpes, CNRS, IRD, G-INP, Institut des Géosciences de l'Environnement, Grenoble, France  \n3Faculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, the Netherlands  \n4Laboratory of Hydraulics, Hydrology, and Glaciology (VAW), ETH Zürich, Zurich, Switzerland  \n5 Swiss Federal Institute for Forest, Snow, and Landscape Research (WSL), Sion, Switzerland  \n6Norwegian Water Resources and Energy Directorate (NVE), Oslo, Norway  \n7Department of Geosciences, University of Fribourg, Fribourg, Switzerland  \n8Bristol Glaciology Centre, School of Geographical Sciences, University of Bristol, Bristol, UK  \n9Department of Atmospheric and Cryospheric Sciences, University of Innsbruck, Innsbruck, Austria  \n10Department of Civil and Environmental Engineering, Carnegie Mellon University, Pittsburgh, PA, USA Correspondence: Kamilla Hauknes Sjursen ([kasj@hvl.no](kasj@hvl.no))  \nReceived: 14 March 2025 – Discussion started: 31 March 2025  \nRevised: 11 August 2025 – Accepted: 22 September 2025 – Published: 17 November 2025  \nAbstract. Glacier evolution models based on temperatureindex approaches are commonly used to assess hydrological impacts of glacier changes. However, current model calibration frameworks cannot efficiently transfer information from sparse high-resolution observations across glaciers. This limits their ability to resolve seasonal mass changes on unmonitored glaciers in large-scale applications. Machine learning approaches can potentially address this limitation by learning relationships from sparse data that are transferable in space and time, including to unmonitored glaciers. Here, we present the Mass Balance Machine (MBM), a data-driven mass balance model based on the XGBoost architecture, designed to provide accurate and high spatio-temporal resolution regional-scale reconstructions of glacier mass balance. We trained and tested MBM using a dataset of approximately 4000 seasonal and annual point mass balance measurements from 32 glaciers across heterogeneous climate settings in mainland Norway, spanning from 1962 to 2021 . To assess the advantage of MBM's generalisation capabilities, we compared its predictions on independent test glaciers at various spatio-temporal scales with those of regional-scale simula-  \ntions from three glacier evolution models. MBM successfully predicted annual and seasonal point mass balance on the test glaciers (RMSE of 0.59–1.00 m w.e. and bias of 􀀀0.01 to 0.04 m w.e.) . On seasonal mass balance, MBM outperformed the other models across spatial scales, reducing RMSE by up to 46 % and 25 % on glacier-wide winter and summer mass balance, respectively. Our results demonstrate the capability of machine learning models to generalise across glaciers and climatic settings from relatively sparse mass balance data, highlighting their potential for a wide range of applications.  \n1 Introduction  \nGlaciers around the world are losing mass and retreating due to atmospheric warming (IPCC, 2019), with numerous impacts on nature and society (Schaub et al., 2013 ; Huss et al., 2017 ; Milner et al., 2017 ; Varnajot and Saarinen, 2021 ; Emmer et al., 2022 ; Bosson et al., 2023) . Glaciers represent significant freshwater reservoirs that modulate downstream freshwater availabil","cbCaif2Fqc0jos0J","https://ap.wps.com/l/cbCaif2Fqc0jos0J","pdf",12629221,1,26,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What problem does the paper address in glacier mass balance modeling?\",\"answer\":\"Existing temperature-index model calibration frameworks cannot efficiently transfer information from sparse high-resolution observations across glaciers, limiting seasonal mass balance prediction for unmonitored glaciers at large scales.\"},{\"question\":\"What is the Mass Balance Machine (MBM)?\",\"answer\":\"MBM is a data-driven mass balance model built on the XGBoost architecture, designed to produce accurate regional-scale reconstructions with high spatio-temporal resolution.\"},{\"question\":\"How was MBM evaluated and what were the main results?\",\"answer\":\"MBM was trained and tested using ~4000 seasonal and annual point mass balance measurements from 32 glaciers in mainland Norway (1962–2021) and then compared on independent test glaciers with simulations from three glacier evolution models. MBM achieved strong annual and seasonal point predictions and outperformed other models on seasonal mass balance, reducing RMSE up to 46% for winter and 25% for summer.\"}]","Machine learning improves seasonal mass balance prediction for unmonitored glaciers | PDF",1785810851,66,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-improves-seasonal-mass-balance-prediction-for-unmonitored-glaciers","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-improves-seasonal-mass-balance-prediction-for-unmonitored-glaciers/122475/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in glacier mass balance modeling?","Question",{"text":75,"@type":76},"Existing temperature-index model calibration frameworks cannot efficiently transfer information from sparse high-resolution observations across glaciers, limiting seasonal mass balance prediction for unmonitored glaciers at large scales.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the Mass Balance Machine (MBM)?",{"text":80,"@type":76},"MBM is a data-driven mass balance model built on the XGBoost architecture, designed to produce accurate regional-scale reconstructions with high spatio-temporal resolution.",{"name":82,"@type":73,"acceptedAnswer":83},"How was MBM evaluated and what were the main results?",{"text":84,"@type":76},"MBM was trained and tested using ~4000 seasonal and annual point mass balance measurements from 32 glaciers in mainland Norway (1962–2021) and then compared on independent test glaciers with simulations from three glacier evolution models. MBM achieved strong annual and seasonal point predictions and outperformed other models on seasonal mass balance, reducing RMSE up to 46% for winter and 25% for summer.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]