Air–Sea Interface Parameters and Heat Flux from Neural Network and Advanced Microwave Scanning Radiometer Observations
Bibliographic record
Abstract
We present a new approach, based on a multi-parameter back-propagation neural network (BPNN) model, to simultaneously retrieve sea surface wind speed, sea surface temperature, near-surface air temperature, and dewpoint temperature over the global oceans from the Advanced Microwave Scanning Radiometer 2 (AMSR2) onboard the Global Change Observation Mission 1st-Water (GCOM-W1). The model is trained and validated with the collocations of AMSR2 multi-channel (6.9–36.5 GHz) brightness temperatures, under both clear and cloudy conditions, and National Data Buoy Center (NDBC) and Tropical Atmosphere Ocean Project (TAO) buoy measurements along with ECMWF ERA5 reanalysis data. The root-mean-square (rms) errors of BPNN-retrieved sea surface wind speed, sea surface temperature, near-surface air temperature, and dewpoint temperature are 1.13 m/s, 1.02 °C, 1.20 °C, and 1.57 °C, respectively. The first three retrieved geophysical parameters and the estimated relative humidity from near-surface air temperature and dewpoint temperature are used to compute the sensible heat flux (SHF) and latent heat flux (LHF), using an improved bulk flux parametrization. The rms errors of the estimated SHF and LHF from BPNN-derived air–sea interface variables, and those from buoy and reanalysis data, are 18.13 W/m2 and 39.56 W/m2. We also compare SHF and LHF estimates with the Yongxing air–sea flux tower measurements in the northern South China Sea. The estimated SHF and LHF in summer and autumn periods are closer to observations than in winter and spring. The proposed method has potential to derive instantaneous air–sea interface atmospheric and oceanic parameters as well as surface sensible and latent heat fluxes from AMSR2 along-track wide swath observations.
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 | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".