Machine Learning Based Estimation of Coastal Bathymetry From ICESat-2 and Sentinel-2 Data
Bibliographic record
Abstract
Satellite technology is an efficient tool, which can provide valuable observations for coastal areas from space. Compared to conventional bathymetric surveying approaches, remote sensing based shallow water bathymetry retrieval methods have been widely used in recent years. Various empirical models have been proposed for deriving bathymetry of coastal shallow water, and prior topographic information is required to construct models. Traditional studies tend to select a cloud-free remote sensing image to map the coastal shallow water topography. As a result, in addition to the selection of empirical models, the high-quality remote sensing image and accurate prior topographic data are also of importance. This study aims to propose a method for mapping coastal shallow water bathymetry from multi-temporal remote sensing imagery. Here, Sentinel-2 imagery time series are composited to produce a clear image, which can effectively avoid the contamination of clouds, water turbidity and other noises. ICESat-2 lidar altimeter data that contain accurate underwater elevations are used to provide topographic information. Moreover, Sentinel-2 based multispectral information and ICESat-2 based topographic information are combined for the coastal bathymetry retrieval by five empirical models (i.e., linear band model, ratio band model, support vector machine, neural network, and random forest). This proposed method is tested in Dongsha Atoll in South China Sea, and achieve a good performance (training: RMSE: 0.97m±0.76m, MAPE: 4.07%±0.046%, R2: 0.90±0.14; validation: RMSE: 1.22m±0.43m, MAPE: 5.43%±0.035%, R2: 0.86±0.089). The comparison confirms that machine learning methods perform better than traditional methods, and the deep learning techniques can be further introduced in estimating shallow water bathymetry in the future, which is expected to achieve an excellent accuracy in bathymetry inversion.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".