Estimating the Aboveground Biomass of Various Forest Types with High Heterogeneity at the Provincial Scale Based on Multi-Source Data
Round 1
Reviewer 1 Report
Forest biomass is the basis material of forest ecosystem, which plays a vital role in addressing climate change and studying the carbon cycle. The study for four forest types, explored the best model for AGB estimation in large areas with complex geography and high forest heterogeneity. The topic is interesting, I think the following concerns should be addressed before it goes to any future.
(1) This study is based on the accurate classification of different types of forest. If the forest type classification is incorrect, the error in the estimation will be large. Can all types of forests be considered as a whole?
(2) For AGB estimation of forest, whether topographic factors, such as DEM, are taken into account? A large number of studies have shown that topographic correction should be carried out in areas with large topographic relief.
(3) There are so many machine learning models. Is there a better model that the models listed?
(4) here are so many formatting errors, and the language should be improved by a native speaker of English.
Forest biomass is the basis material of forest ecosystem, which plays a vital role in addressing climate change and studying the carbon cycle. The study for four forest types, explored the best model for AGB estimation in large areas with complex geography and high forest heterogeneity. The topic is interesting, I think the following concerns should be addressed before it goes to any future.
(1) This study is based on the accurate classification of different types of forest. If the forest type classification is incorrect, the error in the estimation will be large. Can all types of forests be considered as a whole?
(2) For AGB estimation of forest, whether topographic factors, such as DEM, are taken into account? A large number of studies have shown that topographic correction should be carried out in areas with large topographic relief.
(3) There are so many machine learning models. Is there a better model that the models listed?
(4) There are so many formatting errors, and the language should be improved by a native speaker of English.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 2 Report
Remote sensing estimation of forest aboveground biomass in a high heterogeneity area at a provincal scale using multi-source data: a case study in Yunnan province of China:
· Add/Replace the name of the study area with the Keywords.
· Why didn’t you use more advanced machine learning models like deep learning techniques (e.g., LSTM, CNN, GMDH, etc.)?
· In the last paragraph of the Introduction, the authors should mention the weak point of former works (identification of the gaps) and describe the novelties of the current investigation to justify that the paper deserves to be published in this journal.
· “This may be because the effect of soil on AGB distribution may be limited to forest characteristics, rather than having a larger effect on both woody and non-woody ecosystems.”. Explain.
· Focus on the advantages/disadvantages of the proposed method concerning the obtained results.
· What are the strategies/recommendations to reduce uncertainties in this study?
· How can expand the results to other regions with similar/different climates?
The quality of the language needs to be improved for grammatical style and word use.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
The manuscript, entitled „ Remote sensing estimation of forest aboveground biomass in a high heterogeneity area at a provincal scale using multi-source data: a case study in Yunnan province of China ". The performance of models were different in four forest types: a) The specific model performance in four forest types:RRF was the best both in coniferous forests and mixed forest, R2 and RMSE for coniferous forests were 0.63 and 43.23 Mg /ha, and R2 and RMSE for mixed forest were 0.56 and 47.79 Mg /ha; BRNN was the best in evergreen broad-leaved forests, the R2 was 0.53 and RMSE was 68.16 Mg /ha. There are shortcomings and modifications that should be included in order to enhance the manuscript for the readers.
Abstract :
1- Please add the full name of QRF, BRNN, RRF, GBM, RF and k-NN?
2- Line 27. Type of error should be corrected.
3- The abstract should be shorted and presented only the important results.
Keywords:
4- Keywords should be arranged alphabetic.
Introduction:
5- The introduction was good written but still need to present novelty (originality) of the work? And what is new in your work that makes a difference in the body of knowledge?
Materials and Methods:
6- Figure 3 and table 6 should be added in results section.
Analysis of results and discussion
7- Analysis of results and discussion were good written.
8- Please, write the practical applications of your work in a separate section, before the conclusions.
Conclusion
9- Conclusion should be written again. It is similar to abstract.
10- Please write about the limitations of this work in details in conclusion section.
Moderate editing of English language required
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 4 Report
The title is too long. Please make the title shorter and more informative.
Introduction
The introduction is clear and concise.
Lines 96-97: This sentence is not clear, how is the model uncertainty of the 50%?
Study area and materials
*All the acronyms of the ML algorithms must be defined.
*Check spacing between words and parentheses, e.g. DVI(Difference...)
*Figure 2: What did the p-values refer to? Do you work with outliers? Figure 2 is not necessary, since the information is better presented in Table 3.
*Use Mg ha-1 instead of Mg/ha
Methods
Line 294 Decision coefficient?
Analysis of results
Correct and very clear analysis. I am struck by the low values of R2
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
After read the revised MS and the response letter, I think the paper can be accepted after minor language corrections.
There are some grammar errors, and the language should be improved by a native speaker of English.
Author Response
Please see the attachment.
Reviewer 2 Report
I appreciate the authors addressing the comments. The manuscript can be accepted in its current form. Congrats!
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
The authors did significant improvment acording to my comments. It can be accepted for publication.
Author Response
Please see the attachment.
Author Response File: Author Response.docx