Observing lake- and river-ice decay with SAR: advantages and limitations of the unsupervised <i>k</i>-means classification approach
Bibliographic record
Abstract
Abstract Large parts of the Arctic are covered by water bodies. Ice covers on lakes and rivers prohibit the exchange of heat and water vapor between the water body and the atmosphere. With melt onset, the ecosystem is subjected to changes, making it important to monitor the ice decay. As ground-based monitoring of these vast uninhabited areas is expensive and thus restricted to a few locations, remote-sensing techniques need to be applied. Here we evaluate the performance of the unsupervised k-means classification for dividing ice and water fractions on lakes and river channels from spaceborne radar data in comparison to threshold-based methods. The analysis is based on six TerraSAR-X and three RADARSAT-2 images, obtained during spring 2011 over the central Lena Delta in northern Siberia. The performance of the k-means classification is found to be similar to a fixed-threshold approach. As the k-means classification does not need prior statistical backscatter analyses to account for the radar configuration and ice conditions, it is easier to use than the threshold method. In addition, we found that the application of a low-pass filter prior to the classification of river channels and a closing filter on the classification results of lakes strongly improves the overall classification results.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 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 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".