Analysis of the Driving Force of Land Use Change Based on Geographic Detection and Simulation of Future Land Use Scenarios
Round 1
Reviewer 1 Report
Comments for author File: 
Comments.pdf
Author Response
Dear reviewer,
Thank you for your precious comments and advice. 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 have studied comments carefully and have made correction which we hope meet with approval.
The main corrections in the paper and the responds to the reviewer’s comments are as flowing:
Abstract:
Point 1: "land use land cover change" (LULCC) is widely used in such studies, therefore, I suggest you using LULCC instead of "LUCC" throughout the manuscript including the keywords.
Response : The words have been modified to "LULCC" throughout the manuscript.
Point 2:Line 15: Just "urban expansion" not "urban land expansion" .
Response : "urban land expansion" has been revised" urban expansion".
Point 3: Line 15: It's from "1999" to "2019" not "2009"?
Response : It has been revised to"2019".
Point 4: Line 21: km2 .
Response : Initial manuscript description is unclear. Revised: The areas with a distance < 200 km from the city center.(Line 21).
Point 5: Line 22: km2
Response : Initial manuscript description is unclear. Revised:areas with a distance< 25 km from the railway.
Point 6: Line 27: First time the GD is used here. Please be clear either use Geographic Detection (If that is what you meant) or abbreviate it in the beginning.
Response : Add on line 16"geographic detection(GD)".
Point 7: Line 29: Keywords: please use "LULCC" .
Response : Revised: "Land use and land cover changes".
Introduction:
Point 8:Line 32: I suggest you using LULCC instead of "LUCC" throughout the manuscript.
Response : The words have been modified to "LULCC" throughout the manuscript.
Point 9:Line 46: It's better to use "The use of remote sensing and GIS techniques" instead of "
Response :Revised:"The use of remote sensing and GIS techniques".
Point 10:The use of "remote sensing and GIS mapping" after this statement a couple of references are encouraged,
Response :The manuscript adds one reference.
Point 11:Line 54: Please check the spelling of "modes" it should be "models".
Response :The word has been modified to ”models”.
Point 12:Line 56-60: This sentence is quite long. Please break it down to a couple of sentences.
Response :The long sentence has been revised in line56 -60.
Point 13:Line 71: I suggest saying " Taking Chongqing as a case study" instead of " Taking Chongqing".
Response :The word has been modified to " Taking Chongqing as a case study".
Point 14:Line 71-77: In the methodology section I suppose you have employed Markov chain for the simulation but you have not mentioned here? Please clarify by a sentence.
Response : In the “3.2.1. Research method（line179-183,line206）” section, a detailed description is added.
Markov prediction is a stochastic process. It is a prediction method to predict the change of each time in the future based on the current situation of the event. Markov chain prediction method is suitable for predicting the dynamic change of land use. In this paper, the transfer matrix is calculated based on the land use in 2009 and 2019.And then the amount of land use types in 2029 is predicted based on Markov chain.
Study area:
Point 15:Fig.1 could be represented better. The graticule is unclear either remove it or refine it please. In addition, the scale bar needs refinement.
Response : The picture has been remade.
Material and methods
Point 16:Line 95: More information is required (few sentences) about the three time-period maps (i.e., 1999, 2009 and 2019), for example, their accuracy and mode of production.
Response :In the line106, a detailed description is added.
The LULC data used in this study are mainly derived from the "ESA CCI Land Cover project" and " Year-Based Project for On-Board Autonomy-Vegetation (PROBA-V)", and the resolution of these data is 300 meters. Three LULCC data spanning 20 years (1999, 2009, 2019) were selected for research.
Point 17:Line:98-102: Its unclear whether these factors are pre-processed in this study or they were downloaded as they are ( ready)? Please clarify. For example, the factor "distance from the river". Is this factor downloaded as it is or the river network was downloaded then the Euclidean distance was prepared for the study area?
Response :In the line119-127, a detailed description is added.
The DEM data is derived from GLSDEM (www.gscloud.cn). The SL data is generated based on DEM; The TE data is downloaded from the website and mapped by interpolation method. The DRR data is generated by ArcGIS software based on Euclidean distance and river network set. DC data is also generated by ArcGIS software based on Euclidean distance and urban central point data. DRD is mapped by ArcGIS software based road net-work data and Euclidean distance. DRW is mapped by ArcGIS based on railway network and Euclidean distance. GDP data is downloaded from RESD(www.resdc.cn). Pop data is downloaded directly from Worldpop(www.worldpop.org). The SC density map is generated by ArcGIS software based on point density function.（109-117）.
Point 18:Line 173: " a factor detector method" please just by a sentence mention the method.
Response :In the Line200 and line145, a detailed description is added. Such as :
Secondly, the influence of 10 factors are calculated using a factor detector method[39], which can be used to compare the effects of different factors on land change.
Point 19:Line : 193: Fig.3; the " Markov Chain Analysis (MCA)" is only mentioned in this flowchart? Please clarify in the methodology section how the MCA being used and what it does exactly.
Response :In the "3.2.1.Research method"(line179-183)section, a detailed description is added. And the whole workflow is re described(line198-211). As follows:
Markov prediction is a stochastic process. It is a prediction method to predict the change of each time in the future based on the current situation of the event.Markov prediction method is suitable for predicting the dynamic change of land use。In this paper, the transfer matrix is calculated based on the land use in 2009 and 2019.And then the amount of land use types in 2029 is predicted based on Markov chain........
Results and Discussion
Point 20:Line 200: Figure 4: Adding little more text to this figure describing what is what is appreciated.
Response :Figure 4 is redrawn in order and highlighted by dotted lines.
Point 21:Line235: comment from "Line 200" is also true for Table 2.
Response :Table 2 is redesigned with emphasis.
Point 22:Figure 7: It's not clear why ± sign has been used ?
Response :Figure 7 is redrawn.
In addition
(1)The manuscript adds content on research questions in line 65-74。
(2)The manuscript redraws the flow chart (Figure3.) and detailed description of the workflow (line198-212).
(3)The discussion section added information on the intended use of the proposed method.(Line434-437)
...
Author Response File: 
Author Response.docx
Reviewer 2 Report
This is a well written paper.
Author Response
Dear reviewer,
Thank you for your precious comments and advice.
Reviewer 3 Report
The submitted manuscript, although not completely novel, fits the scope of the journal. However, major revision before publication is needed. The methodology is incomplete: there are missing research questions or hypotheses, and proposed procedures and methods are not appropriately elaborated.
The results and discussion sections are rather minimal and must be improved – the results should be based on the scientific findings (why do you propose the government to restrict the development of urban land and how your findings are connected to rational social and economic development?). There are a lot of figures which are almost not discussed at all. Some of them need to be improved: there are some figures which would be more suitable if there are side-by-side comparisons by years. The tables contain a lot of typos, they need to be corrected (e.g. Table 2 – missing “L”). The simulated predictions areas should be stated in square kilometres instead of pixels? The discussion section should include the intended use of the proposed method, indicating the scenarios of using it in real-life scenarios.
Author Response
Dear reviewer,
Thank you for your precious comments and advice. 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 have studied comments carefully and have made correction which we hope meet with approval.
The main corrections in the paper and the responds to the reviewer’s comments are as flowing:
Point 1:The submitted manuscript, although not completely novel, fits the scope of the journal. However, major revision before publication is needed. The methodology is incomplete: there are missing research questions or hypotheses, and proposed procedures and methods are not appropriately elaborated.：
Response 1：
(1)The manuscript adds content on research questions in line 65-74.
Although CA model solves the problem that the interaction of geographical phenomena in spatial proximity cannot be simulated, two limitations exist in the current LULCC simulation models: 1) Most of LULCC models train and estimate the conversion probabilities of each land use type independently, resulting in a separation between the different land use types. The interactions are not well explored in these models. 2) The calculation parameters of the CA model have modeling uncertainty [20,21].Many kinds of evaluation factors are necessary for CA simulation. Too many factors may have multicollinearity and not been objectively evaluated, resulting in low accuracy of evaluation results or simulation results. [22,23]. Therefore, factor selection is the key to constructing an effective CA model [24-27].
(2)The manuscript revised the description of the research method in line 75-88.
In this paper, we present a method different from existing method: its advantage is that it can objectively evaluate the driving factors, and can carefully design the interaction and competition between different land use types. In the proposed model, firstly, we incorporated natural, environmental factors and socio-economic developments into the models. Secondly, it is objective to choose which factors as evaluation factors based on mathematical methods. Thirdly, the Artificial Neural Network(ANN) is designed to ad-dress the complex local land use interactions and estimate the transition probabilities of different land use types. Taking Chongqing as a case study, as the fourth municipality under the direct jurisdiction of the central government of China, this paper uses the geographic detector technique to study and select the factors affecting land cover change , then uses the CA model and selects the artificial neural network as its conversion rule[28]. Following this method, a simulation model of land use change in Chongqing is developed. The results can be used to provide a scientific basis for the sustainable development and utilization of local land resources and the decision-making of government bodies.
(3)The manuscript redraws the flow chart (Figure3.) and detailed description of the workflow (line198-212).
Firstly, a grid map of each factor is generated using ArcGIS software. For example: DRD is mapped by ArcGIS software based road network data and Euclidean distance.
Secondly, the influence of 10 factors are calculated using a factor detector method[39], which can be used to compare the effects of different factors on land change. And then the factors with a value > 0.5 are selected as the factors of the ANN-CA model.
Thirdly, the parameters of the model are calculated by training ANN based on random samples. In each cycle, the conversion probability of land use corresponding to each grid unit is automatically calculated by the neurons of the output layer. Then the amount of future land use is calculated by Markov chain, which has been successfully employed by many studies.
Finally, the future land use scenario is simulated by the selected factors, conversion matrix and future pixel amount. The LULCC of Chongqing in 2019 was simulated by ANN-CA based on the LULCC of 2009 as the initial state. When the simulation results of 2019 were correctly modeled, then LULCC in 2029 is simulated based on the LULCC in 2019.
Point 2:The results and discussion sections are rather minimal and must be improved – the results should be based on the scientific findings (why do you propose the government to restrict the development of urban land and how your findings are connected to rational social and economic development?). There are a lot of figures which are almost not discussed at all. Some of them need to be improved: there are some figures which would be more suitable if there are side-by-side comparisons by years. The tables contain a lot of typos, they need to be corrected (e.g. Table 2 – missing “L”). The simulated predictions areas should be stated in square kilometres instead of pixels? The discussion section should include the intended use of the proposed method, indicating the scenarios of using it in real-life scenarios.
Response2 :
(1)A new description of government restrictions on urban land development has been added to the conclusion, As follows（Line 428-430）
Based on predictions,in the next 10 years, if no restrictions are imposed,the cultivated land in Chongqing will be reduced by 1%, and the increase of urban land will reach a surprising 65% of that in 2019 .
- A new description has been added to the figure in the manuscript.As follows
Line 236-238.:The influence degree of DRW and DRD is about 0.05, which indicates that the influence of different traffic land is almost the same. And DEM has less impact on the growth of urban land, which is 0.04.
Line 284-285. Compared with level 1-2 and level 2-4, this index is at least 0.17 in level 2-4, which is much larger than the level 1-2.
Line 290-294. the index is 0.28 in 2009-2019 and 0.11 in 1999-2009, indicating that the urban land growth is the largest in the area <200km. These areas are mainly located in the suburbs and satellite cities of Chongqing. The rapid urban development occupies a lot of non urban land such as cultivated land and forest land.
Line 325-329. The main rivers in Chongqing are the Jialing, Wujiang, Fujiang , etc. Since most cities are distributed along the river, the urban LULCC is centered on the river and spreads to the surrounding areas. It is found that the biggest impact of rivers on urban land use change is that level 1-2 reached 0.09, and then fell sharply at level 2-4 with an index of 0.03 from Figure 5 in 2009-2019
Line 336-338 It is found from the figure that the DRD impact is almost all in leve1-2, the highest is 0.10, and the impact degree of other levels is almost 0.
.....
(3)Table error has been modified.
(4)The prediction unit and relevant description are changed to square kilometers(Table 4. )(Line 393).
(5)The discussion section added information on the intended use of the proposed method.As follows:
Line434-437:In summary, the proposed model is suitable for analyzing the driving factors of land change and predicting the future land use scenario. The GD-ANN-CA model can not only objectively select evaluation factors, but also be applied to more complex nonlinear systems. This model is especially suitable for land use analysis, ecological evaluation , etc.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
The the quality of the ms has been enhanced quite well. Congratulations!
Reviewer 3 Report
The revised manuscript has been sufficiently improved, I recommend accepting it in its present form.
