Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This an important piece of research.

Some of the english in the abstract and introduction seems a bit clumsy or unclear. EG

L22 perhaps CLQ is necessary for promoting etc.

L62 (and other places) what do you mean by connotation? perhaps intension?

L73, Techical do you mean technique

L74, You often miss the eg the Chinese government, many examples)

L119 pH is a measure of relative acidity perhaps you should write

pH is too acid or too alkaline 

General, I think in discussing the case study you should mention ground truthing,  I also think you should mention irrigation capacity 

L 149 what is sand ginger black soil? I have not heard of this, perhaps it is soil suitable for growing black ginger?

L192. perhaps prediction

L198 Fig 2. Perhaps you could use the FAO criteria for fofest cover, related to % Canopy, instead of Random Forest?  more accurate for remote sensing

L 212.Table 2. health status, what is meant by cleaning degree? It is important to define this somewhere, is it related to soil polution? or heavy metal pollution? 

L300 Many studies have shown that

L368 Fig 7. This is the first place where you mention this important obstacle of Irrigation capacity hence I think some discussion belongs in the introduction. This obstacle has several components, water avilability, standard of canals etc. You rightly discuss the importance of this obstacle.  But you dont mention salinity again after the introduction, does thios mean you detected none in the sampling? You indicate Cleaning degree is low. but I dont yet know what this means, although it might be important, notably in food production for humans 

Comments on the Quality of English Language

Some of the english in the Abstract and introduction seems clumsey or not clear, see comments above

Author Response

We thank editor and reviewers for their valuable remarks and suggestions. We have revised the manuscript thoroughly by the effort contributed by all co-authors. Below we list all the comments of the reviewers followed by our answers. You will see that we have done our best to improve all the points that have been raised. All the lines indicated below are showed in the revised manuscript with red marked.

 

Comments from Reviewer #1

This an important piece of research. Some of the English in the abstract and introduction seems a bit clumsy or unclear.

Comment 1:

L22 perhaps CLQ is necessary for promoting etc.

Response：

Thank you for your good advice. To clarify the meaning of the language more accurately and clearly, we have made modifications in the revised manuscript (Line 22).

 

Comment 2:

L62 (and other places) what do you mean by connotation? perhaps intension?

Response：

Thanks for your comment. The mean of "connotation" equals the mean of "intension". To improve the readability of the manuscript, we have revised "connotation" to "intension" in the revised manuscript (Line 63, Line 65, Line 423, and Line 427).

 

Comment 3:

L73 Techical do you mean technique

Response：

Thank you so much for your reminding. We have revised "technical" to "techniques" in the revised manuscript. (Line 74).

 

Comment 4:

L74 You often miss the eg the Chinese government, many examples

Response：

Thank you for your suggestion. This research illustrated the current research background and progress of cultivated land quality evaluation by giving examples. There are some differences in the usage of "eg" and "for example ". We used "for example "to express opinions more accurately and objectively. When it is appropriate to use "eg", we will take your comments seriously. Thank you again.

 

Comment 5:

L119 pH is a measure of relative acidity perhaps you should write pH is too acid or too alkaline. General, I think in discussing the case study you should mention ground truth, I also think you should mention irrigation capacity.

Response：

Thanks for your suggestion. to improve the readability of the manuscript, we have modified the inappropriate language and added some ground truths, such as irrigation capacity, in the revised manuscript (Line 120-125).

For example, when the soil nutrient content is low, or the soil pH is too acidic or too alkaline, or irrigation cannot be satisfied, they may become an obstacle factor. Irrigation capacity is mainly affected by farmland infrastructure, irrigation water reserves and other factors (Li et al., 2020; Duan et al., 2022). Therefore, to improve the CLQ in a targeted manner, it is necessary to quantitatively evaluate the obstacle degree of each index to CLQ and analyze the causes of the obstacle.

 

1. Li, X.R.; Jiang, W.L.; Duan, D.D. Spatiotemporal analysis of irrigation water use coefficients in China. J. Environ Manage. 2020, 262, 110242. https://doi.org/10.1016/j.jenvman.2020.110242.
2. Duan, D.D. Remote sensing evaluation of cultivated land quality and its spatiotemporal characteristics based on multisource Data. Chinese Academy of Agricultural Sciences. 2022. https://doi.org/10.27630/d.cnki.gznky.2022.000267.

 

Comment 6:

L 149 what is sand ginger black soil? I have not heard of this, perhaps it is soil suitable for growing black ginger?

Response：

Thanks for your comment. We have modified "sand ginger black soil" to "Shajiang black soil" in the revised manuscript (Line 156).

 

Comment 7:

L192. perhaps prediction

Response：

Thank you so much for your reminding. We have revised "predict" to "prediction" in the revised manuscript (Line 202).

 

Comment 8:

L198 Fig 2. Perhaps you could use the FAO criteria for forest cover, related to % Canopy, instead of Random Forest?  more accurate for remote sensing

Response：

Thanks for your comment. The object of this research is cultivated land, not forest. Random forest algorithm is a modeling method, and we used it to construct cultivated land quality evaluation model in this research. In future, if the research object is forest, we seriously consider your suggestion, thank you again.

 

Comment 9:

L212 Table 2. health status, what is meant by cleaning degree? It is important to define this somewhere, is it related to soil pollution? or heavy metal pollution?

Response：

Thanks for your suggestion. We have added the definition of cleaning degree in the revised manuscript (Line 237-239). Cleaning degree can reflect the extent to which cultivated soil is affected by toxic and harmful substances such as heavy metals, pesticides, and agricultural film residues (Zhao et al., 2021; Tang et al., 2023).

 

1. Zhao, C.; Zhou, Y.; Jiang, J.H.; Xiao, P.N.; Wu, H. Spatial characteristics of cultivated land quality accounting for ecological environmental condition: A case study in hilly area of northern Hubei province, China. Sci. Total Environ. 2021, 774, 145765. https://doi.org/10.1016/j.scitotenv.2021.145765.
2. Tang, M.M.; Wang, C.T.; Ying, C.Y.; Mei, S.; Tong, T.; Ma, Y.H.; Wang, Q. Research on cultivated land quality restriction factors based on cultivated land quality level evaluation. Sustainability. 2023, 15, 7567. https://doi.org/10.3390/su15097567.

 

Comment 10:

L300 Many studies have shown that

Response：

Thank you so much for your reminding. we have revised “Many studies shown that” to “Many studies have shown that” in the revised manuscript (Line 350).

 

Comment 11:

L368 Fig 7. This is the first place where you mention this important obstacle of Irrigation capacity. Hence, I think some discussion belongs in the introduction. This obstacle has several components, water availability, standard of canals etc. You rightly discuss the importance of this obstacle.  But you do not mention salinity again after the introduction, does this mean you detected none in the sampling? You indicate cleaning degree is low. but I do not yet know what this means, although it might be important, notably in food production for humans.

Response：

Thanks for your suggestion. We have added the description of irrigation capacity in the introduction of the revised manuscript (Line 120-125).

When the irrigation capacity of cultivated land cannot be met, it may become an obstacle factor. Irrigation capacity is mainly affected by farmland infrastructure, irrigation water reserves and other factors (Li et al., 2020; Duan et al., 2022). Therefore, to improve the CLQ in a targeted manner, it is necessary to quantitatively evaluate the obstacle degree of each indicator to CLQ and analyze the causes of the obstacle.

Soil salinity was not considered in this study for the following two reasons. In the national standard of “Cultivated Land Quality Grade” (GB/T 33469-2016), soil salinity or salinization degree is a supplementary indicator, not a required indicator. At the same time, according to the measured results of soil samples, the salinity content of soil in the study area was very small, there is no salinization, and the spatial difference was small, which had little influence on the CLQ of the study area. For the above reasons, soil salinity was not included in the CLQ evaluation system.

The results of this study showed that the obstacle degree of cleaning degree was low, indicating that the health status of cultivated land was good, and it was not the main limiting factor affecting the CLQ in the study area. In fact, we should pay more attention to the factors with a greater obstacle degree, and put forward targeted improvement measures for these factors, which is more conducive to improving the CLQ.

 

1. Li, X.R.; Jiang, W.L.; Duan, D.D. Spatiotemporal analysis of irrigation water use coefficients in China. J. Environ Manage. 2020, 262, 110242. https://doi.org/10.1016/j.jenvman.2020.110242.
2. Duan, D.D. Remote sensing evaluation of cultivated land quality and its spatiotemporal characteristics based on mul-ti-source Data. Chinese Academy of Agricultural Sciences. 2022. https://doi.org/10.27630/d.cnki.gznky.2022.000267.

 

Comment 12:

Some of the English in the Abstract and introduction seems clumsy or not clear, see comments above

Response：

Thank you for your suggestion. We have tried our best to revise the manuscript according to your comments mentioned above. At the same time, to improve the readability of the manuscript, we invited professional native English speakers to polish the revised manuscript. We have provided the copy of certificate, please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

1）How were the weights of the selected indicators in Table 2 determined? Please provide further details on the calculation methods and data sources.

2） How were the membership functions in Table 3 established? This part is not clearly explained.

3）Please verify the data in line 323. Typically, an R² value of 0.19 indicates a weak correlation between the two variables, not a strong one.

 

Comments on the Quality of English Language

The English language in the paper needs further review by a native speaker or a professional editing service.

Author Response

We thank editor and reviewers for their valuable remarks and suggestions. We have revised the manuscript thoroughly by the effort contributed by all co-authors. Below we list all the comments of the reviewers followed by our answers. You will see that we have done our best to improve all the points that have been raised. All the lines indicated below are showed in the revised manuscript with red marked.

 

Comments from Reviewer #2

Comment 1:

How were the weights of the selected indicators in Table 2 determined? Please provide further details on the calculation methods and data sources.

Response：

Thank you for your suggestion. We have provided detailed supplementary instructions in the revised manuscript (Line 240-248).

It is very important to set the appropriate weight coefficient for each evaluation indicator. In this study, we consulted seven experts in the field of cultivated land quality evaluation from the Chinese Academy of Agricultural Sciences, Shandong Agricultural University and Qingdao Agricultural University in the form of questionnaires. They ranked the importance of selected cultivated land quality evaluation indicators. We combined the expert survey results with the analytic hierarchy process to construct the analytic hierarchy process model, so as to calculate the weight coefficient of the evaluation indicator (Duan et al., 2022; Iheshiulo et al., 2024). Moreover, the calculated results passed the consistency test (the consistency ratio was less than 0.1), indicating that the calculation of the weight coefficient was reasonable and reliable.

 

1. Duan, D.D.; Sun, X.; Liang, S.F.; Sun, J.; Fan, L.L.; Chen, H.; Xia, L.; Zhao, F.; Yang, W.Q.; Yang, P. Spatiotemporal patterns of cultivated land quality integrated with multi-source remote sensing: A case study of Guangzhou, China. Remote Sens. 2022, 14, 1250. https://doi.org/10.3390/rs14051250.
2. Iheshiulo, E.M.A.; Larney, F.; Hernandez-Ramirez, G.; Luce, M.S.; Chau, H.W.; Liu, K. Quantitative evaluation of soil health based on a minimum dataset under various short-term crop rotations on the Canadian prairies. Sci. Total Environ. 2024, 935, 173335. https://doi.org/10.1016/j.scitotenv.2024.173335.

 

Comment 2:

 How were the membership functions in Table 3 established? This part is not clearly explained.

Response：

Thank you for your suggestion. We have added clear and detailed supplementary instructions in the revised manuscript (Line 252-285).

The first step to calculate the membership degree of indicator is to determine the function type between evaluation indicator and CLQ. According to the theory of fuzzy mathematics, the relationship between the selected evaluation indicators and the CLQ is divided into five types of membership functions: conceptual function, top function, bottom function, peak function, and linear function (Cultivated Land Quality Grade, GB/T 33469-2016). In this study, SOM, AP, AK, thickness of ploughing layer and effective soil layer thickness belong to the top function, soil pH and SBD belong to the peak function, and the other indicators are conceptual functions.

The Delphi method is an expert forecasting method that aims to reach a consensus through the opinions of a group of experts (Mamehpour et al., 2021). The advantage of Delphi method is that experts can express their opinions independently and anonymously, collect opinions repeatedly through questionnaires, and finally reach a consensus on the problems to be solved (). In this study, Delphi method was adopted to determine the membership degree of the evaluation indicator. We selected seven experts in the field of cultivated land quality (CLQ) evaluation and asked them to independently assess the CLQ evaluation indicator. Finally, the answers of experts were summarized and analyzed, and the membership degree of each evaluation indicator was determined after three feedbacks and corrections.

For the evaluation indicators of top and peak function, we used Delphi method to evaluate a set of membership degrees on the measured data and fit the membership functions. Then the measured value of each evaluation indicator was brought into the membership function for calculation, so as to obtain the membership degree of each evaluation indicator.

 

1. Ministry of Agriculture and Rural Affairs of People’s Republic of China, 2016. Cultivated Land Quality Grade (GB/ T33469-2016). https://www.doc88.com/p-4334928129828.html.
2. Mamehpour, N.; Rezapour, S.; Ghaemian, N. Quantitative assessment of soil quality indices for urban croplands in acalcareous semi-arid ecosystem. Geoderma. 2021, 382, 114781. https://doi.org/10.1016/j.geoderma.2020.114781.
3. Song, W.; Zhang, H.Z.; Zhao, R.; Wu, K.N.; Li, X.J.; Niu, B.B.; Li, J.Y. Study on cultivated land quality evaluation from the perspective of farmland ecosystems. Ecol. Indic. 2022, 139, 108959. https://doi.org/10.1016/j.ecolind.2022.108959.
4. Tang, M.M.; Wang, C.T.; Ying, C.Y.; Mei, S.; Tong, T.; Ma, Y.H.; Wang, Q. Research on cultivated land quality restriction factors based on cultivated land quality level evaluation. Sustainability. 2023, 15, 7567. https://doi.org/10.3390/su15097567.

 

Comment 3:

Please verify the data in line 323. Typically, an R² value of 0.19 indicates a weak correlation between the two variables, not a strong one.

Response：

Thank you for your good advice. According to you and other reviewers' suggestion, we have recalculated Pearson correlation coefficients (r) and significance tests between the two sets of data in the revised manuscript. The results showed that r was 0.44, p<0.001, which indicated that there was a significant positive correlation between cultivated land quality index and crop yield (Line 373-375).

 

Comment 4:

The English language in the paper needs further review by a native speaker or a professional editing service.

Response：

Thanks for your suggestion. To improve the readability of the manuscript, we invited professional native English speakers to polish the revised manuscript. We have provided the copy of certificate, please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

This study developed a county-level CLQ evaluation system and employed multi-temporal remote sensing data and machine learning methods to assess CLQ in the Jimo District of Shandong Province, China. The authors further analyzed the evaluation results and provided policy recommendations based on their findings. Below are my comments on the paper. 

 

In the introduction, the authors present a substantial body of work related to CLQ. However, they did not adequately summarize the primary challenges in this research field, which should be the central issue this study aims to address. This oversight makes it difficult to fully assess the significance and contribution of their work, despite the substantial effort invested in the study. 

 

The authors are advised to clearly highlight the main contribution or innovation of this study. The work comprises several components, including the construction of the evaluation system, CLQ evaluations using remote sensing data and machine learning methods, and the analysis of the evaluation results. However, it is not clear which aspect represents the primary contribution. What is the key innovation of this work in comparison with previous studies?

 

The evaluation system is fundamental to the CLQ assessment. While the authors have introduced the indicators used in the system, they have not adequately explained the rationale behind their selection. Although the national standard is an important reference, it alone is insufficient to justify the choice of each indicator. The authors should provide more detailed elaboration and considerations to support their selection.

 

This study verified the CLQ evaluation results by analyzing the correlation between the CLQ index and crop yield. Crop yield may vary significantly across different types of crops. How did you tackle this effect in the analysis. Moreover, the authors used R2 value instead of correlation coefficient to assess the linear relationship between the CLQ index and crop year (Figure 4), Why? Can the low R2 value (0.19) indicate a strong relationship?

 

The remote sensing data are used merely as proxies for input indicators in the evaluation. This limited role of remote sensing data makes the study only marginally relevant to the scope of this journal.

 

For Table 2, the authors should clarify how the weight of each indicator was determined. 

 

For Figure 1, please include the subtitles for (a), (b), (c), and (d) in the figure caption.

 

For Figure 3, the authors only provide R2 values, which are not particularly high. It would be beneficial to also include the correlation coefficient for a more comprehensive assessment of model performance.

 

Line 26, it should be county-level. 

 

Line 161, please give a full name of SOM. 

 

Line 193, please explain what are the training and verification of machine learning models?

 

Line 229, Please elaborate the Delphi method and provide necessary references. 

 

Comments on the Quality of English Language

The English is good. 

Author Response

We thank editor and reviewers for their valuable remarks and suggestions. We have revised the manuscript thoroughly by the effort contributed by all co-authors. Below we list all the comments of the reviewers followed by our answers. You will see that we have done our best to improve all the points that have been raised. All the lines indicated below are showed in the revised manuscript with red marked.

 

Comments from Reviewer #3

This study developed a county-level CLQ evaluation system and employed multi-temporal remote sensing data and machine learning methods to assess CLQ in the Jimo District of Shandong Province, China. The authors further analyzed the evaluation results and provided policy recommendations based on their findings. Below are my comments on the paper.

Comment 1:

In the introduction, the authors present a substantial body of work related to CLQ. However, they did not adequately summarize the primary challenges in this research field, which should be the central issue this study aims to address. This oversight makes it difficult to fully assess the significance and contribution of their work, despite the substantial effort invested in the study.

Response：

Thank you for pointing this out. We agree with this comment. In the introduction part of the revised manuscript, we have summarized and highlighted the main challenges in the field of cultivated land quality evaluation and emphasized the key problems to be solved in this study.

The main challenges in the field of cultivated land quality (CLQ) evaluation are as follows: first, due to the different evaluation purposes, there is no consensus on the intension of CLQ in the world, which leads to the lack of a universal evaluation system and technique (Kang et al., 2021; Sun et al., 2023) (Line 62-64; Line 72-74). Second, the traditional CLQ evaluation method relies on a large number of field investigations, which was time-consuming and laborious, resulting in poor timeliness of the evaluation results (Xia et al., 2019) (Line 99-101). Furthermore, traditional statistical methods can not reveal the nonlinear relationship between multi-source data and CLQ (Zhao et al., 2021) (Line 99-115). Third, the existing research results paid too much attention to the spatial distribution of CLQ, often ignored how to further improve the CLQ, and put forward targeted improvement measures (Zhao et al., 2021; Yuan et al., 2022) (Line 116-125).

In response to the challenges mentioned above, based on the national standard of CLQ (GB/ T33469-2016) and the zoning of the study area, this study first established a general county-level CLQ evaluation system, and defined the evaluation technical process, including the determination of index weight coefficient and membership degree (Line 85-98). Secondly, we used multi-temporal Sentinel-2 remote sensing data and machine learning models to improve the timeliness and efficiency of CLQ evaluation, and combined meteorological, soil, terrain and farmland management data to make the CLQ evaluation results more comprehensive and reliable (Line 101-115; Line 302-313). Finally, to further improve the CLQ in the study area, we used the obstacle factor diagnosis model to quantitatively analyze the maximum and average obstacle degree of each evaluation indicator (Line 412-418), and put forward targeted measures to improve the CLQ in the study area by referring to a large number of existing research results (Line 475-517).

 

1. Kang, L.; Zhao, R.; Wu, K.; Huang, Q.; Zhang, S. Impacts of farming layer constructions on cultivated land quality under the cultivated land balance policy. Agronomy. 2021, 11, 2403. https://doi.org/10.3390/agronomy11122403.
2. Sun, X.; Li, Q.; Kong, X.; Cai, W.; Zhang, B.; Lei, M. Spatial characteristics and obstacle factors of cultivated land quality in an intensive agricultural region of the North China Plain. Land. 2023, 12, 1552. https://doi.org/10.3390/land12081552.
3. Xia, Z.Q.; Peng, Y.P.; Liu, S.S.; Liu, Z.H.; Wang, G.X.; Zhu, A.X.; Hu, Y.M. The optimal image date selection for evaluating cultivated land quality based on Gaofen-1 images. Sensors. 2019, 19, 4937. http://dx.doi.org/10.3390/s19224937.
4. Zhao, C.; Zhou, Y.; Jiang, J.H.; Xiao, P.N.; Wu, H. Spatial characteristics of cultivated land quality accounting for ecological environmental condition: A case study in hilly area of northern Hubei province, China. Sci. Total Environ. 2021, 774, 145765. https://doi.org/10.1016/j.scitotenv.2021.145765.
5. Yuan, X.F.; Shao, Y.J.; Li, Y.H.; Liu, Y.S.; Wang, Y.S.; Wei, X.D.; Wang, X.F.; Zhao, Y.H. Cultivated land quality improvement to promote revitalization of sandy rural areas along the Great Wall in northern Shaanxi Province, China. J. Rural Stud. 2022, 93, 367-374. https://doi.org/10.1016/j.jrurstud.2019.10.011.

 

Comment 2:

The authors are advised to clearly highlight the main contribution or innovation of this study. The work comprises several components, including the construction of the evaluation system, CLQ evaluations using remote sensing data and machine learning methods, and the analysis of the evaluation results. However, it is not clear which aspect represents the primary contribution. What is the key innovation of this work in comparison with previous studies?

Response：

Thank you for pointing this out. We agree with this comment. We have highlighted and emphasized the main contributions and innovations of this study in the revised manuscript (Line 144-149).

The main contributions of this study were as follows: (1) to provide an efficient and reproducible CLQ evaluation method applicable to county districts based on national standard with multi-temporal remote sensing data and machine learning models; (2) to reveal the spatial pattern of CLQ in Jimo district, and help stakeholders grasp the current situation of CLQ; (3) to identify the main obstacle factors, and provide targeted measures or policy recommendations.

Compared with previous studies, the key innovation of this study was that based on the China’s first national standard of "Cultivated Land Quality Grade", remote sensing technology and machine learning model were used to build a set of universal CLQ evaluation system and technical method applicable to the county administrative region, which can improve the efficiency and reliability of CLQ evaluation results (Line 25-35; Line 136-137). Moreover, this study identified the main obstacle factors and put forward targeted measures to improve the CLQ of the study area, which made the research results have practical guiding significance and could be adopted by stakeholders (Line 37-42).

 

Comment 3:

The evaluation system is fundamental to the CLQ assessment. While the authors have introduced the indicators used in the system, they have not adequately explained the rationale behind their selection. Although the national standard is an important reference, it alone is insufficient to justify the choice of each indicator. The authors should provide more detailed elaboration and considerations to support their selection.

Response：

Thank you for your good advice. We have added a detailed supplementary description in the revised manuscript to prove that the selection of evaluation indicators is reasonable (Line 224-239).

Topographic location, effective soil layer thickness, texture configuration and thickness of ploughing layer are the key criteria to measure the cultivability of cultivated land, and they are the most commonly used indicators to characterize the site conditions of cultivated land (Kang et al., 2021; Tang et al., 2023) Soil pH, topsoil texture and soil bulk density are key components of soil physicochemical properties (Mamehpour et al., 2021). Soil pH is closely related to the availability of soil nutrients (Han et al., 2022). Topsoil texture can affect the water and fertilizer retention ability of soil (Duan et al., 2024). Soil bulk density has influence on soil permeability and soil temperature (Shi et al., 2020). Nutrient status can represent soil fertility (Bogunovic et al., 2018). Soil organic matter, available phosphorus and available potassium are the most representative indicators of soil nutrients (Mponela et al., 2020). Farmland management is an important measure to improve the CLQ (Damiba et al., 2024). For example, proper irrigation and drainage can ensure the healthy growth of crops (Duan et al., 2024). Farmland forest network degree can improve the cultivated land environment and reduce soil erosion (Li et al., 2021). Biodiversity and cleaning degree were selected to characterize the health status of cultivated land, which is the core of ensuring the quality and safety of agricultural products (Zhao et al., 2021). Biodiversity can reflect the richness of cultivated soil vitality (Klaus et al., 2024; Zhao et al., 2024). Cleaning degree can reflect the extent to which cultivated soil is affected by toxic and harmful substances such as heavy metals, pesticides, and agricultural film residues (Zhao et al., 2021; Tang et al., 2023).

 

1. Kang, L.; Zhao, R.; Wu, K.; Huang, Q.; Zhang, S. Impacts of farming layer constructions on cultivated land quality under the cultivated land balance policy. Agronomy. 2021, 11, 2403. https://doi.org/10.3390/agronomy11122403.
2. Tang, M.M.; Wang, Q.; Mei, S.; Ying, C.; Gao, Z.; Ma, Y.; Hu, H. Research on the inversion model of cultivated land quality using high-resolution remote sensing data. Agronomy. 2023, 13, 2871. https://doi.org/10.3390/agronomy13122871.
3. Mamehpour, N.; Rezapour, S.; Ghaemian, N. Quantitative assessment of soil quality indices for urban croplands in acalcareous semi-arid ecosystem. Geoderma. 2021, 382, 114781. https://doi.org/10.1016/j.geoderma.2020.114781.
4. Han, Y.; Dan, Y.; Ye, Y.C.; Guo, X.; Liu, S.Y. Response of spatiotemporal variability in soil pH and associated influencing factors to land use change in a red soil hilly region in southern China. Catena. 2022, 212, 106074. https://doi.org/10.1016/j.catena.2022.106074.
5. Duan, D.D.; Sun, X.; Wang, C.; Zha, Y.; Yu, Q.; Yang, P. A remote sensing approach to estimating cropland sustainability in the lateritic red soil region of China. Remote Sens. 2024, 16, 1069. https://doi.org/10.3390/rs16061069.
6. Shi, Y.Y.; Duan, W.K.; Fleskens, L.; Li, M.; Hao, J.M. Study on evaluation of regional cultivated land quality based on resource asset-capital attributes and its spatial mechanism. Appl. Geogr. 2020, 125, 102284. https://doi.org/10.1016/j.apgeog.2020.102284.
7. Bogunovic, I.; Trevisani, S.; Pereira, P.; Vukadinovic, V. Mapping soil organic matter in the Baranja region (Croatia): Geological and anthropic forcing parameters. Sci. Total Environ. 2018, 643, 335-345. https://doi.org/10.1016/j.scitotenv.2018.06.193.
8. Mponela, P.; Snapp, S.; Villamor, G.B.; Tamene, L.; Le, Q.B.; Borgemeister, C. Digital soil mapping of nitrogen, phosphorus, potassium, organic carbon and their crop response thresholds in smallholder managed escarpments of Malawi. Sci. Total Environ. 2020, 124, 102299. https://doi.org/10.1016/j.apgeog.2020.102299.
9. Damiba, W.A.F.; Gathenyab, J.M.; Raude, J.M.; Home, P.G. Soil quality index (SQI) for evaluating the sustainability status of Kakia-Esamburmbur catchment under three different land use types in Narok County, Kenya. Heliyon. 2024, 10, e25611. https://doi.org/10.1016/j.heliyon.2024.e25611.
10. Li, Q.; Guo, W.; Sun, X.; Yang, A.; Qu, S.; Chi, W. The differentiation in cultivated land quality between modern agricultural areas and traditional agricultural areas: Evidence from Northeast China. Land. 2021, 10, 842. https://doi.org/10.3390/land10080842.
11. Zhao, C.; Zhou, Y.; Jiang, J.H.; Xiao, P.N.; Wu, H. Spatial characteristics of cultivated land quality accounting for ecological environmental condition: A case study in hilly area of northern Hubei province, China. Sci. Total Environ. 2021, 774, 145765. https://doi.org/10.1016/j.scitotenv.2021.145765.
12. Klaus, V.H.; Schaub, S.; Séchaud, R.; Fabian, Y.; Jeanneretc, P.; Liüischer, A.; Huguenin-Elie, O. Upscaling of ecosystem service and biodiversity indicators from field to farm to inform agri-environmental decision- and policy-making. Ecol. Indic. 2024, 163, 112104. https://doi.org/10.1016/j.ecolind.2024.112104.
13. Zhao, J.Q.; Yu, L.; Newbold, Tim.; Shen, X.L.; Liu, X.X.; Hua, F.Y.; Kanniah, K.; Ma, K.P. Biodiversity responses to agri-cultural practices in cropland and natural habitats. Sci. Total Environ. 2024, 922, 171296. https://doi.org/10.1016/j.scitotenv.2024.171296.
14. Tang, M.M.; Wang, C.T.; Ying, C.Y.; Mei, S.; Tong, T.; Ma, Y.H.; Wang, Q. Research on cultivated land quality restriction factors based on cultivated land quality level evaluation. Sustainability. 2023, 15, 7567. https://doi.org/10.3390/su15097567.

 

Comment 4:

This study verified the CLQ evaluation results by analyzing the correlation between the CLQ index and crop yield. Crop yield may vary significantly across different types of crops. How did you tackle this effect in the analysis. Moreover, the authors used R2 value instead of correlation coefficient to assess the linear relationship between the CLQ index and crop year (Figure 4), Why? Can the low R2 value (0.19) indicate a strong relationship?

Response：

Thank you for your good advice. According to you and other reviewers' suggestions, we have recalculated Pearson correlation coefficients (r) and significance tests between the two sets of data in the revised manuscript. The results showed that r was 0.44, p<0.001, which indicated that there was a significant positive correlation between cultivated land quality index and crop yield (Line 373-375).

The cultivation system in the study area is mainly two-cropping a year, mainly wheat and maize rotation, accounting for nearly 90% (Line 160-161).

The crop yield data used in this study was the sum of maize and wheat yield in one year. Other crop types accounted for less than 10%, so they were not taken into account in this study (Line 355-357).

We will take your suggestions seriously in our future research. By collecting the yield data of different crops, the relationship between them and the cultivated land quality will be further quantitatively analyzed.

 

Comment 5:

The remote sensing data are used merely as proxies for input indicators in the evaluation. This limited role of remote sensing data makes the study only marginally relevant to the scope of this journal.

Response：

Thank you for your comment. To highlight the importance of remote sensing technology in cultivated land quality evaluation, we have added a supplementary description in the introduction of the revised manuscript (Line 100-105).

Remote sensing technology has been widely used in cultivated land quality evaluation (Ma et al., 2020; Zhou et al., 2022; Tang et al., 2023). Compared with traditional field sampling methods, remote sensing technology can quickly obtain a wide range of cultivated land quality information (Xia et al., 2019; Duan et al., 2022). In this study, we used multi-temporal Sentinel-2 remote sensing images to monitor cultivated land quality, which made the monitoring results more objective and time-efficient. At the same time, we combined remote sensing data with meteorology, topography, soil properties and human utilization methods to make the cultivated land quality evaluation results more comprehensive and reliable.

The scope of acceptance of the Remote Sensing journal covers all aspects of remote sensing science. Agricultural remote sensing is an important part of remote sensing science. We believe our research are of interest to a wide range of readers of Remote Sensing and to researchers in the fields of “Multispectral and hyperspectral remote sensing” and “Remote sensing applications”.

 

1. Ma, J.N.; Zhang, C.; Yun, W.J.; Lv, Y.H.; Chen, W.L.; Zhu, D.H. The temporal analysis of regional cultivated land productivity with GPP based on 2000-2018 MODIS data. Sustainability. 2020, 12, 411. https://doi.org/10.3390/su12010411.
2. Zhou, W.; Zhao, L.; Hu, Y.M.; Liu, Z.H.; Wang, L., Ye, C.D.; Mao, X.Y.; Xie, X. Cultivated land quality evaluated using the RNN algorithm based on multisource data. Remote Sens. 2022, 14, 6014. https://doi.org/10.3390/rs14236014.
3. Tang, M.M.; Wang, Q.; Mei, S.; Ying, C.; Gao, Z.; Ma, Y.; Hu, H. Research on the inversion model of cultivated land quality using high-resolution remote sensing data. Agronomy. 2023, 13, 2871. https://doi.org/10.3390/agronomy13122871.
4. Xia, Z.Q.; Peng, Y.P.; Liu, S.S.; Liu, Z.H.; Wang, G.X.; Zhu, A.X.; Hu, Y.M. The optimal image date selection for evaluating cultivated land quality based on Gaofen-1 images. Sensors. 2019, 19, 4937. http://dx.doi.org/10.3390/s19224937.
5. Duan, D.D.; Sun, X.; Liang, S.F.; Sun, J.; Fan, L.L.; Chen, H.; Xia, L.; Zhao, F.; Yang, W.Q.; Yang, P. Spatiotemporal patterns of cultivated land quality integrated with multi-source remote sensing: A case study of Guangzhou, China. Remote Sens. 2022, 14, 1250. https://doi.org/10.3390/rs14051250.

 

Comment 6:

For Table 2, the authors should clarify how the weight of each indicator was determined.

Response：

Thank you for your suggestion. We have provided detailed supplementary instructions in the revised manuscript (Line 240-248).

It is very important to set the appropriate weight coefficient for each evaluation indicator. In this study, we consulted seven experts in the field of cultivated land quality evaluation from the Chinese Academy of Agricultural Sciences, Shandong Agricultural University and Qingdao Agricultural University in the form of questionnaires. They ranked the importance of selected cultivated land quality evaluation indicators. We combined the expert survey results with the AHP to construct the AHP model, so as to calculate the weight coefficient of the evaluation indicator (Duan et al., 2022; Iheshiulo et al., 2024). Moreover, the calculated results passed the consistency test (the consistency ratio was less than 0.1), indicating that the calculation of the weight coefficient was reasonable and reliable.

 

1. Duan, D.D.; Sun, X.; Liang, S.F.; Sun, J.; Fan, L.L.; Chen, H.; Xia, L.; Zhao, F.; Yang, W.Q.; Yang, P. Spatiotemporal patterns of cultivated land quality integrated with multi-source remote sensing: A case study of Guangzhou, China. Remote Sens. 2022, 14, 1250. https://doi.org/10.3390/rs14051250.
2. Iheshiulo, E.M.A.; Larney, F.; Hernandez-Ramirez, G.; Luce, M.S.; Chau, H.W.; Liu, K. Quantitative evaluation of soil health based on a minimum dataset under various short-term crop rotations on the Canadian prairies. Sci. Total Environ. 2024, 935, 173335. https://doi.org/10.1016/j.scitotenv.2024.173335.

 

Comment 7:

For Figure 1, please include the subtitles for (a), (b), (c), and (d) in the figure caption.

Response：

Thank you so much for your reminding. We have added the subtitles for (a), (b), (c), and (d) in the revised manuscript (Line 163-165).

 

Comment 8:

For Figure 3, the authors only provide R2 values, which are not particularly high. It would be beneficial to also include the correlation coefficient for a more comprehensive assessment of model performance.

Response：

Thank you for your good advice. According to you and other reviewers' suggestions, we have recalculated Pearson correlation coefficients (r) and significance tests between the two sets of data in the revised manuscript. The results showed that r was 0.44, p<0.001, which indicated that there was a significant positive correlation between cultivated land quality index and crop yield (Line 373-375).

 

Comment 9:

Line 26, it should be county-level.

Response：

Thank you so much for your reminding. we have made modifications according to your suggestions (Line 26).

 

Comment 10:

Line 161, please give a full name of SOM.

Response：

Thank you so much for your reminding. We have added the full name of SOM in the revised manuscript according to your suggestions (Line 171).

 

Comment 11:

Line 193, please explain what are the training and verification of machine learning models?

Response：

Thanks for your suggestion. We have made a supplementary explanation in the revised manuscript (Line 204-208).

Training is the core part of machine learning, and its purpose is to enable machine learning models to automatically extract useful features through large amounts of training data, and learn how to make predictions on new input data sets (Chen et al., 2019; Mahjenabadi et al., 2022). The main purpose of verification is to prevent machine learning models from overfitting and underfitting, and to optimize the model (Lu et al., 2023; Estévez et al., 2024).

 

1. Chen, D.; Chang, N.J.; Xiao, J.F. Mapping dynamics of soil organic matter in croplands with MODIS data and machine learning algorithms. Sci. Total Environ. 2019, 669, 844-855. https://doi.org/10.1016/j.scitotenv.2019.03.151.
2. Mahjenabadi, V.A.J.; Mousavi, S.R.; Rahmani, A.; Karami, A.; Rahmani, H. A.; Khavazi, K.; Rezaei, M. Digital mapping of soil biological properties and wheat yield using remotely sensed, soil chemical data and machine learning approaches. Comput Electron Agr. 2022, 197, 106978. https://doi.org/10.1016/j.compag.2022.106978.
3. Lu, Q.K.; Tian, S.; Wei, L.F. Digital mapping of soil pH and carbonates at the European scale using environmental variables and machine learning. Sci. Total Environ. 2023, 856(2), 159171. https://doi.org/10.1016/j.scitotenv.2022.159171.
4. Estévez, V.; Mattbäck, S.; Boman, A.; Liwata-Kenttälǎ, P.; Björk, K.M.; Österholm, P. Acid sulfate soil mapping in western Finland: How to work with imbalanced datasets and machine learning. Geoderma. 2024, 447, 116916. https://doi.org/10.1016/j.geoderma.2024.116916.

 

Comment 12:

Line 229, Please elaborate the Delphi method and provide necessary references.

Response：

Thank you for your suggestion. We have added a detailed method description in the revised manuscript (Line 271-279).

The Delphi Method is an expert forecasting method that aims to reach a consensus through the opinions of a group of experts (Mamehpour et al., 2021). ‌ The advantage of Delphi method is that experts can express their opinions independently and anonymously, collect opinions repeatedly through questionnaires, and finally reach a consensus on the problems to be solved (Song et al., 2022; Tang et al., 2023). In this study, Delphi method was adopted to determine the membership degree of the evaluation indicator. We selected seven experts in the field of cultivated land quality (CLQ) evaluation and asked them to independently assess the CLQ evaluation indicator. Finally, the answers of experts were summarized and analyzed, and the membership degree of each evaluation indicator was determined after three feedbacks and corrections.

 

1. Mamehpour, N.; Rezapour, S.; Ghaemian, N. Quantitative assessment of soil quality indices for urban croplands in acalcareous semi-arid ecosystem. Geoderma. 2021, 382, 114781. https://doi.org/10.1016/j.geoderma.2020.114781.
2. Song, W.; Zhang, H.Z.; Zhao, R.; Wu, K.N.; Li, X.J.; Niu, B.B.; Li, J.Y. Study on cultivated land quality evaluation from the perspective of farmland ecosystems. Ecol. Indic. 2022, 139, 108959. https://doi.org/10.1016/j.ecolind.2022.108959.
3. Tang, M.M.; Wang, C.T.; Ying, C.Y.; Mei, S.; Tong, T.; Ma, Y.H.; Wang, Q. Research on cultivated land quality restriction factors based on cultivated land quality level evaluation. Sustainability. 2023, 15, 7567. https://doi.org/10.3390/su15097567.

 

At the same time, to further improve the readability of the manuscript, we invited professional native English speakers to polish the revised manuscript. We have provided the copy of certificate, please see the attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

Comments and Suggestions for Authors

The authors correctly said that there is no consensus on the connotation of CLQ due to the diversity of perspectives on cultivated land worldwide. They made a good connection between ideas in a very well-written introduction.

When they decided to use CLQ parameters and evaluate them at a county level, it meant an important step from a regional to a local approach.

The authors presented an excellent location map. In general, most authors do not properly characterize the study area. As many readers are from outside China, they cannot understand the location. However, the authors made a very good job presenting the study area in a high level of details.

Figures are okay, and the technology roadmap is easy to understand.

 

The study is well-written and well-designed. The study supports the environmental management of land areas, and their methods can be used in other regions worldwide.

Author Response

We thank editor and reviewers for their valuable remarks and suggestions. We have revised the manuscript thoroughly by the effort contributed by all co-authors. Below we list all the comments of the reviewers followed by our answers. You will see that we have done our best to improve all the points that have been raised. All the lines indicated below are showed in the revised manuscript with red marked.

 

Comments from Reviewer #4

Comment:

The authors correctly said that there is no consensus on the connotation of CLQ due to the diversity of perspectives on cultivated land worldwide. They made a good connection between ideas in a very well-written introduction.

When they decided to use CLQ parameters and evaluate them at a county level, it meant an important step from a regional to a local approach.

The authors presented an excellent location map. In general, most authors do not properly characterize the study area. As many readers are from outside China, they cannot understand the location. However, the authors made a very good job presenting the study area in a high level of details.

Figures are okay, and the technology roadmap is easy to understand.

The study is well-written and well-designed. The study supports the environmental management of land areas, and their methods can be used in other regions worldwide.

Response：

We really appreciate for your support and affirmation of this research. According to the suggestions of editor and other reviewers, we have tried our best to further improve the manuscript. We believe that the revised manuscript will be more qualified for publication.

Author Response File: Author Response.pdf

Reviewer 5 Report

Comments and Suggestions for Authors

Please see document attached.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

English is mostly okay, with a few things that need to be changed as mentioned in the document attached.

Author Response

We thank editor and reviewers for their valuable remarks and suggestions. We have revised the manuscript thoroughly by the effort contributed by all co-authors. Below we list all the comments of the reviewers followed by our answers. You will see that we have done our best to improve all the points that have been raised. All the lines indicated below are showed in the revised manuscript with red marked.

 

Comments from Reviewer #5

In the paper titled “County-level cultivated land quality evaluation using multi- temporal remote sensing and machine learning models: From the perspective of national standard” the authors used time series remotely sensed data along with three machine learning models to evaluate the quality of cultivated land in Jimo district of Shandong Province in China. The data sources are clear, the methods are well explained, and the figures are okay. The Conclusion section could be expanded a bit more to highlight the novel information that the study found. Overall, the topic is interesting and the paper is well-written and would be suitable for publication following a minor revision.

Comment 1:

Line 23: Goals is plural but then only one goal is listed. So authors should say one of the SDGs and

list the goal.

Response：

Thank you for your good advice. In the revised manuscript, we have made modifications according to your suggestions (Line 23).

Comment 2:

Line 29: Sentence is very long, consider splitting it into two sentences.

Response：

Thanks for your useful suggestion. To improve the readability of the manuscript, we have divided the longer sentence into two shorter sentences (Line 29-32).

 

Comment 3:

Line 55: is the fundamental what? Do the authors intend to say fundament?

Response：

Thank you so much for your reminding. We have revised "fundamental" to "fundament" in the revised manuscript (Line 56).

 

Comment 4:

Paragraph that starts on line 46, CLQ is repeated a lot, can the paragraph be rewritten so that there

is less repetition?

Response：

Thanks for your useful suggestion. We have rewritten the whole paragraph to reduce repetition. The number of "CLQ" has been reduced from eight to four in the revised manuscript (Line 47-61).

 

Comment 5:

Line 73: “the evaluation technical were not uniform.” This is not proper English, did the author mean

to say technique?

Response：

Thank you so much for your reminding. We have revised "technical" to "techniques" in the revised manuscript (Line 74).

 

Comment 6:

Line 277: add space

Response：

Thank you so much for your reminding. We have added space in the revised manuscript (Line 327).

 

Comment 7:

English is mostly okay, with a few things that need to be changed as mentioned in the document attached.

Response：

We really appreciate for your support and affirmation of this research. According to the suggestions of editor and other reviewers, we have tried our best to improve the manuscript. We believe that the small things you mentioned have been corrected in the revised manuscript.

To further improve the readability of the manuscript, we invited professional native English speakers to polish the revised manuscript. We have provided the copy of certificate, please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

The article has been revised accordingly based on the feedback from the reviewers, and I recommend accepting the paper.

Reviewer 3 Report

Comments and Suggestions for Authors

The authors have addressed all my concerns. The paper can be considered for publicaiton in the present format.