Landslide Displacement Prediction Using Kernel Extreme Learning Machine with Harris Hawk Optimization Based on Variational Mode Decomposition

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This study focuses on constructing a Landslide Displacement Prediction model in China. I found this manuscript interesting; however, some sections need improvement. I want the authors to address the following points to enhance the manuscript:

1.     Keywords: I suggest changing the keywords that appear both in the title and in the keyword section. This change will improve the paper's visibility in bibliographic repositories by introducing a greater variety of terms.

2.     Introduction: The aim of the study is missing.

o   The authors briefly mention China, but the context of landslides in the country is not well described, nor are previous studies on this topic.

o   The authors mention the results at the end of the section, but the introduction is not an abstract. You should focus on the study's aim, justification, the research gap, and the methods.

3.     Section 3.1: I suggest including a location map and the environmental context of the study area (e.g., climate, geomorphology, etc.).

4.     Discussion: This section is poorly developed and needs to be rewritten. It reads more like a conclusion than a discussion, and it lacks comparisons with other studies.

5.     Conclusion: What are the challenges of the study? What are the future steps? Will this new approach be implemented elsewhere?

 

 

Author Response

Dear Editors and Reviewers,

We sincerely thank the Editors and the Reviewers for your careful and timely review and valuable comments on our manuscript (Manuscript ID: land-3226200). These comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We carefully considered and revised the article based on the opinions of reviewers. The revised manuscript of the paper has been revised in review mode and the important revisions are marked in red. The main corrections in the paper and the responds to the reviewer’s comments are as following:

 

Comments 1. Keywords: I suggest changing the keywords that appear both in the title and in the keyword section. This change will improve the paper's visibility in bibliographic repositories by introducing a greater variety of terms.

Response 1: Thank you for your suggestion. We have adjusted the keywords to improve the visibility of the paper in bibliographic repositories. The revised keywords are: Displacement Prediction; Kernel Extreme Learning Machine; Variational Mode Decomposition; Three Gorges Reservoir Area; Influencing Factors

 

Comments 2. Introduction: The aim of the study is missing.

Response 2：We sincerely appreciate the valuable comments. We added the aim of the study in the introduction of the revised manuscript.

 

Comments 2.1 The authors briefly mention China, but the context of landslides in the country is not well described, nor are previous studies on this topic.

Response 2.1: Thank you very much for your suggestions on revisions. In the introduction, the context of landslides in the Three Gorges Reservoir Area of China has been described and supplemented. Modified as follows: In the Three Gorges Reservoir Area of China, thousands of landslides are influenced by substantial mass movements due to the complex geological environment, posing a severe threat to the surrounding environment. A typical example is the Qianjiangping landslide that occurred in July 2003, causing serious casualties within a few days after the reservoir reached an elevation of 135 m. Thus, landslide displacement prediction is crucial in landslide disaster research, as an accurate displacement prediction model can reduce disaster loss and risk[6-9]. Quaternary sediments are widely distributed in the TGRA. The most significant features are loose compositions, distinct viscoelastic deformation, and high porosity, making them highly susceptible to water infiltration. Long-term studies have demonstrated that landslide deformation in the TGRA are caused by slow gravitational downslope processes that occur before the failure of the slope[10, 11]. Reservoir water level and precipitation are considered the most important triggers for landslides among these factors.

 

Comments 2.2 The authors mention the results at the end of the section, but the introduction is not an abstract. You should focus on the study's aim, justification, the research gap, and the methods.

Response 2.2: We think this is an excellent suggestion. We have revised the end of the introduction and emphasized the purpose, justification, and methodology of the study. The specific revisions are as follows: The purpose of this study is to propose a novel landslide displacement prediction model of VMD-HHO-KELM that considers the external influences on displacement deformation. VMD decomposes the cumulative displacement of landslides into a trend, periodic, and random terms. Then, the external influencing factors are decomposed into two sub-sequences, characterized by periodicity and stochasticity, and fused into the training set as input data. Taking a typical landslide of Shuizhuyuan in the TGRA as an example, three components are predicted separately using the HHO-KELM model and the predicted total displacement is the sum of the three components. To validate the practicality and effectiveness of the HHO-KELM model, performance comparisons are conducted with methods such as ELM, KELM, and PSO-KELM.

 

Comments 3. Section 3.1: I suggest including a location map and the environmental context of the study area (e.g., climate, geomorphology, etc.).

Response 3: Thanks to the reviewer for the suggestion. The location map and geological context of the study area are supplemented and improved in Section 3.1. Modified as follows: The study area has typical characteristics of a subtropical humid monsoon climate. The surface materials of the Shuizhuyuan landslide are loose gravelly soil with good permeability. The underlying bedrock mainly consists of mudstone and marlstone. The sliding surface has a depth of approximately 30 m. The front edge of the landslide is below the water level of the Yangtze River at 145 m, and the stability of the landslide is significantly affected by the reservoir water level (Figure 5).

 

Comments 4. Discussion: This section is poorly developed and needs to be rewritten. It reads more like a conclusion than a discussion, and it lacks comparisons with other studies.

Response 4: Thanks to the reviewer for the suggestion. We have rewritten the discussion section. Modified as follows:

The deformation characteristics of landslides in the TGRA are closely related to various factors, mainly including their own geological structure, precipitation, and reservoir water level adjustments. Through an in-depth analysis of displacement characteristics and deformation mechanisms, it was demonstrated that precipitation during the flood season and fluctuations in water level are the main influencing factors for the Shuizhuyuan landslide. Under the dual influence of these factors, the landslide shows a displacement deformation curve akin to a step-like pattern. Therefore, the prerequisite for conducting landslide displacement prediction is the accurate decomposition.

Traditional methods such as EMD and EEMD have no regularity in the feature components of displacement decomposition. After decomposition, each component requires observation and analysis, followed by recombination to obtain the desired characteristic components. Recombination of these components often increases the duration of data analysis and reduces data processing efficiency. In this study, VMD can adaptively decompose the landslide displacement into characteristic components based on a predetermined number of modes. For instance, when K=3, it can effectively extract trend, periodic, and random displacement components, each with a clear physical meaning. This can effectively suppress the issues of incomplete data decomposition and irregular decomposition patterns that are common in traditional methods.

Comparing models helps to validate the accuracy of the proposed method[25]. ELM is a typical representative machine learning method used for displacement prediction. Therefore, this study used ELM, KELM, and PSO-KELM models to verify the predictive performance of HHO-KELM[4, 25]. As shown in Figure 15 and Table 3, the RMSE and R² of ELM are 1.6995 and 0.9559, respectively, indicating that ELM has the worst predictive ability. After incorporating the kernel function into the ELM, the RMSE and R² of the KELM are 1.0338 and 0.9837, which represents a certain improvement in the displacement prediction capability. To further improve the training efficiency of KELM, optimization algorithms are introduced to optimize the parameters of KELM. The results indicate that the RMSE and R² of the HHO-KELM model are 0.3680 and 0.9979, respectively, providing the best predictive outcomes among the models tested. This is mainly attributed to the global search and adaptive parameter adjustment capabilities of the HHO algorithm. Figure 15 highlights that HHO-KELM, which considers external influencing factors, achieves better landslide displacement prediction and has a very accurate displacement prediction ability, proving that the step-like displacement is affected by precipitation and reservoir water level fluctuation.

In addition, the rapid development of Deep Learning techniques such as Multi-layer Perceptron (MLP) and Transformer provides feasible solutions for long-term series prediction. In future research, the generalization and computational capabilities of Deep Learning will provide more reference options for predicting the displacement of different types of landslides.

 

Comments 5. Conclusion: What are the challenges of the study? What are the future steps? Will this new approach be implemented elsewhere?

Response 5: We sincerely appreciate the valuable comments. We have adjusted and optimized the content of the conclusion. The revised manuscript supplements the issues that this study will face, as well as future research plans and implementation steps, and concludes with the expected scope of application for the new method. Modified as follows: Although the proposed HHO-KELM has achieved better displacement prediction results than other methods, factors such as extreme rainfall conditions and sudden drops in reservoir water level have not been fully considered, which can have a significant impact on displacement prediction performance. Considering the limitations of existing landslide monitoring data, it is insufficient to only consider the effects of precipitation and water level on displacement. More monitoring information needs to be incorporated into the model to enhance predictive capabilities. The displacement deformation of landslides varies over time, and it is important to continuously update monitoring data within the model to gradually replace existing monitoring data to enhance the accuracy of model predictions.

Overall, accurate and reliable displacement prediction can be realized at the stage of slow deformation and step-like landslide deformation by combining the background of landslide breeding and dynamic evolution theory through machine learning technology. The proposed method can be popularized and applied in the TGRA and other landslide-prone areas with step-like displacement.

 

We tried our best to improve the manuscript and made some changes in the manuscript. These changes will not influence the content and framework of the paper.

 

We appreciate for Editors/Reviewers’ warm work earnestly, and hope that the correction will meet with approval.

 

Once again, thank you very much for your comments and suggestions.

 

Best regards,

 

Chenhui Wang

E-mail: wangchenhui@mail.cgs.gov.cn

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Dear author:

Hello, it's my honor to review your manuscript. First of all, I agree with your contribution in this research. The manuscript “Landslide Displacement Prediction using Kernel Extreme Learning Machine with Harris Hawk Optimization based on Variational Mode Decomposition” addresses an interesting topic, which adhere to Land journal policies.

 

After minor revisions I agree with the publication of the manuscript.

1.      At the end of the abstract and at the end of the introduction, it is necessary to emphasise the importance of the research, what distinguishes this research from others and what is new about the research!

2.      Keywords. Try not to use words from the title of the manuscript so that your work can be found more easily by other authors in the future.

3.      The beginning of the introduction should be improved to include more examples. It is recommended to give examples for other countries, regions and continents.

4.      The aims of the research paper are not clearly stated in the introduction. Please state the aims of the research paper in detail.

5.      The section "Theory and Methodology" is very well structured, systematic. This applies in particular to the part of the Prediction procedure and Workflow diagram of VMD-HHO-KELM (Figure 3).

6.      Give basic information about the geological structure of the study area (a few sentences), as part of Figure 4 (Geological profile of the Shuizhuyuan landslide).

7.      Line 208 add references.

8.      Lines 226 and 227 add references.

9.      The results of the investigation are well explained. The graphics are excellent, they show the research results very well.

10.  Expand the discussion. The discussion lacks comparison and discussion with similar studies by other researchers. It would be good to add references to the existence of erosion in other parts of the world in the one paragraph of the discussion (mentioning the most important examples). „The existing literature suggests” (line 312) add references!

11.  In the last paragraph of the discussion, it is good that you write in which direction future research should go. 

 

Author Response

Dear Editors and Reviewers,

Thank you very much and the Reviewers for your careful and timely review and valuable comments on our manuscript (Manuscript ID: land-3226200). Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We carefully considered and revised the article based on the opinions of reviewers. The revised manuscript of the paper has been revised in review mode and the important revisions are marked in red. The main corrections in the paper and the responds to the reviewer’s comments are as following:

 

Comments 1: At the end of the abstract and at the end of the introduction, it is necessary to emphasise the importance of the research, what distinguishes this research from others and what is new about the research!

Response 1: Thanks to the reviewer for the suggestion. We have rewritten the end of the abstract and introduction. Modified as follows: Therefore, under the premise of VMD effectively decomposing displacement data, combined with the global optimization ability of HHO heuristic algorithm and the fast-learning ability of KELM, HHO-KELM can be used for displacement prediction of step-like landslides in the TGRA.

 

Comments 2: Keywords. Try not to use words from the title of the manuscript so that your work can be found more easily by other authors in the future.

Response 2: Thank you for your suggestion. We have adjusted the keywords to improve the visibility of the paper in bibliographic repositories. The revised keywords are: Displacement Prediction; Kernel Extreme Learning Machine; Variational Mode Decomposition; Three Gorges Reservoir Area; Influencing Factors

 

Comments 3: The beginning of the introduction should be improved to include more examples. It is recommended to give examples for other countries, regions and continents.

Response 3: We sincerely appreciate the valuable comments. In the introduction, the context of landslides in the Three Gorges Reservoir Area of China has been described and supplemented. Modified as follows: In the Three Gorges Reservoir Area of China, thousands of landslides are influenced by substantial mass movements due to the complex geological environment, posing a severe threat to the surrounding environment. A typical example is the Qianjiangping landslide that occurred in July 2003, causing serious casualties within a few days after the reservoir reached an elevation of 135 m. Thus, landslide displacement prediction is crucial in landslide disaster research, as an accurate displacement prediction model can reduce disaster loss and risk[6-9]. Quaternary sediments are widely distributed in the TGRA. The most significant features are loose compositions, distinct viscoelastic deformation, and high porosity, making them highly susceptible to water infiltration. Long-term studies have demonstrated that landslide deformation in the TGRA are caused by slow gravitational downslope processes that occur before the failure of the slope[10, 11]. Reservoir water level and precipitation are considered the most important triggers for landslides among these factors.

 

Comments 4: The aims of the research paper are not clearly stated in the introduction. Please state the aims of the research paper in detail.

Response 4: We think this is an excellent suggestion. We have rewritten the end of the introduction and emphasized the purpose, justification, and methodology of the study. The specific revisions are as follows: The purpose of this study is to propose a novel landslide displacement prediction model of VMD-HHO-KELM that considers the external influences on displacement deformation. VMD decomposes the cumulative displacement of landslides into a trend, periodic, and random terms. Then, the external influencing factors are decomposed into two sub-sequences, characterized by periodicity and stochasticity, and fused into the training set as input data. Taking a typical landslide of Shuizhuyuan in the TGRA as an example, three components are predicted separately using the HHO-KELM model and the predicted total displacement is the sum of the three components. To validate the practicality and effectiveness of the HHO-KELM model, performance comparisons are conducted with methods such as ELM, KELM, and PSO-KELM.

 

Comments 5: The section "Theory and Methodology" is very well structured, systematic. This applies in particular to the part of the Prediction procedure and Workflow diagram of VMD-HHO-KELM (Figure 3).

Response 5: Thank you very much for the reviewer's comments on this section.

 

Comments 6: Give basic information about the geological structure of the study area (a few sentences), as part of Figure 4 (Geological profile of the Shuizhuyuan landslide).

Response 6: We sincerely appreciate the valuable comments. The location map and geological context of the study area are supplemented and improved in Section 3.1. Modified as follows: The study area has typical characteristics of a subtropical humid monsoon climate. The surface materials of the Shuizhuyuan landslide are loose gravelly soil with good permeability. The underlying bedrock mainly consists of mudstone and marlstone. The sliding surface has a depth of approximately 30 m. The front edge of the landslide is below the water level of the Yangtze River at 145 m, and the stability of the landslide is significantly affected by the reservoir water level (Figure 5).

 

Comments 7: Line 208 add references.

Response 7: Thanks to the reviewer for the suggestion. It is true as Reviewer suggested that recent relevant references should be included. We have rewritten the discussion section and supplemented the relevant references. The papers mentioned have been added to the References.

1. Du H, Song D, Chen Z et al. Prediction model oriented for landslide displacement with step-like curve by applying ensemble empirical mode decomposition and the PSO-ELM method. Journal of Cleaner Production 2020, 270, 122248.

 

Comments 8: Lines 226 and 227 add references.

Response 8: Thanks to the reviewer for the suggestion. As Reviewer suggested that relevant references should be included in Line 226 and Line 227. The papers mentioned have been added to the References.

1. Guo Z, Chen L, Gui L et al. Landslide displacement prediction based on variational mode decomposition and WA-GWO-BP model. Landslides 2019, 17, 567-583.
2. Guo W, Meng Q, Wang X et al. Landslide Displacement Prediction Based on Variational Mode Decomposition and GA-Elman Model. Applied Sciences 2023, 13, 450.

 

Comments 9: The results of the investigation are well explained. The graphics are excellent, they show the research results very well.

Response 9: Thank you very much for the reviewer's comments.

 

Comments 10: Expand the discussion. The discussion lacks comparison and discussion with similar studies by other researchers. It would be good to add references to the existence of erosion in other parts of the world in the one paragraph of the discussion (mentioning the most important examples). „The existing literature suggests” (line 312) add references!

Response 10: Thanks to the reviewer for the suggestion. Considering the Reviewer’ s suggestion, we have rewritten the discussion section. Modified as follows:

The deformation characteristics of landslides in the TGRA are closely related to various factors, mainly including their own geological structure, precipitation, and reservoir water level adjustments. Through an in-depth analysis of displacement characteristics and deformation mechanisms, it was demonstrated that precipitation during the flood season and fluctuations in water level are the main influencing factors for the Shuizhuyuan landslide. Under the dual influence of these factors, the landslide shows a displacement deformation curve akin to a step-like pattern. Therefore, the prerequisite for conducting landslide displacement prediction is the accurate decomposition.

Traditional methods such as EMD and EEMD have no regularity in the feature components of displacement decomposition. After decomposition, each component requires observation and analysis, followed by recombination to obtain the desired characteristic components. Recombination of these components often increases the duration of data analysis and reduces data processing efficiency. In this study, VMD can adaptively decompose the landslide displacement into characteristic components based on a predetermined number of modes. For instance, when K=3, it can effectively extract trend, periodic, and random displacement components, each with a clear physical meaning. This can effectively suppress the issues of incomplete data decomposition and irregular decomposition patterns that are common in traditional methods.

Comparing models helps to validate the accuracy of the proposed method[25]. ELM is a typical representative machine learning method used for displacement prediction. Therefore, this study used ELM, KELM, and PSO-KELM models to verify the predictive performance of HHO-KELM[4, 25]. As shown in Figure 15 and Table 3, the RMSE and R² of ELM are 1.6995 and 0.9559, respectively, indicating that ELM has the worst predictive ability. After incorporating the kernel function into the ELM, the RMSE and R² of the KELM are 1.0338 and 0.9837, which represents a certain improvement in the displacement prediction capability. To further improve the training efficiency of KELM, optimization algorithms are introduced to optimize the parameters of KELM. The results indicate that the RMSE and R² of the HHO-KELM model are 0.3680 and 0.9979, respectively, providing the best predictive outcomes among the models tested. This is mainly attributed to the global search and adaptive parameter adjustment capabilities of the HHO algorithm. Figure 15 highlights that HHO-KELM, which considers external influencing factors, achieves better landslide displacement prediction and has a very accurate displacement prediction ability, proving that the step-like displacement is affected by precipitation and reservoir water level fluctuation.

In addition, the rapid development of Deep Learning techniques such as Multi-layer Perceptron (MLP) and Transformer provides feasible solutions for long-term series prediction. In future research, the generalization and computational capabilities of Deep Learning will provide more reference options for predicting the displacement of different types of landslides.

 

Comments 11: In the last paragraph of the discussion, it is good that you write in which direction future research should go.

Response 11: We sincerely appreciate the valuable comments. We proposed future research directions in the last paragraph of discussion. Modified as follows: In addition, the rapid development of Deep Learning techniques such as Multilayer Perceptron (MLP) and Transformer provides feasible solutions for long-term series prediction. In future research, the generalization and computational capabilities of Deep Learning will provide more reference options for predicting the displacement of different types of landslides.

 

We tried our best to improve the manuscript and made some changes in the manuscript. These changes will not influence the content and framework of the paper.

 

We appreciate for Editors/Reviewers’ warm work earnestly, and hope that the correction will meet with approval.

 

Once again, thank you very much for your comments and suggestions.

 

Best regards,

 

Chenhui Wang

E-mail: wangchenhui@mail.cgs.gov.cn

Author Response File: Author Response.pdf