Combining Spectral and Textural Information from UAV RGB Images for Leaf Area Index Monitoring in Kiwifruit Orchard
Round 1
Reviewer 1 Report
The paper is focused on testing the different LAI estimation models used for yield estimation and growth of kiwifruit trees in orchard. There was analyzed combination of spectral indices and texture features extracted from UAV RGB images.
- how many samples (kiwi trees) were measured?
-chapter 2.2.2; There is missing parametres of images: flight heights , spatial resolutions (ground sample distance - GSD), type of coordinate system
- Fig. 4, 5, 6; to missing LEGEND; prediction and measured LAI
- to reformulate the title of chapter 4.2, figure 3.2.3 and tables 7, S1-S3
- to unified; texture parameters / texture features
- in the text and tables, small typos are marked (yellow color) in the text
Comments for author File: 
Comments.pdf
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
The topic of this study is intersting and well presented. Here you can find my suggestions:
OVERALL: Please, replace all figures with HD images, and check all sections to fit the template of the Journal. The tables must be reconstructed. Pay extreme attention to Figure 3: Please put the 3 figure in coloumn to enlarge them properly. The font must be adjusted in all figures.
INTRODUCTION: Please, mention in the scientific bakgroundalso some example of UAV-based analysis on the vegetated water ways (i.e., "Lama, G.F.C.; Crimaldi, M.; Pasquino, V.; Padulano, R.; Chirico, G.B. Bulk Drag Predictions of Riparian Arundo donax Stands through UAV-Acquired Multispectral Images. Water 2021, 13, 1333, https://doi.org/10.3390/w13101333).
Taddia, Y., Russo, P., Lovo, S. et al. Multispectral UAV monitoring of submerged seaweed in shallow water. Appl Geomat 12, 19–34 (2020). https://doi.org/10.1007/s12518-019-00270-x
Fernández-Lozano, J.; Sanz-Ablanedo, E. Unraveling the Morphological Constraints on Roman Gold Mining Hydraulic Infrastructure in NW Spain. A UAV-Derived Photogrammetric and Multispectral Approach. Remote Sens. 2021, 13, 291. https://doi.org/10.3390/rs13020291
METHODOLOGY: Please use some figures to improve the clarity of the methods proposed for all parameters analyzed in your work. This is crucial for guiding the reader carefully. Otherwise, the scientific quality of your work is poor.
RESULTS: Please, improve the quality of Figure 7, following the same indications of Figure 3.
I will reconsider the article after major revision.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
In this article, the authors proposed a method to combine the spectral and textual information from UAV RGB images for leaf area index monitoring. Concerning this study, high-resolution UAV images of three growth stages of kiwifruit 15 orchard were acquired from May to July 2021. The extracted significantly correlated spectral and 16 textural parameters were used to construct univariate and multivariate regression models with LAI 17 measured for corresponding growth stages. The optimal model was selected for LAI estimation and 18 mapping by comparing the stepwise regression (SWR) and random forest regression (RFR).
Overall, this paper is well written.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
The overall quality of the manuscript has been highly improved in all sections. Just very little comments can be sugested.
- INTRODUCTION: Please, consider in the scientific background of your study, also some applications of machine learning apporaches in agricultural and geoscience research (
Benos, L.; Tagarakis, A.C.; Dolias, G.; Berruto, R.; Kateris, D.; Bochtis, D. Machine Learning in Agriculture: A Comprehensive Updated Review. Sensors 2021, 21, 3758. https://doi.org/10.3390/s21113758.
Sadeghifar, T.; Lama, G.F.C.; Sihag, P.; Bayram, A.; Kisi, O. Wave height predictions in complex sea flows through soft computing models: Case study of Persian gulf. Ocean Eng. 2022, 245, 110467, https://doi.org/10.1016/j.oceaneng.2021.110467.
Hashim, W.; Eng, L.S.; Alkawsi, G.; Ismail, R.; Alkahtani, A.A.; Dzulkifly, S.; Baashar, Y.; Hussain, A. A Hybrid Vegetation Detection Framework: Integrating Vegetation Indices and Convolutional Neural Network. Symmetry 2021, 13, 2190. https://doi.org/10.3390/sym13112190 ).
After these corrections I will accept the manuscript for publication.
Author Response
Response : We appreciate the reviewer’s recommendation and thank for pointing out the quality of our study and critical comments for this manuscript. We have made corresponding modifications to the manuscript, and we believe that the revised manuscript has reached the level of publication.
We thank the suggestion of the reviewer. The revised parts are marked in red accordingly. Please see the introduction on Page 2 of the revised manuscript. Please see the revised parts are marked in red, which we wish to get your approval.
