Evaluation of Synthetic-Temporal Imagery as an Environmental Covariate for Digital Soil Mapping: A Case Study in Soils under Tropical Pastures

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

In this study, the authors tried to map regional soil properties based on multiple environmental covariates. The manuscript is interesting, and contains description of new approach of analysis of soil contamination assessment. However, there are some issues that need to be resolved before this manuscript can be considered for publication. My recommendation is MAJOR revision.
General comments:

1.       As resources is an international journal, it seems to be better to give soil names in accordance with international soil classification (WRB).

2.       Abstract should be modified after whole revising, as a shorter one, and should be clear to appear understandable overall contents (i.e. including objective, method, result, discussion, conclusion), but not too long. Currently, there are too many confused expressions here.

3.       The language needs to be edited by native speakers. The use of language should be carefully checked. There are many unnecessary descriptions. There are more deficiencies in language use. English polishing is must.

4.       In general, the logics among all sections are poor. Therefore, I can hardly get your objectives in this review.

 

Specific comments:

1.       The introduction needs to be expanded.

2.       Please provide a bit more big-picture motivation of how your analyses benefit society and how they have evolved over the past decade. However, from my point of view, the article does not provide a sufficiently thorough review of the issue under study. There are good references for the study techniques, but the paper is missing a "big-picture" introduction with some references in my opinion. I suggest that the authors should do a better analysis of the literature. It seems that the bulk of the text is a sort of compilation of statements in the individual articles cited. It would be better, I think, to extract ideas from individual articles and tie them together into a more fluid and conceptually homogeneous text. As it is, the text looks rather clumsy.

3.       Research gaps, objectives of the proposed work should be clearly justified before the problem formulation section. This paper includes some little useful information and the main objectives of the study is not well defined. Problem statement is not clear and the objectives are obscure. Furthermore, the paper lacks a very clear and good justification for what is new and innovative about this case or this approach.

4.       For DSM, some recent articles available for similar studies can be read.
a) Assessing toxic metal chromium in the soil in coal mining areas via proximal sensing: Prerequisites for land rehabilitation and sustainable development. Geoderma, 2022, 405, 115399.
b) Remote sensing of soil degradation: Progress and perspective. International Soil and Water Conservation Research.2023, 11(3), 429-454.
c) Updated soil salinity with fine spatial resolution and high accuracy: The synergy of Sentinel-2 MSI, environmental covariates and hybrid machine learning approaches. CATENA, 2022, 212: 106054.

5.       L146 The basic introduction of machine learning technology (RF) in soil science is necessary. Moreover, each symbol in your expressions should be illustrated clearly.

6.       L95  Why 104 ?

 

 

Comments on the Quality of English Language

moderate

Author Response

Thank you for reviewing the manuscript. The detailed responses and revisions/corrections are in the re-submitted file.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The research subject is quite important as digital soil mapping methods are gaining importance due to practical limitations associated with traditional soil survey and soil mapping techniques.

The paper relates environmental covariates derived from land surface phenological metrics derived from NDVI time series and rainfall patterns with soil properties. The study covers a geography of 314 ha divided in to grids of 130m. Landsat NDVI time series were subjected to smoothening algorithm to generate phenological metrics. The prediction model is Random Forest algorithm and the explaining power of variables was analysed through correlation methods.

 

While the authors have carried out the study  in a systematic manner, the uniqueness of this study compared to many other such studies reported in the past is not brought out. Therefore, this study becomes yet another case study in digital soil mapping methods.

 

NDVI based phenology and rainfall patterns will represent the soil properties to certain extent only and hence the unexplained variability in the model needs to be highlighted in the report.

 

Median accuracy and kappa accuracy were reported to be 61.1% and 0.43 respectively for the pooled datasets. Accuracies were found to be higher for the dominant soil classes.  That means the proposed model works for certain soil groups only. Can this be clarified?

 

How are the accuracies varying across the selected themes i.e., pasture, native forest, forest plantation?

 

It is advisable to evaluate the results over each of the above themes.

The study was carried-out over a smaller geography and the possible sources of uncertainties when it is extended to larger areas need to be highlighted.

 

Model uncertainties and error propagation details of the entire methodology need to be explicitly discussed.

 

Comments on the Quality of English Language

Minor improvements are needed to improve the content and its readability

Author Response

Thank you for reviewing the manuscript. The detailed responses and revisions/corrections are in the re-submitted file.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

none

Comments on the Quality of English Language

none