Integrating System Dynamics, Land Change Models, and Machine Learning to Simulate and Predict Ecosystem Carbon Sequestration Under RCP-SSP Scenarios: Fusing Land and Climate Changes
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsReview of Manuscript land-3305772: “Integrating system dynamics, land change models, and machine learning to simulate and predict ecosystem carbon sequestration under RCP-SSP scenarios: Fusing land and climate changes”.
General comments
Simulating and predicting C sequestration potential under different RCP-SSP scenarios using system dynamic, land use change models and machine learning is an important part of land-use change policies. Similar research complements the national and international efforts for neutral emission and sink. The article uses a patch-generating simulation, model (PLUS) in association with other models like system dynamic and random forest algorithm to predict NPP under three climate change scenarios. However, the order and method of presentation of the models shows some weakness for the reader to understand the models and for the replicability concern. A slight restructuring (suggested below) can help improving the clarity of the methodology.
Detailed comments
P. 1-2, L. 43-45. Please provide examples or references on your statement: “However, due to the current lack of appropriate tools and methodologies, many local governments estimate future carbon sink levels based on experience rather than quantitative scientific analysis”.
P.7, 213-214. Please explain what these abbreviations stand for, notably the scenarios, to be understood by non-expert readers: “CMIP6 datasets, particularly the CAS-ESM2-0 model using the SSP1-1.9, SSP2-4.5, and SSP5-8.5 pathways”.
P. 8, L. 245-250. This paragraph should come in the beginning of the presentation of the models.
P.9, L. 308. Fill the missing letter in: “The smallest Gini value for is….”
P. 12, Table 4. Why this high value for grassland (9995.58) in 2060 SSP119?
P. 13, Figure 7. The scenarios show urban expansion mainly at the account of cultivated lands. Meanwhile, no arable lands or constructions are expanding towards forestlands. Are forests a protected land use in the study area?
P. 15, Figure 9 and 10. The highest C sequestration are marked in red. Is his color organization justified or it is perhaps better to switch off the colors with the lower values of C sinks shown in red and the highest values shown in green.
P. 18, L. 500. Must be forest land not arable land.
P.18, L. 512-514. What are the potential socio-economic and ecological consequences of the NPP shifted from northwards to southwards regions in Hubei Province?
Author Response
Thank you for your valuable feedback and revision suggestions on my manuscript. Your advice has helped me improve the content of the paper and enhance the quality of the manuscript. Based on your feedback, I have made the following revisions and provide the detailed responses below:
Comments 1:P. 1-2, L. 43-45. Please provide examples or references on your statement: “However, due to the current lack of appropriate tools and methodologies, many local governments estimate future carbon sink levels based on experience rather than quantitative scientific analysis”.
Response 1:Thank you for pointing out ,We agree with this comment.In the revision, we have added a description indicating that some local governments in China only make estimations of forestry carbon sequestration values when developing climate change mitigation plans, and have included the corresponding references. The specific changes are as follows:
However, due to the current lack of appropriate tools and methodologies, many local governments often estimate future carbon sequestration levels based on experience rather than quantitative scientific analysis. For instance, some local governments in China rely on estimations to determine forestry carbon sequestration when developing policies to address climate change. [8]
[8]. Bureau, C.M.E.A., Chongqing's Response to Climate Change "Fourteenth Five-Year Plan" (2021-2025). 2022.
Comments 2:P.7, 213-214. Please explain what these abbreviations stand for, notably the scenarios, to be understood by non-expert readers: “CMIP6 datasets, particularly the CAS-ESM2-0 model using the SSP1-1.9, SSP2-4.5, and SSP5-8.5 pathways”.
Response 2:Thank you for pointing out ,We agree with this comment.In the revision,In section“2.3.1General Procedure”, we have added explanations of different Shared Socio-economic Pathways (SSPs) to clarify the social development scenarios corresponding to different SSPs.The specific changes are as follows:
Three different SSPs are used in this study,particularly the CAS-ESM2-0 model using the SSP1-1.9, SSP2-4.5, and SSP5-8.5 pathways,SSP119 represents a sustainable development path with a strong emphasis on ecological conservation and significant shifts in energy and industrial structures towards low-carbon development. SSP585, on the other hand, represents a high-emission development path that prioritizes the continued large-scale use of fossil fuels. SSP245 serves as a medium-carbon pathway, balancing elements of both extremes.
Comments 3:P. 8, L. 245-250. This paragraph should come in the beginning of the presentation of the models.
Response 3:Thank you for pointing out ,We agree with this comment.Since the explanations for different climate scenarios were explained in 2.3.1General Procedure, the main content of this paragraph was revised to explain the rules of land use type conversion in the PLUS model.The specific changes are as follows:
In the simulation process, we applied restrictions to the land-use type transition rules in the model based on different SSPs and local policies. For example, in the SSP585 scenario, no additional restrictions were imposed, allowing for mutual conversions between all land types. In the SSP2-4.5 scenario, locally designated ecological protection lines and permanent croplands were prohibited from converting to other land types. The SSP1-1.9 scenario, building upon SSP2-4.5, further restricted the conversion of ecologically important areas to other land types.
Comments 4:P.9, L. 308. Fill the missing letter in: “The smallest Gini value for is….”
Response 4:Thank you for pointing out ,We agree with this comment.Add the characters that are not displayed and change it .The specific changes are as follows:
The smallest Gini value for is selected as the optimal split point for further calculations.
Comments 5:P. 12, Table 4. Why this high value for grassland (9995.58) in 2060 SSP119?
Response 5:Thank you for pointing out ,We re-examined the model and cross-checked the data, and found that the data is consistent with the budgeted values in the model. The possible reason for this is that, in the system dynamics model we constructed to predict different land-use types, grassland was treated as a parameter to adjust the total land area in the model due to its relatively small proportion. Some discrepancies occurred in certain years, but since grassland accounts for a very small proportion of the study area (usually around 3%-4%), its impact on the overall trend of NPP in the study area is negligible. Therefore, no modifications were made in this regard during this revision, however, we will further optimize the model in the next study.
Comments 6:P. 13, Figure 7. The scenarios show urban expansion mainly at the account of cultivated lands. Meanwhile, no arable lands or constructions are expanding towards forestlands. Are forests a protected land use in the study area?
Response 6:Thank you for pointing out ,According to the land-use transition rules set in our PLUS model, not all forested areas are protected. In the SSP245 scenario, only forests located within the ecological protection lines are protected. In the SSP585 scenario, only those forests within the ecological protection lines and those with high ecological value are designated for protection.
Comments 7:P. 15, Figure 9 and 10. The highest C sequestration are marked in red. Is his color organization justified or it is perhaps better to switch off the colors with the lower values of C sinks shown in red and the highest values shown in green.
Response t:Thank you for pointing out ,we have made changes to the figures.
Figure 9. Spatial distribution of simulated and observed NPP 2020.(A)Spatial distribution of observed NPP ;(B) Spatial distribution of NPP simulated by random forest model.
Figure 10. Prediction results of dynamic spatial distribution of NPP in multi-scenario.
Comments 8:P. 18, L. 500. Must be forest land not arable land.
Response 8:Thank you for pointing out ,Yes is forest land, have corrected the error.
Comments 9:P.18, L. 512-514. What are the potential socio-economic and ecological consequences of the NPP shifted from northwards to southwards regions in Hubei Province?
Response 9:Thank you for pointing out. A discussion of the relevant potential impacts has been added
Such changes could lead to a negative impact on traditional agriculture in the region, resulting in a decline in agricultural output and a reduction in related employment opportunities. Additionally, climate change may threaten biodiversity, disrupting the original ecological balance. In the southern regions, issues such as soil erosion and land degradation could be further exacerbated. To address these challenges, Hubei Province should strengthen the implementation of ecological protection policies, promote the development of a green economy, raise public awareness of ecological conservation, and guide land use and industrial layout through scientific planning.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsIn the article presented the influence of land use on carbon sequestration using RCP-SSP scenarios. The research was provided in Hubei Province in central region of China and demonstrates the interactions between effectivness of land use, climate change, topography, vegetation conditions and carbon sequestration process. Providing simulation of future plant carbon sequestration rely on liniear regression models, carbon coefficient emission models and Thornthwaite Memorial model.
Please do the corrections of all Figures and Tables in the article, as they are not quite readible.
Please read carefully all text of the article and make some corrections to improve some sentences.
In Section Conclusions please introduce Sub Sections with a description of the most important findings of the study.
Author Response
Thank you for your valuable feedback and revision suggestions on my manuscript. Your advice has helped me improve the content of the paper and enhance the quality of the manuscript. Based on your feedback, I have made the following revisions and provide the detailed responses below:
Comments 1:Please do the corrections of all Figures and Tables in the article, as they are not quite readible.
Response 1:Thank you for pointing out ,We have corrected and optimized some tables and data, such as: Table 3、Table 4, and some of the numbers and symbols in the manuscript.
Comments 2:Please read carefully all text of the article and make some corrections to improve some sentences.
Response 2:Thank you for pointing out ,We double-checked the manuscript and corrected some of the errors.
Comments 3:In Section Conclusions please introduce Sub Sections with a description of the most important findings of the study.
Response 1:Thank you for pointing out .Some new findings are added to the conclusion, such as the trend of northward migration of the main carbon sink area in this region, and the discussion of the potential impact of this change on Hubei Province is added to the discussion.The specific changes are as follows:
Moreover, the study demonstrates that changes in carbon sequestration rates vary under different pathways. For instance, NPP changes in the study area exhibit "inverse S-shaped," "S-shaped," and "parabolic" curves under different policies, indicating significant impacts on local ecosystems, and the main carbon sink areas in the region show a northward shift.. In scenarios with low carbon emissions, future NPP is projected to have greater growth potential, making it easier to achieve carbon neutrality goals.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsThis is a very well organized paper. The authors use a combination of models to predict ecosystem carbon sequestration under climate change scenarios. I think this article can be published with simple changes.
1. The title of this article is too long. I propose to delete "Fusing land and climate changes".
2. I propose to add theoretical construction to section 2.3.1, especially the relationship between the various subsystems.
3. I suggest adding references to the variables in Figure 1.
Author Response
Thank you for your valuable feedback and revision suggestions on my manuscript. Your advice has helped me improve the content of the paper and enhance the quality of the manuscript. Based on your feedback, I have made the following revisions and provide the detailed responses below:
Comments 1:The title of this article is too long. I propose to delete "Fusing land and climate changes".
Response 1:Thank you for pointing out ,we have deleted "Fusing land and climate changes".
Comments 2: I propose to add theoretical construction to section 2.3.1, especially the relationship between the various subsystems.
Response 1:Thank you for pointing out ,We have added relevant content. The specific changes are as follows:
The variation in NPP is influenced by a combination of factors such as land use, climate change, slope, and elevation, and these factors do not have a linear relationship with NPP. Therefore, when simulating future NPP, it is essential to consider the effects of these factors and incorporate future land use and climate projections into the model. In this study, we first predict the spatial and quantitative changes in land use, and based on these predictions, simulate the future distribution of land use. Subsequently, we integrate future climate data to ultimately model the future NPP.
Comments 3:I suggest adding references to the variables in Figure 1.
Response 3:Thank you for pointing out ,Figure 1 is a location map that is used to show our study area without corresponding variables
Author Response File: Author Response.pdf
