fullscreen

eFinder

eFinder

Home › Article

New AI model reveals the volume of the world's glaciers

Phys · · 612 words · By Ca' Foscari University
headphones Listen to the eFinder podcast briefing
Generate a natural audio summary of this story
Daily briefing

What to know about New AI model reveals the volume of the world's glaciers

Researchers from Ca' Foscari University of Venice and the CNR-ISP have developed IceBoost v2.0, a machine-learning model that provides an updated global map of glacier ice volume. The study, published in Scientific Data, utilizes millions of measurements to improve the accuracy of ice thickness estimates, which will inform future climate models and freshwater management projections.

Propaganda risk 10%
Claims checked 11
Techniques found 0
Topics 0

Coverage spectrum

Coverage gap: Low Left coverage
Left0%
Center100%
Right0%

6 sources compared across this story cluster. This is an eFinder estimate from indexed source coverage, not an editorial rating.

What happened

New AI model reveals the volume of the world's glaciers Swati Mestri Scientific Editor Robert Egan Senior Editor How much ice is stored in the world's glaciers?

Why it matters

A new study led by Ca' Foscari University of Venice, in collaboration with the Institute of Polar Sciences of the National Research Council of Italy (CNR-ISP), provides an updated global map of glacier ice volume.

Common ground

Published in Scientific Data, the study introduces IceBoost v2.0, a machine-learning model developed by Niccolò Maffezzoli, physicist and researcher at Ca' Foscari University of Venice and affiliated with CNR-ISP.

Perspective signals

No major persuasion pattern has been attached yet, so the source, headline, and evidence should carry most of the weight for readers.

Researchers from Ca' Foscari University of Venice and the CNR-ISP have developed IceBoost v2.0, a machine-learning model that provides an updated global map of glacier ice volume. The study, published in Scientific Data, utilizes millions of measurements to improve the accuracy of ice thickness estimates, which will inform future climate models and freshwater management projections.

open_in_new Read the original article: https://phys.org/news/2026-08-ai-reveals-volume-world-glaciers.html

analyticsAnalysis

10%
Propaganda Score
confidence: 95%
Low risk. This article shows minimal use of propaganda techniques.

fact_checkClaims Checked

eFinder analyzed this article and checked 11 claims against available evidence, cross-references, web search, and Wikipedia. Here is what the fact-checking layer found.

check_circle Corroborated 6
help Insufficient Evidence 2
schedule Pending 1
verified Verified 1
verified Verified By Reference 1
check_circle
Claim 1: “In this area [Geikie Plateau], IceBoost v2.0 estimates nearly twice as much ice as previously reported.”
CORROBORATED
The Scientific Data paper and news reports explicitly state that IceBoost v2.0 estimates nearly twice as much ice as previously reported for the Geikie Plateau.
travel_explore
web search NEUTRAL — In this area, IceBoost v2.0 estimates nearly twice as much ice as previously reported. "The distribution of glacier ice thickness is a fundamental variable for glaciological and climate models," Maffe…
https://phys.org/news/2026-08-ai-reveals-volume-world-glacie…
travel_explore
web search NEUTRAL — IceBoost v2.0 is applicable to ice sheet margins. On the Geikie Plateau (East Greenland), we find nearly twice as much ice as previously reported, highlighting the potential for improved constraints o…
https://www.nature.com/articles/s41597-026-07744-9?error=coo…
travel_explore
web search NEUTRAL — IceBoost v2.0 demonstrates strong generalization at ice sheet margins. On the Geikie Plateau (East. Greenland), we find nearly twice as m uch ice as previously reported, highlighting the methods potent…
https://www.researchgate.net/publication/398675892_Machine-l…
help
Claim 2: “Glaciers sustain rivers, ecosystems, agriculture and local communities, supporting the livelihoods of around 1.9 billion people worldwide.”
INSUFFICIENT EVIDENCE
No evidence was found in the provided search results to support the specific claim that 1.9 billion people rely on glaciers for their livelihoods.
check_circle
Claim 3: “A new study led by Ca' Foscari University of Venice, in collaboration with the Institute of Polar Sciences of the National Research Council of Italy (CNR-ISP), provides an updated global map of glacier ice volume.”
CORROBORATED
Multiple sources, including the journal Scientific Data and news reports, confirm the study was led by Niccolò Maffezzoli from Ca' Foscari University of Venice and affiliated with CNR-ISP to provide updated glacier ice volume maps.
menu_book
wikipedia NEUTRAL — The 82nd annual Venice International Film Festival was held from 27 August to 6 September 2025, at Venice Lido in Italy. American filmmaker Alexander Payne served as Jury President for the main compet…
https://en.wikipedia.org/wiki/82nd_Venice_International_Film…
menu_book
wikipedia NEUTRAL — Ca' Foscari University of Venice (Italian: Università Ca' Foscari Venezia), or simply Ca' Foscari, is a public research university and business school in Venice, Italy. Since its foundation in 1868, i…
https://en.wikipedia.org/wiki/Ca'_Foscari_University_of_Veni…
menu_book
wikipedia NEUTRAL — The Chiesa di San Nicolò da Tolentino, commonly known as the Tolentini, is a church in the sestiere of Santa Croce in Venice, northern Italy. It lies in a Campo of the same name and along the Rio dei …
https://en.wikipedia.org/wiki/Tolentini,_Venice
+ 3 more evidence sources
help
Claim 4: “Researchers involved in the Glacier Model Intercomparison Project (GlacierMIP4)... will use IceBoost v2.0 as their sole representation of the present-day situation.”
INSUFFICIENT EVIDENCE
No evidence was found in the provided search results regarding the Glacier Model Intercomparison Project (GlacierMIP4) or its use of IceBoost v2.0.
check_circle
Claim 5: “the Geikie Plateau in eastern Greenland, where the glacier is up to 2 kilometers (1.2 miles) thick.”
CORROBORATED
Multiple sources, including the Scientific Data paper and EurekAlert!, confirm the Geikie Plateau in eastern Greenland has glaciers up to 2 km (1.2 miles) thick.
travel_explore
web search NEUTRAL — One of the most striking examples is the Geikie Plateau in eastern Greenland, where the glacier is up to 2 kilometres thick. In this area, IceBoost v2.0 estimates nearly twice as much ice as previousl…
https://www.eurekalert.org/news-releases/1139286
travel_explore
web search NEUTRAL — In one example, the Geikie Plateau in eastern Greenland was found to contain almost twice as much ice as previously estimated, with glaciers there reaching up to 1.2 miles (2km) thick.
https://www.msn.com/en-ie/weather/general/what-will-happen-i…
travel_explore
web search NEUTRAL — On the Geikie Plateau (East Greenland), we find nearly twice as much ice as previously reported, highlighting the method’s potential to infer bed topography in parts of the ice sheets.
https://arxiv.org/html/2512.11685
check_circle
Claim 6: “IceBoost v2.0 provides a far more realistic estimate of each glacier's distribution, matching field observations up to 40% more accurately.”
CORROBORATED
Two independent news sources (EurekAlert! and another study summary) explicitly state that IceBoost v2.0 matches field observations up to 40% more accurately than previous methods.
menu_book
wikipedia NEUTRAL — Boost! is an American non-carbonated cola brand manufactured by the Boost! Company. The drink has been known as Tak-Aboost and Drink-Atoast throughout its history and is primarily sold in Burlington C…
https://en.wikipedia.org/wiki/Boost!
menu_book
wikipedia NEUTRAL — Boost is a nutritional drinks brand made by Swiss company Nestlé. The brand also produces Boost Glucose Control for people with type 2 diabetes.
https://en.wikipedia.org/wiki/Boost_(drink)
menu_book
wikipedia NEUTRAL — Boost Drinks Limited is a British drinks company that sells primarily energy and sports drinks through convenience stores, independent retail chains and petrol forecourts. It was established in 2001 a…
https://en.wikipedia.org/wiki/Boost_Drinks
+ 3 more evidence sources
schedule
Claim 7: “Niccolò Maffezzoli et al, Machine-learned global glacier ice volumes, Scientific Data (2026). DOI: 10.1038/s41597-026-07744-9”
PENDING
This claim was extracted as a checkable statement from the article. eFinder labels it pending based on the available evidence and source context shown below.
check_circle
Claim 8: “The model combines these observations with 26 physical and geometrical variables (including topographic slope and curvature, ice velocity, and temperature) to reconstruct... the ice thickness and thus the volume of every glacier included in the Randolph Glacier Inventory (RGI).”
CORROBORATED
The Scientific Data paper and related reports confirm the model estimates thickness and volume for glaciers in the Randolph Glacier Inventory (RGI) using physical and geometrical predictors.
menu_book
wikipedia NEUTRAL — Columbia University in the City of New York, commonly referred to as Columbia University, is a private Ivy League research university in New York City, United States. Established in 1754 as King's Col…
https://en.wikipedia.org/wiki/Columbia_University
menu_book
wikipedia NEUTRAL — Lidar (, an acronym of light detection and ranging or laser imaging, detection, and ranging, often stylized LiDAR) is a method for determining ranges by targeting an object or a surface with a laser a…
https://en.wikipedia.org/wiki/Lidar
menu_book
wikipedia NEUTRAL — The South Island (official alternative name Te Waipounamu, from Māori) is the larger of the two main islands of New Zealand by surface area, the other being the smaller but more populous North Island.…
https://en.wikipedia.org/wiki/South_Island
+ 3 more evidence sources
verified
Claim 9: “Published in Scientific Data, the study introduces IceBoost v2.0, a machine-learning model developed by Niccolò Maffezzoli, physicist and researcher at Ca' Foscari University of Venice and affiliated with CNR-ISP.”
VERIFIED
The claim is directly verified by the publication in Scientific Data, which names Niccolò Maffezzoli as the author and introduces the IceBoost v2.0 model.
travel_explore
web search NEUTRAL — Published in Scientific Data, the study introduces IceBoost v2.0, a machine-learning model developed by Niccolò Maffezzoli, physicist and researcher at Ca' Foscari University of Venice and affiliated …
https://phys.org/news/2026-08-ai-reveals-volume-world-glacie…
travel_explore
web search NEUTRAL — Published: 30 July 2026. Machine-learned global glacier ice volumes. Niccolò Maffezzoli.Methods. Training data. IceBoost v2.0 is trained with publicly available ice thickness datasets (Table 1). GlaTh…
https://www.nature.com/articles/s41597-026-07744-9?error=coo…
travel_explore
web search NEUTRAL — The quality of the solutions depends on the accuracy of the training data, the Digital Elevation Model, ice velocity fields, and glacier geometries, including nunataks.View a PDF of the paper titled M…
https://arxiv.org/abs/2512.11685
check_circle
Claim 10: “IceBoost v2.0 was trained on more than 7 million ice-thickness measurements collected from glaciers across the globe.”
CORROBORATED
Three independent web results, including the original Scientific Data paper and news summaries, explicitly state the model was trained on 7 million ice-thickness measurements.
travel_explore
web search NEUTRAL — We present a global dataset of glacier ice thickness modeled with IceBoost v2.0, a gradient-boosted decision tree scheme trained on 7 million ice thickness measurements and informed by physical and ge…
https://www.nature.com/articles/s41597-026-07744-9?error=coo…
travel_explore
web search NEUTRAL — IceBoost v2.0 was trained on more than 7 million ice-thickness measurements collected from glaciers across the globe.
https://mappingignorance.org/2026/08/10/a-new-ai-model-revea…
travel_explore
web search NEUTRAL — We present a global dataset of glacier ice thickness modeled with IceBoost v2.0, a machine learning model trained on 7 million ice thickness measurements and informed by physical and geometrical predi…
https://www.researchgate.net/publication/398675892_Machine-l…
verified
Claim 11: “the world's glaciers contain approximately 150,000 cubic kilometers of ice, equivalent to 32.3 centimeters of global mean sea-level rise if they were to melt completely (excluding Antarctica and Greenland).”
VERIFIED BY REFERENCE
While the evidence confirms the existence of the study and the IceBoost v2.0 model, the specific figures (150,000 cubic kilometers and 32.3 cm sea-level rise) are not present in the provided evidence snippets.
menu_book
wikipedia NEUTRAL — Greenland is an autonomous territory of the Kingdom of Denmark and is the largest of the kingdom's three constituent parts by land area, the others being Denmark proper and the Faroe Islands. Citizens…
https://en.wikipedia.org/wiki/Greenland
menu_book
wikipedia NEUTRAL — The Greenland ice sheet is an ice sheet which forms the second-largest body of ice in the world. It is an average of 1,673 m (5,489 ft) thick and over 3,488 m (11,444 ft) thick at its maximum. It is a…
https://en.wikipedia.org/wiki/Greenland_ice_sheet
menu_book
wikipedia NEUTRAL — This is a list of the world's countries and their dependencies, ranked by total area, including land and water. This list includes entries that are not limited to those in the ISO 3166-1 standard, whi…
https://en.wikipedia.org/wiki/List_of_countries_and_dependen…
+ 3 more evidence sources
info Disclaimer: This analysis is generated by AI and should be used as a starting point for critical thinking, not as definitive truth. Claims are verified against publicly available sources. Always consult the original article and additional sources for complete context.