Next Article in Journal
6G Cognitive Information Theory: A Mailbox Perspective
Next Article in Special Issue
Prediction of Cloud Fractional Cover Using Machine Learning
Previous Article in Journal
Effects of Neuro-Cognitive Load on Learning Transfer Using a Virtual Reality-Based Driving System
Previous Article in Special Issue
Event Detection in Wikipedia Edit History Improved by Documents Web Based Automatic Assessment
 
 
Article
Peer-Review Record

Unraveling the Impact of Land Cover Changes on Climate Using Machine Learning and Explainable Artificial Intelligence

Big Data Cogn. Comput. 2021, 5(4), 55; https://doi.org/10.3390/bdcc5040055
by Anastasiia Kolevatova 1, Michael A. Riegler 2,3, Francesco Cherubini 4, Xiangping Hu 4 and Hugo L. Hammer 3,5,*
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Big Data Cogn. Comput. 2021, 5(4), 55; https://doi.org/10.3390/bdcc5040055
Submission received: 30 August 2021 / Revised: 30 September 2021 / Accepted: 8 October 2021 / Published: 15 October 2021
(This article belongs to the Special Issue Multimedia Systems for Multimedia Big Data)

Round 1

Reviewer 1 Report

Thank you for the opportunity of learning your work. Generally, your paper is well structured to follow and represents well the ML model’s performance to describe the relationship between the temperature and LC changes. Here are a few points to be answered and improved.

  • Page 2, Introduction, last paragraph AND in Table 2: If any multicollinearity exists between your variables? This issue affects the accuracy of the prediction for some of the models that the authors used in Table 2.
  • Page 3, section 2-1: How the LC aggregation process is done? Is a unique LC assigned to each cell in ML models? Adding more details about the aggregation process is suggested
  • Page 3, section 2-2: Adding more details about the climate modeling process, which is only constrained to the LC is highly recommended. 

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

The manuscript, entitled "Unraveling the Impact of Land Cover Changes on Climate using Machine Learning and Explainable Artificial Intelligence" (by Kolevatova, A. et al.) tested four different machine learning methods (SVR, RF, MLR and LASSO) to evaluate the impact of Land Cover (LC) changes on temperature. This relationship was further analyzed by the “optimal” (among the applied four) ML method and explainable artificial intelligence (XAI).

General remarks

The manuscript deals with a topic of international interest. The applied methodologies and output results are certainly valuable. However, I find the structure and the content of the manuscript being not acceptable. I would like to justify my decision by revealing indicatively two (among others) key points which are not satisfied by this study:

First of all, the theoretical backgrounds of applied ML methods and XAI approach are totally missing. This lack contributes to high difficulty in understanding by readers, especially those not being too familiar to the specific methodologies.

In addition, there are neither relevant “Results” and “Discussion” sections, nor some relevant paragraphs providing the presentation and the interpretation of produced results. The authors just preferred to highlight comparatively the results of other previous similar studies!

And as a comment of minor significance; the absence of line numbers in submitted manuscripts makes difficult the task of reviewing!

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

 

Round 2

Reviewer 2 Report

Thank you for taking into your account my reviewing suggestions/comments. The significant improvement of the manuscript as a result of revision procedure enables me to change totally my initial decision. Hence, I recommend the acceptance of your manuscript in order to be published.

Back to TopTop