A Conditional Denoising Diffusion Probabilistic Model for Sea Ice Concentration Estimation
Bibliographic record
Abstract
Research on estimating sea ice concentration (SIC) from synthetic aperture radar (SAR) data using convolutional neural networks (CNNs) has been widely reported. However, the presence of speckle noise in dual-polarization SAR signals and confusion at ice-water boundaries complicates accurate density estimation, often leading to significant underestimations of SIC. Recently, diffusion models (DMs) have shown significant success in various remote sensing tasks, demonstrating their potential to address these challenges. However, applying DMs directly to SIC estimation leads to singularity issues, hindering the accuracy of results. Additionally, directly incorporating conditional images can cause denoising models to overlook the differences between conditional and noise information. We introduce a conditional denoising diffusion probabilistic model (DiffSIC) that can fundamentally resolve the singularity problem by reweighting the loss function. We designed a U-shaped architecture that integrates conditional information, time steps, and noise information for SIC estimation. Extensive experiments conducted on the AI4Arctic dataset indicate that the proposed DiffSIC framework achieves a coefficient of determination (<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</i><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>) of 90.959% and a root mean square error (RMSE) of 8.632%, demonstrating the effectiveness and potential of diffusion models in the task of SIC estimation.
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 | 0.000 |
| Science and technology studies | 0.001 | 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".