Aug 2026· Remote Sensing· Vol 18, pp. 2511· 0 citations· 49 references
Abstract
Submarine sand waves are widespread on shallow continental shelves. Their complex morphology and potential mobility create challenges for engineering surveys, navigation safety, and seabed stability assessment. Multibeam surveys provide accurate bathymetry but are costly and spatially limited, whereas satellite-based methods offer broader coverage but remain challenging in complex sand wave fields. Here, we propose a spatial-sequential 2DCNN–LSTM model for retrieving submarine sand wave bathymetry from Sentinel-2 surface reflectance imagery. The model represents each target point as a sequence of local multispectral image patches, allowing convolutional layers to extract two-dimensional textural features and LSTM layers to learn profile-scale rhythmic continuity associated with sand wave morphology. The model was trained using multibeam bathymetry and applied to a large extrapolation area of approximately 4000 km2 on the Taiwan Banks. Evaluation on the large extrapolated area against in situ bathymetric data achieved a root mean square error (RMSE) of 3.78 m, a mean absolute error (MAE) of 2.99 m, and a mean relative error (MRE) of 9.1%. The results demonstrate that sand wave-induced optical textures can provide useful information for broad-scale bathymetric reconstruction, although model performance remains dependent on image texture visibility controlled by hydrodynamic, illumination, and atmospheric conditions. This framework offers a cost-effective approach for satellite-based monitoring of large submarine sand wave fields, providing a new perspective for engineering applications.
It is shown that high-resolution sea ice topography can be reconstructed directly from optical satellite imagery using a conditional diffusion framework, providing a scalable pathway for high-resolution sea ice mapping and roughness estimation in data-sparse environments.
T. Cannon, Michel Tsamados, P. Manescu et al.· 0 citations
Mapping seafloor topography is of great significance for deep-sea navigation, marine resource exploration, and aquatic ecosystem conservation. Advances in bathymetric surveying technology have progressively enriched our understanding of the oceans. However, due to the high cost and low coverage of ship-based surveys, extensive regions of the global ocean remain unmeasured. Bathymetric prediction based on gravity anomalies remains the dominant approach for mapping the seafloor. Traditional physical methods are constrained by limitations in model assumptions, making it difficult to further improve the accuracy of depth estimation. Given their strong capability for nonlinear fitting, neural network methods have attracted growing interest in bathymetric estimation. Nevertheless, their inherent tendency to overfit often leads to poor generalization performance—particularly when the water depth distribution in the test set diverges from that of the training set, a common scenario in seafloor mapping due to ship tracks typically avoiding shallow or reef-prone areas. To address this limitation, this paper proposes a novel framework integrating traditional physical models with neural networks: the Geospatial Dual-Channel Attention Physics-constrained Network for bathymetry prediction. The bathymetric model derived from the Parker–Oldenburg method is incorporated into the network. Notably, an attention mechanism is integrated into the architecture to enhance the model’s fitting capacity. Extensive validation demonstrates the effectiveness of the proposed model, with 97.2561% of the residuals falling within \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pm 100$$\end{document} m.
Jia Hu, Yi-Feng Luo, Chao Wang et al.· Deutsche Hydrographische Zei...· 1 citation
The use of Satellite-Derived Bathymetry (SDB) constitutes an efficient, cost-effective, time-saving, and scalable approach for generating high-resolution shallow-water bathymetry. In this context, SDB can be proven to be a valuable method for supporting bathymetric surveys of submerged archaeological sites. This paper focuses on the ancient city of Asopos, located on the coast of the modern village of Plytra in Laconia, SE Peloponnese, Greece. The site occupies an extensive coastal area characterised by numerous ancient remains and geomorphological features distributed along the shoreline and within the nearshore zone. To achieve the objective of producing a very-high-resolution SDB map, one empirical and four machine learning approaches were evaluated: (a) the quadratic Stumpf band-ratio model; (b) Categorical Boosting; (c) Random Forest; (d) Extreme Gradient Boosting, with all models trained using the same three optimal spectral band ratios; and (e) the CatBoost model trained using principal components derived from a Principal Component Analysis of the multispectral dataset. These approaches were developed using multispectral WorldView-2 imagery and 208 in situ depth measurements as ground truth, collected across a different range of depths and distances from the coastline. Pan-sharpened imagery was used for visual interpretation. Model accuracy was assessed using an additional validation dataset of 57 depth measurements. This combined approach demonstrates that VHR SDB mapping of the nearshore zone is highly effective when employing three band ratios involving the blue, green, and yellow bands, achieving a root mean squared error of less than 1 m, and can therefore serve as a reliable method for shallow-water geoarchaeological investigations.
Supraglacial lake depth is a key variable for quantifying surface meltwater storage and assessing ice-shelf stability, yet spatially continuous and reliable bathymetric information remains difficult to obtain in polar regions because in situ measurements are scarce and optical imagery cannot directly provide water depth. This study develops an integrated framework for supraglacial lake identification and bathymetry retrieval by combining ICESat-2 ATL03 photon-counting lidar data with Sentinel-2 multispectral imagery. ICESat-2 lake photons were used to constrain lake-region extraction from Sentinel-2 imagery, and the photon-derived along-track depths were corrected for scattering and refraction before being converted into Sentinel-2 pixel-level depth labels. Based on these labels, four retrieval models were constructed and evaluated, including an empirical model, CatBoost, a convolutional neural network (CNN), and a residual dense network (RDN). CatBoost generated initial depth estimates, while CNN and RDN further incorporated the CatBoost-derived depth prior and Sentinel-2 multispectral features for pixel-level depth prediction. Experiments over four investigated supraglacial lakes showed that RDN achieved the best average performance across the investigated lakes, with mean R2, RMSE, and MAE values of 0.927, 0.187 m, and 0.144 m, respectively. For the investigated lakes, the integration of ICESat-2 and Sentinel-2 extended discrete along-track reference-depth observations to spatially continuous bathymetry maps. Because the training and validation samples were obtained from different spatial blocks within the same four lake scenes, the reported performance primarily reflects within-lake spatial generalization under the investigated conditions, and transferability to unseen lakes remains to be evaluated. These maps may provide inputs for future lake-volume estimation and ice-shelf hydrological analyses, while their applicability to lakes with different morphological and optical conditions requires further evaluation.
Yuzhou Wu, Yinqiang Zheng, Yi Shen et al.· Remote Sensing· 0 citations
Satellite-derived bathymetry (SDB) technology for mapping shallow water around islands and reefs plays a crucial role in the management of coastal zone resources. The accuracy of SDB depends strongly on the selection of satellite remote sensing data and bathymetric models. This study evaluated the performance of five SDB inversion methods, including the log-transformed linear model, log-transformed band-ratio model, k-nearest neighbor regression, random forest, and support vector regression, using Landsat-8, Sentinel-2, and WorldView-2 imagery together with measured bathymetric data from Lingyang Reef. We compared and analyzed the bathymetric results of remote sensing data with different spatial resolutions in empirical models and machine learning models. The results show that the bathymetric results derived from different data across all models were able to reflect the spatial variation trends of water depth. The machine learning models achieved higher overall accuracy than the empirical models, with the random forest performing best across different data conditions. Sentinel-2 data exhibited greater stability in empirical model fitting, while WorldView-2 imagery achieved higher bathymetric accuracy when used with machine learning models. This study provides an empirical evidence for the appropriate selection of multispectral imagery with varying spatial resolutions and corresponding shallow water bathymetry models, contributing to enhanced accuracy and broader applicability of SDB.
Tianqi Lu, Luyi Wang, Caiying Ji et al.· Scientific Reports· 0 citations
Uniform density-contrast assumptions in gravity-derived bathymetry produce substantial systematic errors. This problem stands out in regions with strong lateral density variation, such as the central–northern South China Sea. Conventional constant or simple vertically varying density models fail to capture these complexities. To overcome this limitation, a spatially varying density-contrast field is constructed by integrating multi-source geophysical data (crustal, gravity, and bathymetric data) using a back-propagation (BP) neural network. This field is incorporated into an adaptive Parker–based inversion, yielding a high-resolution bathymetric grid with Root Mean Square (RMS) improvements of 2.6 m over the constant-density approach, together with the smallest systematic bias. The most significant gains occur in shallow reef-dominated waters (0 to −1500 m), where relative RMS reductions reach approximately 9%. By coupling neural network-derived density modelling with physically rigorous inversion, the approach overcomes limitations of uniform-density assumptions while retaining interpretability, providing an efficient and reliable approach to high-precision seafloor mapping in geologically complex regions.
Chunhong Wu, Chuang Xu, Laiyong Song et al.· Geophysical Journal Internat...· 0 citations
