Next Article in Journal
CNN-Based Tree Species Classification Using High Resolution RGB Image Data from Automated UAV Observations
Previous Article in Journal
Nocturnal Surface Urban Heat Island over Greater Cairo: Spatial Morphology, Temporal Trends and Links to Land-Atmosphere Influences
 
 
Article
Peer-Review Record

Modeling Bidirectional Polarization Distribution Function of Land Surfaces Using Machine Learning Techniques

Remote Sens. 2020, 12(23), 3891; https://doi.org/10.3390/rs12233891
by Siyuan Liu 1, Yi Lin 1, Lei Yan 1,2 and Bin Yang 3,*
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Remote Sens. 2020, 12(23), 3891; https://doi.org/10.3390/rs12233891
Submission received: 20 October 2020 / Revised: 23 November 2020 / Accepted: 25 November 2020 / Published: 27 November 2020

Round 1

Reviewer 1 Report

Manuscript summary
I have read with interest the manuscript that addresses the issue of predicting polarized
reflectance using empirical models and machine learning algorithms. The analysis is
comprehensive and the volume of data allows a safe inference on the applicability and
performance of implemented models.
I have some very minor comments that the authors may feel free to address. In particular:
- I would expect to see a correlogram describing the relationships between the variables used
in the study.
- I would also expect to see the variable importances based on random forests for the predictor
variables of the ML models.
- Finally, I would expect to see a model that averages (with equal weights) the predictions of
all models (i.e. empirical and machine learning models). I expect this model to be even more
accurate than single models.

Author Response

Please see the attachment. Thanks.

Author Response File: Author Response.pdf

Reviewer 2 Report

1. The literature review needs to be extended in the Introduction section
2. Please provide the equations used in Random Forest model and give the proper citations for them.
3. Please provide information regarding the software used for each applied model.
4. The readers would be interested in the architecture used in each algorithm to allow them to reproduce the results obtained herein as well as to apply the proposed methodology for other case studies.
5. What the readership of this journal would be interested in is to how to properly apply such algorithms? How to fine-tune such algorithms?
6. The authors are encouraged to:
a. Provide clear description of the architecture of their algorithms, software used, adopted convergence criteria etc.
b. If the above deemed impractical, perhaps the authors would consider providing a prediction tool or attaching the most accurate code/algorithm into the appendix.
7. Please provide several reasons for which your paper deserves to be published in Remote Sensing journal!
8. The language of the manuscript can be refreshed to eliminate minor typos and grammatical errors.

 

Author Response

Please see the attachment. Thanks.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The paper can be accepted in the present form! 

Back to TopTop