Development and Integration of Metocean Data Interoperability for Intelligent Operations and Automation Using Machine Learning: A Review

Round 1

Reviewer 1 Report

Dear Authors,

I found your article very interesting, and I would like to recommend its publishing after introducing small remarks:

1. The paper is very well edited, but please revise the style of citations inside the manuscript.

2. In my opinion the list of abbreviations should be placed in the beginning of the paper.

3. I would suggest to add additional graph regarding the data flow in the analysis of Metocean Data System.

After improving above described issues in the paper I’d like to give my positive opinion on signing my review report.

Author Response

Dear Reviewer,

Thank you very much for taking your valuable time to review our manuscript. Our responses are below and in the attached document.

Comment One:

The paper is very well edited, but please revise the style of citations inside the manuscript.

Response One:

Thank you. All style citations in the manuscript have been revised and modified based MDPI style guide.

Comment Two:

In my opinion the list of abbreviations should be placed in the beginning of the paper.

Response Two:

The list of abbreviations has been organized based on the MDPI style guide.

Comment Three:

I would suggest to add additional graph regarding the data flow in the analysis of Metocean Data System.

Response Three:

• An additional figure has been added “Figure 7. Metocean data condition flow information of numerical modeling approach between components” in subsection “7. Metocean Data System”
• The figure illustrates metocean data system information using data flow.

Reviewer 2 Report

There are some weaknesses through the manuscript which need improvement. Therefore, the submitted manuscript cannot be accepted for publication in this form, but it has a chance of acceptance after a major revision. My comments and suggestions are as follows:

1- Abstract gives information on the main feature of the performed study, but some details about the reviewed research works and the proposed system must be added (the first sentences can be removed).

2- Authors must clarify necessity of the performed research. Research questions, aims and objectives of the study must be clearly mentioned in introduction.

3- The literature study must be enriched. In this respect, authors must read and refer to the following papers: (a) https://doi.org/10.1016/j.jmrt.2021.07.004 (b) https://doi.org/10.1016/j.matpr.2021.12.101 and other research works.

4- It would be nice, if authors could add a figure showing the overall structure of the paper to enhance the readability of the paper. In addition, all images must be illustrated in a more scientific way with a high quality.

5- What is the strategy for selecting the reviewed literature? What are the keywords for searching? The review is not comprehensive.

6- Besides, without a methodology section to clarify the review process, the structure of the paper is confusing.

7- The main reference of each formula must be cited. Moreover, each parameters in equations must be introduced. Please double check this issue.

8- Differences of the proposed model with previous models available in literature must be discussed.

9- In its language layer, the manuscript should be considered for English language editing. There are sentences which have to be rewritten.

10- The conclusion must be more than just a summary of the manuscript. List of references must be updated based on the proposed papers. Please provide all changes by red color in the revised version.

11-Authors must clarify how the algorithms are developed. How its performance is evaluated.

12-How the current limitations can be solved? Authors must discuss it in details.

13-It is suggested to support discussion (section 8) with available and reviewed research works.

Author Response

Dear Reviewer,

Thank you very much for taking your valuable time to review our manuscript. Our responses are below and in the attached document.

Comment One:

Abstract gives information on the main feature of the performed study, but some details about the reviewed research works and the proposed system must be added (the first sentences can be removed).

Response One:

Thank you for the first sentence in the abstract has been removed.

Comment Two:

Authors must clarify necessity of the performed research. Research questions, aims and objectives of the study must be clearly mentioned in introduction.

Response Two:

• A new subsection has been added, “Research Questions” in Section 1.2.
• A new subsection has been added, “Research Objective” in Section 1.3.
• While the aims of research have already been mentioned in the third paragraph

“The main aim of this work is to a proposed methodological method for developing a new model and integrating it with the existing Metocean data system (SEAMOME) using a machine learning algorithm. The model will be able to monitor and interoperate with maximum performance. Metocean data from Carigali Sdn Bhd will be used as the training data for this research. Testing and evaluation of the algorithm will be conducted. It is expected that the findings will unlock the Metocean data system to deliver more valuable insights. It will integrate the Metocean data to enhance users' work with interactive analysis, visualization, and reporting for better efficiency and new Metocean data intelligence. Likewise, reducing the manual work maximizes the oil and gas data system and reduces operational overhead.”

Comment Three:

The literature study must be enriched. In this respect, authors must read and refer to the following papers: (a) https://doi.org/10.1016/j.jmrt.2021.07.004 (b) https://doi.org/10.1016/j.matpr.2021.12.101 and other research works.

Response Three:

• The papers have been read and referred.
• Table 1 has been modified using the referred papers.
• Also, a new paragraph has been added based on the referred papers.

“Although the application of ML technique has been utilized in a various domain which includes manufacturing sectors. Example Nasiri & Khosravani [35], investigate additive manufacturing (AM) parameters and prediction of mechanical behavior of 3D components using ML technique. Adding to this the authors focus on the prediction of ML applications for mechanical behavior. However, current challenges have been provided which include the lacking huge datasets from 3D printing can lead to low accuracy results. More recent evidence Verma & Verma [36], surveyed ML applications in the healthcare sector, where it plays a vital role in several areas such as healthcare data analytics and medical data protection. However, medical records and disease forecasts are been analyzed using ML applications. The authors also provide a research gab for efficient use of ML algorithms in the healthcare sector with an opportunities and challenges.”

Comment Four:

It would be nice, if authors could add a figure showing the overall structure of the paper to enhance the readability of the paper. In addition, all images must be illustrated in a more scientific way with a high quality.

Response Four:

• A new figure “Figure 2. Structure of the review study” has been added in Section 3.
• All image illustration has been modified and illustrated more scientifically.

Comment Five:

What is the strategy for selecting the reviewed literature? What are the keywords for searching? The review is not comprehensive.

Response Five:

• The strategy for selecting the reviewed literature is based on the research question and the review study method.
• Also, the keywords search has been provided in “Figure 1 Flowchart for data collection process”

Comment Six:

Besides, without a methodology section to clarify the review process, the structure of the paper is confusing.

Response Six:

• A new section titled “Review Methodology” has been added.
• Also, a new figure “Figure 2. Structure of the review study” has been added.

Comment Seven:

The main reference of each formula must be cited. Moreover, each parameters in equations must be introduced. Please double check this issue.

Response Seven:

• Equations and each parameter were amended accordingly.

Comment Eight:

Differences of the proposed model with previous models available in literature must be discussed.

Response Eight:

The proposed model together with the previous related works have been updated.

Comment Nine:

• In its language layer, the manuscript should be considered for English language editing. There are sentences which have to be rewritten.

Response Nine:

English proofreading has been conducted (Please, see the number the attachment).

Comment Ten:

The conclusion must be more than just a summary of the manuscript. List of references must be updated based on the proposed papers. Please provide all changes by red color in the revised version.

Response Ten:

• The conclusion section has been modified.
• The list of references has been carefully revised and modified.
• All revised versions can be viewed through track changes however, we have enabled the track changes so that all changes can be visible.  

Comment Eleven:

Authors must clarify how the algorithms are developed. How its performance is evaluated.

Response Eleven:

Expatiated the discussion on algorithms.

Comment Twelve:

How the current limitations can be solved? Authors must discuss it in details.

Response: Twelve:

• How the current limitation can be solved has been disused in “10. Limitation of the Study”
• Also, a new paragraph has been added.

“The current limitation can be overcome through implementing additional AI models based on DL algorithms such as CCN, RNN, GAN, and BDN to investigate metocean data conditions. The proposed techniques/models can also be improved through hyperparameter turning or feature selection techniques. Adding to this, data quality assurance has to be considered in selecting datasets. However, relevant related studies before 2019 can be referred to, and also other database sources can be explored.”

Comment Thirteen:

It is suggested to support discussion (section 8) with available and reviewed research works.

Response Thirteen:

The section “9. Discussion” has been enhanced with more research works.  

Reviewer 3 Report

In the present paper, the authors are presenting a review study related to the development and integration of metocean data interoperability for intelligent operations and automation using Machine Learning (ML) tools. The authors are providing a reasonable number of papers related to the topic. The authors should revise their paper in order the paper to be accepted for publication. Below are suggestions to the authors.
-English language is not good. A professional individual should help the authors. Several grammatical and editorial errors exist in many places within the paper. The paper cannot be accepted for publication in its current state.
-The last paragraph of the Introduction, apart from the fact that exhibits bad English language, it needs to be revised so the authors can demonstrate what is new with their review paper and in which areas it contributes additional information to the existing one.
-In section 5, it would be nice if the authors added more figures of web application for operational decision.
-Section 6 is quite small and incomplete. The authors should provide larger amount of published work for Malaysia and worldwide.
-Section 7 is the most critical part of the paper; however, it is small in comparison to the rest of the paper. The authors should provide more published work related to ML.

Author Response

Dear Reviewer;

Thank you very much for taking your valuable time to review our manuscript. Our responses are below and in the attached document.

Comment One:

English language is not good. A professional individual should help the authors. Several grammatical and editorial errors exist in many places within the paper. The paper cannot be accepted for publication in its current state.

Response One:

English proofreading has been conducted by a professional expert.

Comment Two:

The last paragraph of the Introduction, apart from the fact that exhibits bad English language, it needs to be revised so the authors can demonstrate what is new with their review paper and in which areas it contributes additional information to the existing one.

Response Two:

The authors have fixed the issue of the last 2 paragraphs in the Introduction Section.

Comment Three:

In section 5, it would be nice if the authors added more figures on web applications for operational decisions.

Response Three:

A new figure has been in “Figure 5. Data communication, flow between field device, cloud server and customer [71]” which shows the data communication and data for analytics.

Comment Four:

Section 6 is quite small and incomplete. The authors should provide a larger amount of published work for Malaysia and worldwide.

Response Four:

• The section has been modified by adding a new paragraph in subsection “7.1 Metocean Data System in Malaysia”
• Also, studies from Malaysia have been added and other countries which as the U.S.

Comment Five:                  

Section 7 is the most critical part of the paper; however, it is small in comparison to the rest of the paper. The authors should provide more published work related to ML.

Response Five:

• The section “8. Machine Learning for Metocean Data Integration” has been enhanced by adding more relevant published work related to ML.

Reviewer 4 Report

I have reviewed an article title as Development and Integration of Metocean Data Interoperability for Intelligent Operations and Automation using Machine Learning: A Review. The manuscript is well written and falls within the scope of Applied Sciences. Below are few minor comments

1. Remove Figure 1 with higher resolution figure.
2. Discuss ML algorithms with mathematical equations in section 3
3. Replace Figure 3 with more meaningful figure
4. Add more examples of semi supervised learning and reinforced learning in oil and gas industry
5. Enhance machine learning literature review by citing the following papers
1. Artificial Intelligence-Based Model of Mineralogical Brittleness Index Based on Rock Elemental Compositions
2. A systematic review of data science and machine learning applications to the oil and gas industry)
3. Data-Driven Acid Fracture Conductivity Correlations Honoring Different Mineralogy and Etching Patterns
4. The Potential of Machine Learning for Enhancing CO2 Sequestration, Storage, Transportation, and Utilization-based Processes: A Brief Perspective

      6. Add some insights about the following issues with ML

1. 1. How can the machine learning models be generalized, needs some comments on this perspective.
   2. How normalization and standardization are playing important role in machine learning modeling
   3. Explain about feature engineering? How feature engineering can improve the prediction
   4. Data quality assurance

        7.Conclusion needs to be revisit, what’s the new model ?

Author Response

Dear Reviewer,

Thank you very much for taking your valuable time to review our manuscript. Our responses are below and in the attached document.

Comment One:

Remove Figure 1 with higher resolution figure.

Response One:

Thank you. Figure 1 “Figure 1. Metocean forecast data loading along route position time from correlate map with data vectors showing selected point.” has been removed.

Comment Two:

Discuss ML algorithms with mathematical equations in section 3

Response Two:

• The section “section 4. Dimensions of Machine Learning Algorithms” has been modified.
• Also, a paragraph has been added which discusses ML with its mathematical equations.

Comment Three:

Replace Figure 3 with more meaningful figure

Response Three:

• The previous “figure 3. Visualization based on management web application for operational decision” has been replaced with a meaningful figure.
• The updated figure is “Figure 6. Gas production profiling using DTS data”

Comment Four:

Add more examples of semi supervised learning and reinforced learning in oil and gas industry

Response Four:

• An additional example of semi-supervised learning in the oil and gas industry has been added in subsection “4.3 Semi-supervised Learning”.
• An additional example of reinforced learning in the oil and gas industry has been added in subsection “4.4 Reinforcement Learning”.

Comment Five:

Enhance machine learning literature review by citing the following papers

1. Artificial Intelligence-Based Model of Mineralogical Brittleness Index Based on Rock Elemental Compositions
2. A systematic review of data science and machine learning applications to the oil and gas industry)
3. Data-Driven Acid Fracture Conductivity Correlations Honoring Different Mineralogy and Etching Patterns
4. The Potential of Machine Learning for Enhancing CO2 Sequestration, Storage, Transportation, and Utilization-based Processes: A Brief Perspective

Response Five:

• All papers have been refereed.
• Also, a new paragraph has been added in “2. Metasurvey” to enhance the ML literature review.

Comment Six:

Add some insights about the following issues with ML

1. How can the machine learning models be generalized, needs some comments on this perspective.
2. How normalization and standardization are playing important role in machine learning modeling
3. Explain about feature engineering? How feature engineering can improve the prediction
4. Data quality assurance

Response Six:

• Some insight has been added in “4. Dimensions of Machine Learning Algorithms”
• Also, a new paragraph has been added.

“Interestingly, ML can be generalized through training, and demonstration of models for data classification. Also, normalization and standardization play an important role in ML modeling by rescaling values and data. Moreover, feature engineering improves Ml prediction or unseen data after transforming raw data into features. However, to archive efficient integrity results data quality assurance has to be considered. Figure 4 illustrates the categories of ML.”

Comment Seven:

Conclusion needs to be revisited, what’s the new model?

Response Seven:

The conclusion has been updated accordingly.

Round 2

Reviewer 3 Report

The authors successfully addressed all my comments. The paper can be accepted for publication.

Reviewer 4 Report

No further comments