This paper introduces a highly novel approach to disentangling the complex processes driving short-term beach changes through an unsupervised, data-driven method. This is impressive work, as it enables the grouping of similar processes across both space and time, allowing researchers to make effective use of the vast amounts of PLS data. The proof-of-concept presented here is both important and interesting, offering a significant step forward in how we interpret high-frequency coastal dynamics. However, while the data-driven methodology is a strong asset, the manuscript would benefit from a more rigorous geomorphological justification for the specific thresholds and technical choices made during the analysis.

One area for improvement concerns the integration of environmental variables. While the authors claim to combine these variables with the 4D-OBCs, the current analysis remains largely qualitative, relying on manual comparisons and interpretations for only eight selected clusters. To avoid giving readers the false impression of a fully automated or integrated analysis, the abstract and introduction should be rephrased to accurately reflect this level of manual intervention. Furthermore, the authors should explore or at least highlight a bit earlier whether/how a more data-driven comparison, such as calculating direct correlations between clusters and environmental drivers. At the moment some discussion is performed solely towards the end of the manuscript.

The spatial relevance of the environmental data requires further clarification. The monitoring stations used appear quite distant from the PLS site, raising questions about whether these data streams remain spatially correlated with the local beach forms. The authors should also address whether the model needs to account for sediment availability, specifically considering inputs from along-shore transport or foreshore regions, which are critical drivers of geomorphic change. Finally, regarding data management, the authors suggest partitioning large datasets based on existing gaps. However, for continuous datasets where gaps are few or non-existent, a clearer strategy is needed; the authors might consider discussing whether a sliding window approach would be more appropriate than arbitrary partitioning to avoid artificial hard breaks in the process analysis.

More specific comments:

L. 117-118: It needs to be clearly demonstrated how the proposed method is transferable to other monitoring platforms and different spatial scales.

Fig. 2: Please add a scale bar to the map so that the reader can assess the actual distances between the meteorological stations and the PLS site.

L. 177-178: Could you clarify the reasoning behind the assumption that smaller scale changes are not considered geomorphological changes?

L. 180: Regarding the choice of a one-week averaging window, please justify this specific timeframe and address whether there is a risk of smoothing out significant short-term signals.

L. 182: It would be helpful to know the magnitude of the data gaps encountered; please provide a summary or descriptive statistics for these gaps.

L. 187: Please provide specific numerical values to define what is considered too large in this context.

L. 188: How does the model account for geomorphic processes that do not return to the original elevation, such as permanent erosion or dune formation? It might be beneficial to mention this briefly here, even if the authors expanded upon this in the discussion, to resolve potential reader confusion early on.

L. 195: Please explicitly define the parameter used for the homogeneity criteria.

L. 200: Why was an area of 10 m² selected, and how does this specific size relate to the scale of the expected geomorphic processes?

L. 236-238: Would it be possible to consider filtering the 4D-OBCs individually, such as filtering the margins of an object rather than only using internal variability for noise identification and subsequent removal?

L. 259-260: Might a centroid be more suitable for the analysis.

L. 271-275: I am afraid that this paragraph is unclear to me; would it be possible to scale or normalize the volumeTS to improve interpretability?

L. 308: Please specify how the weight vectors are initialized, e.g., are they generated randomly?

L. 302: What specific metric is used for the maximum dissimilarity sampling? Is it, e.g., based on Euclidean distance.

L. 320: When you mention radius are you referring to sigma?

L. 335-336: Could you confirm if you are using average linkage for the clustering? If so, did you also consider the Ward linkage approach, which might provide more balanced clusters by accounting for cluster variance?

L. 351-357: I am afraid that this entire paragraph is difficult for me to follow.

L. 362: Why was only a single cluster selected for manual investigation, and what were the specific criteria used to choose this one?

L. 364: Please clarify what is meant by “relative frequency by season".

The authors present a study that performs unsupervised classifications of 4D objects-by-change (4D-OBCs) across a large dataset of over 20.000 hourly point clouds from PLS to identify short-term topographic changes at a beach. Specifically, Self-Organizing Maps (SOMs) and hierarchical clustering are employed to identify and group similar 4D-OBCs across space and time in a data-driven approach. Eight selected clusters are analyzed in depth and compared with environmental timeseries data to link the objects and clusters to physical processes to evaluate the presented workflow.

The approach is novel and innovative because it has the potential to enable the investigation of large 4D point clouds and higher-dimensional datasets through spatiotemporal object detection and classification without supervision for short-term coastal dynamics. The manuscript is well structured and well written, with clear visuals, and the presented results are of high quality. However, I am missing some information and rationales for technical aspects that were not presented (see comments below). Occasionally, a more critical discussion on how meaningful the clustering is, and how well it might generalize to other settings or data, could be included.

One beneficial addition would be the rationale for using Self-Organizing Maps (SOMs) and hierarchical clustering. While SOMs seem a natural choice given the spatial nature of the data, other options for dimensionality reduction exist. Even more alternatives for hierarchical clustering are conceivable (e.g., DBSCAN, DBCV, k-means); therefore, arguments for why the specific methods (and their specific settings/parameters) were chosen would strengthen the study.

Another aspect that could be strengthened is the confidence in the robustness and meaningfulness of the clustering in this study. A key element would be to add information on how interpretable the other clusters are, beyond the 8 analyzed clusters. This is also related to the previous point, because if some of the clusters are not really interpretable or well defined, improvements with different algorithms or parameters (or even feature engineering) might be possible. Therefore, the process of selecting and tuning these becomes more central. A way to allow for visual evaluation of the clustering could be i) adding a dimensionality reduced plot of the 4D-OBCs as a PCA and/or t-SNE; and ii) adding a dendrogram for the clusters. Such representations have been widely used in other fields (e.g., biology or biomedical research) for similar clustering approaches of high-dimensional data.

A more critical discussion of the role of algorithm choice and parametrization, as well as the inherent limits of clustering without external validation, could be added in section 5.4. Likewise, the limitations from the need for manual validation (and the resulting avenues for future studies) could be expanded (currently in lines 672-674).

For more specific, minor comments, please refer to the comments in the attached PDF.