A 3.3‐Million‐Year Record of Antarctic Iceberg Rafted Debris and Ice Sheet Evolution Quantified by Machine Learning
Bibliographic record
Abstract
Abstract Over the last 3.3 million years, the Antarctic Ice Sheet (AIS) has undergone phases of ice sheet growth and decay, impacting sea level and climate globally. Presently, the largely marine‐terminating AIS loses mass primarily by iceberg calving and basal melt of ice shelves. Quantifying past rates and timing of AIS melt is vital to understanding future cryosphere and sea level changes. One proxy for past ice sheet instabilities is iceberg rafted debris (IRD) fluxes. However, traditional methods of IRD quantification are labor‐intensive. Here, we present a new method of identifying IRD grains in sediment core X‐ray images using a convolutional neural network machine learning algorithm. We present a 3.3‐million‐year record of AIS IRD melt events using sediment cores from International Ocean Discovery Program Sites U1536, U1537, and U1538 in the Southern Ocean's “Iceberg Alley.” We identify two increases in the IRD fluxes throughout this period, at ∼1.8 and 0.43 Ma. We propose that after 1.8 Ma, the AIS expanded and transitioned from a primarily terrestrial‐terminating to a primarily marine‐terminating ice sheet. Therefore, after 1.8 Ma, glacial terminations and AIS iceberg discharge are associated with variations in global ice volume, presumably through the mechanism of sea level and, therefore, grounding line change. The second AIS regime change occurs during the Mid‐Brunhes Event (∼0.43 Ma). After this time, there are heightened and continuous IRD fluxes at each glacial termination, indicating increased AIS size and instability after this time.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".