Large-scale and High-resolution Frontal Ablation Estimates in the Arctic through a Machine Learning Approach
Bibliographic record
Abstract
Frontal ablation is an important component of tidewater glacier mass loss, however, high temporal resolution estimates have remained elusive due to difficulty in reliably capturing terminus position changes with satellite imagery. Recent developments in machine learning-based radar image segmentation to automatically delineate glacier fronts has opened an opportunity to calculate frontal ablation over fine timescales. Through segmentation of Sentinel-1 synthetic aperture radar image sequences, we aim to quantify seasonal and annual frontal ablation across several Arctic regions, using a deep learning-based terminus segmentation algorithm. Svalbard, an Arctic region characterized by variable and complex glacier and fjord geometries, will serve as a methodological test site before expanding the scope to the Canadian Arctic, Greenland periphery, and Russian Arctic, or ~1400-1500 marine-terminating glaciers in the Northern Hemisphere. The derived frontal ablation information is valuable to climate and glacier models, which could benefit from high-resolution reference data, resulting in improved calibrations and parameterizations. Future project efforts will include quantifying total mass budget for all glaciers in the study by integrating frontal changes, ice discharge calculations from ice thickness and surface velocity products, and climatic mass balance data. To identify and evaluate external drivers of glacier change, the frontal ablation and mass balance products will be combined with modeled and observational atmospheric, oceanic, and sea ice data. Through multivariate statistical analyses between these Earth system datasets and mass balance components, we look to provide an improved understanding of dynamic tidewater glacier processes, their spatio-temporal variability, and the influence of glacier geometry on observed changes throughout the Arctic.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".