Optimization of Aggregate Characteristic Parameters for Asphalt Binder—Aggregate System under Moisture Susceptibility Condition Based on Random Forest Analysis Model

Round 1

Reviewer 1 Report

Overall, the idea of the paper is good, i had some issues with english and grammar such as unfinished sentences. Also the background of the paper should be supported better with recent references.  Methodology is sound and appropriate for this study. 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

This paper uses a random forest to maximize the screening of aggregate characteristic factors. In the current form, the discussion part of the article must be improved. In my opinion, the authors should discuss and try to verify their results with those of published studies. The article also needs extensive editing of English language and style required. My opinion is major revision. Moreover, My comments and questions are as follows:

The research gap and novelty of the article is not well-written.

I suggest that “the importance analysis” be replaced with “sensitivity analysis” throughout the article.

Please remove the following sentence in lines 31 and 32:  “(List three to ten pertinent keywords specific to the article yet reasonably common within the subject discipline.)” in lines 31 and 32

Please remove the unnecessary spaces in line 41 in citing references.

Replace brought on in line 42.

I suggest that Line 91 be revised: “more and more scholars are”

Replace “it was possible” to it is possible in line 93.

The paragraph in lines 95 to Line 102 must be revised and written more carefully.

Lines 184 and 185 must be revised.

Sentence in line 193 is not clear and must be revised.

Figure 8 seems redundant an can be removed as it does add any value.

The authors should provide a more details discussion of figure 9.

Revise “abundantly evident” in line 311

The sentence written in Lines 323-325 must be re-written.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

The following are comments that require clarification:

1.       Table 1 presents the results of testing the asphalt binder. No description of test methods (standards).

2.       Table 2 presents the results of aggregate tests. No description of test methods (standards).

3.       The word "gum" appears on line 55 and line 60. It should be replaced by the word "resin".

4.       Formula (8) describes the method of determining r_ij when x_ij is a negative index. This applies, for example, to the Wb index. In equation (8), x_imax is described as the maximum value of the index j. What is the maximum (theoretical) value for the index Wb (without washing)? What will be the value of r_ij?

5.       Lines 218-220: "Interventionary studies involving animals or humans, and other studies that require ethical approval, must list the authority that provided approval and the corresponding ethical approval code." What is the purpose of this statement?

6.       Figure 7 shows the mineral phase content of different aggregates. For better visualization, the same mineral (e.g. quartz) should be marked with the same color for all aggregates.

7.       When describing the aggregates, it was found that there are two types of limestone A and B. Figure 7 shows that limestone A and B consists mainly of dolomite (over 70%). So is this aggregate limestone or dolomite?

8.       The method of determining the SiO2 content on the basis of combined XRF and XRD tests requires clarification (line: 287-294).

9.       The peeling rate (Wb) values in Fig. 9 are in %. It does not result from formula (1) - index value without units.

10.   The “Immersion Marshall test” and “Freeze-thaw splitting test” were carried out on mixes with the specified type of aggregate. Did these mixes consist 100% of this particular type of aggregate (respectively: limestone A and B, granite, diabase, basalt). Does this also apply to the dust fraction (<0.063 mm)? What was the void content in the tested samples?

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 4 Report

Dear authors,

I have read this interesting paper which follows the actual trend using for various tasks ML. Studiyng and predicting moisture susceptibility nad adhesion belongs definitely to the problems where ML shall have a good use and impct. The paper was interesting to read and random forrest as one of many technigues available seems to me appropriate for the described case and predictive modeling. I found only few parts in the manuscript where some clarification or explanation is need. Please, see the attached file. Furthermore, I was thinking about the parameters selected as inputs. For aggregates, would surface energy be not additional aspect to be considered. Surface morfology is included, does it somehow consider also porosity of the aggregates since also this might be important when bitumen film is formed. In case of the bitumen maybe FTIR or SARA would provide additional input information since the chemical characteristics might be most probably more important that only knowledge of penetration or softening point. Have some of these aspects been considered as well?

 

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

The authors have considered my comments and the quality of article is improved.In my opinion,  article can be accepted.

Reviewer 4 Report

Dear authors, I have read the revised version and the response you provided. Many thanks. Now everything is clear to me and I have no further questions or comments.