Decision Support for Carbon Emission Reduction Strategies in China’s Cement Industry: Prediction and Identification of Influencing Factors
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThe article is well-structured, with a clear research design and thorough contextualization within existing literature. The results are clearly presented and supported by comprehensive references. The conclusions and policy recommendations are logically derived from the empirical findings. Areas for Improvement: Deeper Exploration of Regional Variations: The article provides a solid analysis of factors influencing cement consumption. However, it could benefit from a deeper exploration of regional variations. Including more detailed case studies or examples from specific provinces could provide richer insights and strengthen the overall analysis. Impact Assessment: Assessing the potential economic, social, and environmental impacts of the proposed policy recommendations would add depth to the analysis. Incorporating a cost-benefit analysis or scenario modeling could provide a more robust evaluation of the proposed strategies.
Comments on the Quality of English LanguageThe document generally employs clear and formal English. However, there are areas where the quality of the English language can be improved for better readability and professionalism. Observations:
1. Correct punctuation is essential for readability. Ensure proper use of commas, semicolons, and periods. For instance, "With the increase in urbanization rate, urban population continues to grow, urban scale expands, and the demand for urban infrastructure and public service facilities also increases" can be punctuated more clearly: "With the increase in the urbanization rate, the urban population continues to grow; the urban scale expands; and the demand for urban infrastructure and public service facilities also increases"​​.
2. Some sentences are long and complex. Breaking them into shorter, clearer sentences will improve understanding. For example, "This study aims to explore the prediction of cement consumption and its influencing factors across 31 provinces in China, thus providing support for addressing the carbon emissions challenge in the cement industry" can be revised to "This study explores the prediction of cement consumption and its influencing factors across 31 provinces in China. It aims to support efforts in addressing the carbon emissions challenge in the cement industry"​​.
Author Response
Please see the attachment
Author Response File: Author Response.docx
Reviewer 2 Report
Comments and Suggestions for AuthorsDear Editor,
The paper named “Decision support for carbon emission reduction strategies in China's cement industry: Prediction and identification of influencing factors using the RF-MLP-LR model” has been evaluated, and the suggestions are as follows:
The study investigates the prediction of cement consumption and its influencing factors across 31 provinces in China using a hybrid model combining Random Forest (RF), Multi-Layer Perceptron (MLP), and Logistic Regression (LR), referred to as the RF-MLP-LR model. The results indicate that this model excels in predicting cement consumption with high accuracy, achieving a Mean Absolute Percentage Error (MAPE) below 10% in most provinces. The RF-MLP-LR model outperforms traditional models such as RF, MLP, and LR, particularly in handling complex scenarios or specific regions. Thus, I recommend this manuscript for publication in Sustainability after the following minor revisions:
As a reviewer, I would provide the following comments:
1. The methodology section should detail the data sources, preprocessing steps, and the rationale for selecting the RF-MLP-LR model.
2. It would be beneficial to explain the integration process of RF, MLP, and LR models, including how they complement each other in terms of handling various complexities in the data.
3. The evaluation metrics, particularly MAPE, should be clearly defined, and the reasons for their selection should be provided.
Comments on the Quality of English Language
Moderate editing of English language required
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
Comments and Suggestions for AuthorsIn general, please correct all the citations in the text. The format is wrong and confusing.
Page 1, line 28: Correct the citation.
Page 1, line 33: Correct the citation.
Page 2, line 60: Correct the citation.
Page 2, line 63: Correct the citation.
Page 4, line 192. It is a paper, not a book. Please remove Chapter 2, etc.
Page 5, line 207. Change it to Step 1, data preparation:
Page 5, line 222. Step 4:
In general, the methodology section is confusing, with many details for each model. Please reduce the text and summarize it.
Page 6, line 255. The equation is incorrect. Yi-Yi.
Page 7, line 274. The equation is incorrect. Yi-Yi.
Page 12, line 362. The figure is unreadable.
Very poor results and a discussion section. Please elaborate more on the model(s) prediction and output.
Comments on the Quality of English LanguageAcceptable english.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Round 2
Reviewer 3 Report
Comments and Suggestions for AuthorsThe paper provides a predictive model utilizing ANN regarding cement consumption in China. The idea has solid foundations, but the results don't represent it well.
Page 1, line 28: [1, 2] not [1], [2]. Please correct the entire manuscript.
Page 14, line 432: Figure 5, those are the original data; why are they in the results section? Is it something that you calculated or acquired?
The conclusions are not convincing. In Figure 7, MAPE below 10% shows a very good model performance, but for several provinces, it is significantly higher. What influences the model for that specific province that cannot be predicted accurately?
In addition, it is mentioned that one reason is the sensitivity of the data. Could you please elaborate more on which specific data? Did you conduct a sensitivity analysis to observe which variables influence the predictability of the model the most?
Comments on the Quality of English Language
Sufficient English language.
Author Response
Please see the attachment
Author Response File: Author Response.docx