This study introduces a new software, cLASpy_T, that helps design models for the automatic 3D point cloud classification of coastal environments. This software is based on machine learning algorithms from the scikit-learn library and can classify point clouds derived from LiDAR or photogrammetry. Input data can be imported via CSV or LAS files, providing a 3D point cloud, enhanced with geometric features or spectral information, such as colors from orthophotos or hyperspectral data. cLASpy_T lets the user run three supervised machine learning algorithms from the scikit-learn API to build automatic classification models: RandomForestClassifier, GradientBoostingClassifier and MLPClassifier. This work presents the general method for classification model design using cLASpy_T and the software’s complete workflow with an example of photogrammetry point cloud classification. Four photogrammetric models of a coastal dike were acquired on four different dates, in 2021. The aim is to classify each point according to whether it belongs to the ‘sand’ class of the beach, the ‘rock’ class of the riprap, or the ‘block’ class of the concrete blocks. This case study highlights the importance of adjusting algorithm parameters, selecting features, and the large number of tests necessary to design a classification model that can be generalized and used in production.

Swell propagation and transformation across variable bathymetry and coastal obstacles fundamentally control nearshore wave energy redistribution, sediment transport, and shoreline evolution. Conventional satellite altimetry cannot adequately resolve these dynamics, particularly refraction and diffraction as swell transition into shallow waters. Leveraging high‐rate (HR) observations from the Surface Water and Ocean Topography (SWOT) mission, we present the first spaceborne measurements of nearshore‐coastal wave transformation at sub‐kilometric scales. SWOT HR observations over the English Channel during Storm Mathis reveal wavelength shortening, directional shift and distinctive fan‐shaped diffraction patterns, including a 27.5° island‐induced diffraction signal undetected by operational models. Comparisons with in situ measurements and the Atlantic‐European Northwest Shelf (NWShelf) Reanalysis, a regional configuration of the WAVEWATCH III spectral wave model, validate the robustness of the SWOT‐derived wave parameters. This finding establishes SWOT HR data as a new observational capability for quantifying wave‐bathymetry interactions and the resultant redistribution of wave energy that conventional altimetry fails to resolve.

Storm waves undergo rapid transformation as they propagate into shallow, complex coastalwaters, yet these processes are difficult to observe at the scales at which they occur. We assess the capability of Surface Water and Ocean Topography (SWOT) High-Rate (HR) altimetry to map storm-wave wavelength, propagation direction and period across the English Channel. Four storms (Mathis, Ciarán, Debi and Nelson, 2023–2024) were analysed over HR scenes on 5 km boxes, using two independent spectral estimators (2D Welch and Radon–Fourier). The 180° ambiguity was resolved from the SSH–𝜎 0 cross-spectrum, period was derived through finite- depth dispersion including a depth-weighted current Doppler correction, and every retrieval carries bootstrap uncertainty and an observability grade. Propagation direction is the most robust product, it agrees with a WAVEWATCH III forecast within about 11° RMSE, and the two estimators agree within 10° in 96% of common boxes. Wavelength is systematically longer than modelled (+32 to +45 m). Decomposition of the retrieved wavevector attributes this bias to across-track compression near nadir and along-track compression consistent with known KaRIn imaging distortions, which the derived period inherits. Relative changes along transects are nevertheless robust. For Storm Ciarán, SWOT HR resolves 19% depth-controlled wavelength shortening consistent with linear dispersion, refraction reproduced in sign and magnitude by ray tracing, and a 36–49° directional rotation with spectral broadening in the lee of Sark, characteristic of diffraction. SWOT HR thus provides a new spatial observation of coastal storm- wave transformation, while inversion of the imaging response is required to retrieve absolute wavelength, period and energy.