A Practical Method for the Automatic Recognition of Rock Structures in Panoramic Borehole Image during Deep-Hole Drilling Engineering

Round 1

Reviewer 1 Report

The manuscript presents research related to the application of artificial intelligence techniques for image recognition with application in drilling. The presented method mixes time and materials, resources and drilling, which is very important in the implementation of infrastructure projects. The authors have verified their method in solving a real practical problem at Wudongde Hydropower Station in the south-west of China.

I have no significant remarks, but the authors should carefully review the formatting and layout of the manuscript. The presented figures are also not of good quality and no uniform font is used when writing them.

Author Response

Thanks for your kind suggestion. We have reviewed and revised the formatting and layout of the manuscript based on the download Word Template. The figures and their font are changed accordingly. We appreciate your kind work very much. Once again, thank you very much for your recommendations.

Reviewer 2 Report

The authors introduce  an automatic recognition method that exploits a clustering mechanism and the characteristic functions in order to intelligently analyze and automatically interpretate researches dealing with the analysis of the borehole images obtained at the Wudonge hydropower station in the southwest of China.

 

The theoretical analysis presented in the paper is detailed and the authors have provided all the intermediate derivations in order to enable the reader to easily follow it. The structure of the paper is good and the authors have elaborated over all the details that are necessary for the reader in order to follow the paper.

 

Furthermore, the authors have presented some indicative results in order to show the pure operation and the performance of the proposed framework. The authors should consider the following suggestions provided by the reviewer in order to improve the scientific depth of their manuscript, as well as they should address the following comments in order to improve the quality of presentation of their manuscript.

 

Initially, in Section 1, the authors should discuss machine learning approaches that have been introduced in the literature, such as Huang, Xin-Lin, Xiaomin Ma, and Fei Hu. "Machine learning and intelligent communications." Mobile Networks and Applications 23.1 (2018): 68-70, in order to deal with similar clustering mechanisms.

 

 Additionally, the authors should discuss content based and collaborative based mechanisms, such as Stai, E., et al. "A holistic approach for personalization, relevance feedback & recommendation in enriched multimedia content." Multimedia Tools and Applications 77.1 (2018): 283-326, Thai, My T., Weili Wu, and Hui Xiong, eds. Big data in complex and social networks. CRC Press, 2016 that have been introduced in the literature in order to perform the automatic recognition of images from big datasets.

 

Furthermore, the authors should include an additional subsection in their manuscript discussing the computational complexity and providing the corresponding theoretical analysis, as well as the implementation cost in order the proposed framework to be implemented in a realistic set up supporting real life applications.

 

Based on the previous comment, the authors should provide some indicative numerical results quantifying the computational complexity of the proposed framework in a realistic setup and discussing its real time or even close to real time implementation.

 

Finally, the overall manuscript should be checked for typos, syntax, and grammar errors in order to improve the quality of its presentation.

 

Author Response

First of all, we appreciate your kind work and thanks for your recommendations very much about “The structure of the paper is good and the authors have elaborated over all the details that are necessary for the reader in order to follow the paper.” We totally accept your advice and revised the points as follow:

(1) We have introduced the machine learning approaches about the clustering mechanisms in Section 1, and referenced this paper. (Huang, X.-L.; Ma, X.; Hu, F. Editorial: Machine Learning and Intelligent Communications. Mobile Networks and Applications 2018, 23, 68-70, doi:10.1007/s11036-017-0962-2.).

(2) We have revised the part about the automatic recognition process and discussed some contents based on the mechanisms. We referenced them. (Thai; T., M.; Wu, W.; Hui, X. Big Data in Complex and Social Networks; Chapman and Hall/CRC Press: 2016; https://doi.org/10.1201/9781315396705. Stai, E.; Kafetzoglou, S.; Tsiropoulou, E.E.; Papavassiliou, S. A holistic approach for personalization, relevance feedback & recommendation in enriched multimedia content. Multimedia Tools and Applications 2018, 77, 283-326, doi:10.1007/s11042-016-4209-1).

(3) Thanks for your kind suggestion. The theoretical mechanism of the automatic recognition method based on clustering and characteristic functions has introduced in the revision. The computational complexity of this method can be reflected in Table 3. As the limit of content and time, we cannot discuss too much as an additional subsection and it is hard to verify them under ideal conditions if we used them during the actual complex applications. We hope you can understand it and thanks again.

(4) Because of the same reason, some indicative numerical results about the computational complexity of the method cannot be provided this time. The aim of this manuscript is to provide a practical method which can be applied in complex drilling engineering, in order to improve the work efficiency and reduce engineering time cost for front-line scientific researchers when faced with hundreds or thousands of borehole data. The real time implementation and some others can be reflected in Section 4 and Table 3. Thanks for your hard work and kind comments.

(5) We have revised and proofreading the whole manuscript in order to ensure the high quality. The typos, syntax, and grammar errors may have been rechecked and revised accordingly.  Thanks for your kind suggestion very much.

All in all, we have revised and proofreading the whole manuscript in order to meet the high quality of the publication. We appreciate your kind work very much. Once again, thank you very much for your recommendations.

Reviewer 3 Report

The authors presented a method of automatic recognition of rock structures on a panoramic image of a borehole during deep hole drilling engineering. The proposed method is of practical importance, it will significantly improve labor productivity, accelerating technical progress and saving manpower and material resources. The article is well structured.

My comments are as follows:

- in the part describing the characteristics of the hydroelectric power plant, there is no information about the year of its construction and the nature of the power plant operation. For readers outside of China, the location of this plant is needed. It is worth inserting a map with the location of this power plant.

- the paper lacks a diagram of a hydroelectric power plant with marked places of sampling and measurements.

- a methodological scheme for automatic recognition of rock structures is needed.

- repetition of information: caption under Figure 2 and description on pages 138-140

Technical Notes:

- line 432 is '151-159' and it should be '151-159'

- line 439 '685-693' and it should be 685-693 '

- line 469 is '867-876' and it should be '867-876'

- line 483 is '2199-2209' and it should be '2199-2209'

- line 489 is '17-29; and there should be '17-29 ' Line 496 '381-389' '381-389'

- line 506 is '96-100 'and it should be '96-100' and many others ….

Author Response

Thanks for your kind comments very much. Your comments are very valuable and helpful for the improvement of our manuscript. Here below are our responses to your comments.

(1) The location of this plant can be searched online by using Google earth. It is worth inserting a map with the location of this power plant. However, we think more detail information about this plant cannot be provided because of some sensitive information related to national major project. We are sorry for that (Specific key information) and hope you can understand that. Thanks again.

(2) We added a diagram of a hydroelectric power plant with marked places of sampling and measurements in the revision. Thank you.

(3) Thanks for your kind comments. A methodological scheme shown as in Figure 4 for automatic recognition of rock structures is added accordingly.

(4) The repetition of information of caption under Figure 2 and description on pages 138-140 is deleted and revised accordingly.

(5) Some pages errors about the Technical Notes in Reference are revised and we updated the whole reference part. Thanks for your kind comments.

Lastly, we hope these responses and revision will make this manuscript more acceptable for publication. Once again, Thanks for your kind comments.

Round 2

Reviewer 2 Report

The authors have addressed the reviewers' comments. The quality of presentation of the manuscript, as well as its scientific depth have been substantially improved.