A Machine-Learning Approach to Intertidal Mudflat Mapping Combining Multispectral Reflectance and Geomorphology from UAV-Based Monitoring

Round 1

Reviewer 1 Report

Review of remotesensing-1964897 “A machine learning approach to intertidal mudflat mapping combining multispectral reflectance and geomorphology from UAV-based monitoring”

General comment:

Very interesting paper. The hypotheses, methodology, results, discussion and conclusion are well presented. The manuscript needs some minor changes before being published. Details are listed below:

Abstract

Line 17: "difficult to access", please replace with another word or add hyphen

Introduction

Lines 37-43: the message is confused. Please re-ordered and rephrased the paragraph. Line 72: please, replace with “have rich ecosystems”

Line 63: "detecting" carbon uptake?

Lines 81-83: ...geomorphic unit by geomorphic unit. please re-phrase the sentence.

Materials and Methods

table 2: it seems to be incomplete. please check the size and elements presented.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Thank you for the opportunity to review this manuscript. Overall, it is a very good application that is well-conducted and advances the field. I only have a few minor comments:

-Lines 227-228: It is unclear what the main ground elevation reference is. How was it set? Please add some clarifications.

-Lines 332-333: The kappa coefficient is more robust than the overall accuracy as it accounts for random chance in the accuracy assessment, unlike the overall accuracy. The kappa coefficients must be put forward whenever possible.

-Line 509: overall, not global.

-Lines 621-622, and 678: Add the kappa values of the two classifications to enable a direct comparison.

-I would recommend adding one map showing the pixel-by-pixel differences between the two classifications. The results would be a binary agreement/disagreement map that would put the differences into a spatial context.

-The English language requires some review, especially in the abstract and the introduction, but also elsewhere.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

The authors submitted a well written and an interesting manuscript dealing with intertidal mudflat mapping using UAV photogrammetry-based approach. The methodology is well described and the conclusions are supported by the results. However, the authors should improve the manuscript before it could be considered for publication. Below are some comments and suggestions to improve the overall quality of the manuscript:

Line 1: Please specify the type of the manuscript. I think you can indicate it as an article.

Lines 5-6: Please adopt the instructions provided in the template of the Journal.

Lines 64-67: Please provide some references. Please refer to (1)  Harishidayat, D.; Al-Shuhail, A.; Randazzo, G.; Lanza, S.; Muzirafuti, A. Reconstruction of Land and Marine Features by Seismic and Surface Geomorphology Techniques. Appl. Sci. 2022, 12, 9611. https://doi.org/10.3390/app12199611. (2) Gkiatas, G.T.; Koutalakis, P.D.; Kasapidis, I.K.; Iakovoglou, V.; Zaimes, G.N. Monitoring and Quantifying the Fluvio-Geomorphological Changes in a Torrent Channel Using Images from Unmanned Aerial Vehicles. Hydrology 2022, 9, 184. https://doi.org/10.3390/hydrology9100184. For Unmanned Aerial Vehicle (UAV)-based image acquisition for geomorphological mapping.

Lines 73-76: The authors could provide a short review of recent studies which delt with the confusion between MPB and oysters or rocks covered by epibionts that share similar spectral signature and indicate the contribution of this manuscript compared to the past studies.

Lines 75-76: in the Table 1, please add “parameter” as the header for the descriptions of UAV, cameras and Flight plan settings.

Lines 295-297: Please provide equations for these different indexes: NDVI, GNDVI, and NDWI.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf