MétaCan
Menu
Back to cohort
Record W4408422800 · doi:10.5194/egusphere-egu25-725

Breaking the Ice Between Machine Learning Experts and Cryosphere Scientists - The ML4Cryo Research Community

2025· preprint· en· W4408422800 on OpenAlexaff
Kim B. Bente, Julia Kaltenborn, Andrew McDonald

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldDecision Sciences
TopicScientific Computing and Data Management
Canadian institutionsMcGill UniversityMila - Quebec Artificial Intelligence Institute
Fundersnot available
KeywordsCryospherePhysical geographyAstrobiologyEnvironmental scienceEarth scienceGeologyGeographyOceanographySea icePhysics

Abstract

fetched live from OpenAlex

Recently, Machine Learning (ML) has emerged as a powerful tool within cryospheric sciences, offering innovative and effective solutions for observing, modelling, and understanding Earth's frozen regions. However, the ML and cryosphere communities have traditionally been poles apart, each shaped by distinct research motivations, publishing paradigms, and evaluation criteria. These research silos can lead to common pitfalls of interdisciplinary research, such as "helicopter science", insights getting lost in translation, or the continued use of outdated (ML) methods. To fully harness the compelling opportunities for impactful research at the intersection of these two fields, machine learning practitioners and domain scientists must join forces. To address this gap between machine learning and cryosphere research, we established ML4Cryo (Machine Learning for the Cryosphere, see https://ml4cryo.github.io/), a global research community that leverages collective expertise across diverse fields such as deep learning, physics-informed ML, remote sensing, and both terrestrial and marine cryospheric domains. Our goal is not only to advance scientific discovery but also to foster application-driven advances in machine learning research. ML4Cryo aims to empower researchers by initiating conversations and collaborations, enabling machine learning specialists to learn about the most pressing challenges within the cryosphere, while cryosphere researchers can learn about the state-of-the-art models developed by the ML community. Contributing to ML4Cryo’s mission, our platform serves as a community-driven hub to share and discover ideas, recent publications, tools, software, datasets, knowledge resources, funding opportunities, best practices, as well as relevant conferences and events. We invite you to join ML4Cryo, where the synergy between machine learning and cryospheric science paves the way for impactful and rewarding research.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.037
metaresearch head score (Gemma)0.068
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesScience and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Commentary · Consensus signal: none
Teacher disagreement score0.996
Threshold uncertainty score0.196

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0370.068
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0040.004
Science and technology studies0.0040.006
Scholarly communication0.0100.026
Open science0.0040.024
Research integrity0.0060.010
Insufficient payload (model declined to judge)0.0230.018

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.498
GPT teacher head0.521
Teacher spread0.023 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

Study designNot applicable
Domainnot available
GenreCommentary

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicScientific Computing and Data ManagementFrench-language works237,207