Bridging the cloud gap: AHI/ATMS synergy through CNN feature fusion for all-weather SST retrieval
Bibliographic record
Abstract
Infrared-based Sea Surface Temperature (SST) retrieval methods face persistent challenges from cloud-induced data gaps and accuracy degradation. This study bridges this critical limitation through multisensor satellite synergy, integrating geostationary Advanced Himawari Imager (AHI) with Advanced Technology Microwave Sounder (ATMS) data via a Convolutional Neural Network (CNN) for all weather SST retrieval. The CNN model adaptively extracts features from multi-band AHI/ATMS imagery, effectively predicting SST under varying cloud conditions. Evaluation results demonstrate a root mean square error (RMSE) of 2.07 °C, a mean absolute error (MAE) of 1.22 °C, and a coefficient of determination (R 2 ) of 0.88 on the test dataset. Under the same CNN framework, unimodal retrievals from AHI and ATMS alone yield substantially lower performance (R 2 = 0.51, RMSE = 3.45 °C; and R 2 = 0.63, RMSE = 2.64 °C, respectively), confirming the complementary benefits of multisensor fusion. Comparisons with a Transformer-based model, the daily OSTIA product, and the official AHI SST product (clear-sky conditions) further indicate that the proposed CNN achieves the highest accuracy. Although RMSE exceeds 1 °C for certain cloud types, the method substantially mitigates cloud-induced data loss and provides a reliable, high-accuracy, all-weather SST retrieval strategy for satellite ocean remote sensing.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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".