Identifying and Monitoring Gardens in Urban Areas Using Aerial and Satellite Imagery

Round 1

Reviewer 1 Report

The submitted manuscript is good and found to be accepted without any comments

Author Response

Dear reviewer,

Thank you for your time and positive feedback

Best regards,

Authors

Reviewer 2 Report

The manuscript titled as "Identifying and Monitoring Gardens in Urban Areas Using Aerial and Satellite Imagery" is well written and described. Author attempted to figure out the region for gardening by using Satellite images. The objectives of the work have been successfully achieved and the readability of the manuscript is further improved after the inclusion of following comments:

1. Introduction section is well written and also combined with major related studies. At the end of this section, author has to include their contribution.

2. Abstract section is very lengthy, so rewrite it and include only required information.

3. Author has to perform more literature study and present it in a separate section if possible.

4. In methodology section, author had used machine learning algorithm for classification process. For each classifier, kindly mention the used parameter value like optimum value of 'k' for knn classifier, optimized parameters value for SVM and so on.

5. In result section, author have to present a comparative analysis of current work with recently published work.

6. In literature there are so many study reported better accuracy than the current work. So author has to justify the novelty behind the present study.

7. Minor language polishing required.

 

Minor revision required.

Author Response

Dear reviewer,

We thank you for your time and useful suggestions that helped us improve our manuscript further. We addressed all your comments and highlighted the changes.

Thank you!

Best regards,

Authors

 

The reviewers' comments:

Reviewer 2:

The manuscript titled as "Identifying and Monitoring Gardens in Urban Areas Using Aerial and Satellite Imagery" is well written and described. Author attempted to figure out the region for gardening by using Satellite images. The objectives of the work have been successfully achieved and the readability of the manuscript is further improved after the inclusion of following comments:

 

1) Introduction section is well written and also combined with major related studies. At the end of this section, author has to include their contribution.

Authors: Contribution section was added in the introduction:

"The main contributions of this study can be primarily expressed in four aspects: 1) In the current research, the fusion of Sentinel-2 images and RGB aerial images is used, which makes it possible to obtain images with high spatial and spectral resolution. Many studies have been done on the fusion of Landsat 8 images, but the number of studies on the fusion of aerial images and Sentinel-2 is limited, and the use of aerial imaging is much less expensive than UAV; 2) The land cover of gardens and crops are very similar to each other and in most studies they put these two in the same category, but in this research, gardens are separated and the effect of adding NDVI images obtained from fusion, DSM to aerial images for Increased accuracy was investigated; 3) The numbers and locations of the buildings created after the destruction of the gardens were determined, while in previous studies only the percentage of changes in use was calculated. 4) LST variations as a result of the changes in the land cover in gardens and destruction of gardens are investigated, while in former studies, LST changes resulting from the total change in land cover in the city have been investigated. This study only focuses on the destruction of gardens and its consequences on the fragile ecosystem of dry areas."

 

2) Abstract section is very lengthy, so rewrite it and include only required information.

Authors: The abstract was rewritten and written more concisely, the number of words decreased from 374 to 314.

"In dry regions, gardens and trees within the urban space, are of considerable significance. These coverages are facing harsh weather conditions and environmental stresses, on the other hand, due to the high value of land in urban areas, they are constantly subject to destruction and land use change. Therefore, identifying and monitoring of gardens in urban areas in dry regions and impact of gardens on the ecosystem are the aims of this study. The data utilized are aerial and Sentinel-2 images (2018 - 2022) for Yazd Township in Iran. Several satellite and aerial image fusion methods were employed and compared. The root mean square error (RMSE) of horizontal shortcut connections (HSC) and color normalized (CN) were the highest among other methods with values of 18.37 and 17.5, respectively, while Ehlers method showed the highest accuracy with RMSE value of 12.3. Then, the normalized difference vegetation index (NDVI) was calculated using the images with 15 cm spatial resolution retrieved from the fusion. Aerial images were classified by NDVI and digital surface model (DSM) with object oriented methods. Different object-oriented classification methods were investigated, including support vector machine (SVM), Bayes, random forest (RF), and k-nearest neighbor (KNN). The SVM showed the greatest accuracy with overall accuracy (OA) and kappa of 86.2 and 0.89, respectively, followed by RF with OA and Kappa of 83.1 and 0.87, respectively. Separating the gardens using NDVI, DSM, and aerial images of 2018, the images were fused in 2022, and the current status of the gardens and associated changes were classified into completely dried, drying, acceptable, and desirable conditions. It was found that gardens with a small areas were more prone to destruction, and 120 buildings were built in the existing gardens in the region during 2018 - 2022. Moreover, the monitoring of land surface temperature (LST) showed an increase of 14℃ in the areas that were changed from gardens to buildings."

3) Author has to perform more literature study and present it in a separate section if possible.

Authors: A few literature reviews were added according to the reviewer’s comment. The literature review section is given in separate paragraphs in the introduction.

"The results of another research also showed that the fusion of Landsat and UAV data with the Gram-Schmidt method also helps product identification [28]. The results of Zhao’s study [28] not only indicates the possibility of combining satellite images and UAV images for land parcel level crop mapping for fragmented landscapes, but it also implies a potential scheme to exploit optimal choice of spatial resolution in fusing UAV images and Sentinel-2A.

Moltó [31] used Sentinel-2 images, orthophotos and images obtained with drones to generate images with high spatial and spectral resolution. The results showed that the fusion of high-resolution RGI (red, green, infrared) images with Sentinel-2 has the ability to estimate the normalized difference vegetation index (NDVI) with high accuracy.

Phiri et al. [34] reviewed the results of 25 studies comparing Sentinel-2 image classification methods and concluded that the support vector machine (SVM) and Bayes methods have the highest accuracy."

 

4) In methodology section, author had used machine learning algorithm for classification process. For each classifier, kindly mention the used parameter value like optimum value of 'k' for knn classifier, optimized parameters value for SVM and so on.

Authors: In this research, eCognition software was used to classify aerial images using object-oriented methods, and eCognition software has the Nearest Neighbor implemented as a classifier that can be applied using the algorithm classifier (KNN with k=1).

 

5) In result section, author have to present a comparative analysis of current work with recently published work.

Authors: In the discussion section, the results were compared with previous studies and some new comparisons were added.

"Also, the results of the current research are in line with the study of Moltó [31] that used the fusion of RGI high resolution images and Sentinel-2. It is possible to prepare the NDVI with high accuracy and distinguish different land covers because in the current research, the capability of RGB high resolution images in this field was also confirmed.

 

Zhang [129] results showed that spectral information from fusion of multispectral aerial imagery can be used for machine learning-based land cover classification, and among all methods, SVM had the best performance, which confirms the results of the present study."

 

6) In literature there are so many study reported better accuracy than the current work. So author has to justify the novelty behind the present study.

Authors: In the current research, classification was done to separate gardens from agricultural lands and this type of land cover is very similar to each other. Therefore, it is expected to be more accurate in researches that are conducted in order to separate and classify different land covers such as soil and plants.

 

7) Minor language polishing required.

Authors: We carefully proofread the manuscript and corrected all the grammar/typo/style issues that we could find. Thank you!

 

Reviewer 3 Report

The manuscript titled "Identifying and Monitoring Gardens in Urban Areas Using Aerial and Satellite Imagery" presents a study that aims to identify and monitor gardens and trees in urban areas in dry regions, as well as the impact of gardens on the ecosystem of these regions. The data used in the study are aerial and Sentinel-2 images from 2018 to 2022 for Yazd Township in Iran. The manuscript presents a approach to identifying and monitoring gardens in urban areas using aerial and satellite imagery. The use of several satellite and aerial image fusion methods, as well as the application of object-oriented classification methods, adds to the originality of the work. 

 

Some comments:

Introduction: The author should further highlight the research gap of existing research and explain how they are addressing it. While the research gaps are mentioned sporadically throughout the article, it is recommended that the author summarizes and organizes these gaps in the introduction section.

 

Result and Discussion: It is advisable to further subdivide the result section and discussion section into sub-subsections for better organization and clarity.

 

Page 13, Line 457: It would be better to provide explanations on how to determine the NDVI threshold values in table 3.

 

Page 17, Line 551: Modify "examining" to "Examining" for consistency and proper capitalization.

 

Page 18, Line 614: The discussion of the evaluation of classification results for different classifiers could be more in-depth. Instead of simply stating that it is in line with existing research, it could delve into the types of data that the classifiers are more appropriate for. For example, I randomly search a classifier discussion paper on Remote Sensing: Improving Crop Mapping by Using Bidirectional Reflectance Distribution Function (BRDF) Signatures with Google Earth Engine

Author Response

Dear reviewer,

We thank you for your time and useful suggestions that helped us improve our manuscript further. We addressed all your comments and highlighted the changes.

Thank you!

Best regards,

Authors

The reviewer's comments:

Reviewer 3:

The manuscript titled "Identifying and Monitoring Gardens in Urban Areas Using Aerial and Satellite Imagery" presents a study that aims to identify and monitor gardens and trees in urban areas in dry regions, as well as the impact of gardens on the ecosystem of these regions. The data used in the study are aerial and Sentinel-2 images from 2018 to 2022 for Yazd Township in Iran. The manuscript presents a approach to identifying and monitoring gardens in urban areas using aerial and satellite imagery. The use of several satellite and aerial image fusion methods, as well as the application of object-oriented classification methods, adds to the originality of the work.

Some comments:

1) Introduction: The author should further highlight the research gap of existing research and explain how they are addressing it. While the research gaps are mentioned sporadically throughout the article, it is recommended that the author summarizes and organizes these gaps in the introduction section.

Authors: A new section was added to the introduction and the gaps that existed in previous studies and were taken into account in this research were explained

"The main contributions of this study can be primarily expressed in four aspects: 1) In the current research, the fusion of Sentinel-2 images and RGB aerial images is used, which makes it possible to obtain images with high spatial and spectral resolution. Many studies have been done on the fusion of Landsat 8 images, but the number of studies on the fusion of aerial images and Sentinel-2 is limited, and the use of aerial imaging is much less expensive than UAV; 2) The land cover of gardens and crops are very similar to each other and in most studies they put these two in the same category, but in this research, gardens are separated and the effect of adding NDVI images obtained from fusion, DSM to aerial images for Increased accuracy was investigated; 3) The numbers and locations of the buildings created after the destruction of the gardens were determined, while in previous studies only the percentage of changes in use was calculated. 4) LST variations as a result of the changes in the land cover in gardens and destruction of gardens are investigated, while in former studies, LST changes resulting from the total change in land cover in the city have been investigated. This study only focuses on the destruction of gardens and its consequences on the fragile ecosystem of dry areas."

2) Result and Discussion: It is advisable to further subdivide the result section and discussion section into sub-subsections for better organization and clarity.

Authors: The Results and Discussion were given as separate sections. The results section was divided into the following sub-sets:

3.1 Comparison of fusion methods

3.2 Comparison of object-oriented classification methods

3.3 Monitoring the state of vegetation in gardens

3.4 Identification of new constructions in gardens

3.5 Investigating the effect of the garden destruction on the LST

 

3) Page 13, Line 457: It would be better to provide explanations on how to determine the NDVI threshold values in table 3.

Authors: Determining the NDVI threshold was in order to divide the state of trees into four states, which was done by using a review of sources in this field and then a ground visit, an example of which is shown in Figure 9.

4) Page 17, Line 551: Modify "examining" to "Examining" for consistency and proper capitalization.

Authors: It was corrected . Thank you.

5) Page 18, Line 614: The discussion of the evaluation of classification results for different classifiers could be more in-depth. Instead of simply stating that it is in line with existing research, it could delve into the types of data that the classifiers are more appropriate for. For example, I randomly search a classifier discussion paper on Remote Sensing: Improving Crop Mapping by Using Bidirectional Reflectance Distribution Function (BRDF) Signatures with Google Earth Engine

Authors: Thank you for introducing this article. This article was added to the references. In a study previously conducted by the authors, a full explanation of the evaluation of classification results was given. According to the judges, new materials were added to the article in this field.

Aliabad, F. A.; Malamiri, H. R. G.; Shojaei, S.; Sarsangi, A.; Ferreira, C. S. S.; Kalantari, Z. Investigating the Ability to Identify New Constructions in Urban Areas Using Images from Unmanned Aerial Vehicles, Google Earth, and Sentinel-2. Remote Sensing. 2022, 14(13), 3227.

"In the present study, DSM image and NDVI were used to increase the accuracy of aerial image classification. DSM image by adding height information and NDVI by adding spectral information of complications helps to separate garden from agricultural fields. In the classification using the Bayes method, building land cover and bare lands have not been appropriately separated from each other and the roads are not identified at all and the land is classified as buildings; hence from a visual point of view, this method does not have the ability to distinguish different land covers. KNN and RF methods have moderate accuracy and SVM method has better distinguished different land covers. In fact, the SVM outperforms other methods in terms of separation of different land covers, especially roads. The criteria used for evaluation were the overall accuracy and Kappa coefficients. Because it takes into account the agreement that would be predicted by chance, the kappa coefficient is a more reliable indicator than the total accuracy metric."

Reviewer 4 Report

Dear Authors,

As a reviewer I have no objections to your submitted manuscript.

Best regards!

Reviewer.

Author Response

Dear reviewer,

Thank you for your time and positive feedback

Best regards,

Authors