Application of the k-Prototype Clustering Approach for the Definition of Geostatistical Estimation Domains
Round 1
Reviewer 1 Report
This paper applies the k-prototype clustering method to the geostatistical estimation domain definition. Extensive analysis is performed. My major comments are as follows.
1. The K-prototype is not a state-of-the-art method. There have been plenty of clustering methods proposed that could handle category data. Reasons for using this method should be provided.
2. The 3-D figures are not easy to follow. Maybe the authors could provide the views from different sides to show the characteristics.
3. In the case study, it is better to present the k-prototype results first and then discuss whether the results follow the observations. The authors introduce too much about the correlation between variables. It is distractive. These analyses should be used to validate the K-prototype results. The case study section could be improved.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
I consider that the manuscript describes a very interesting proposal, I have no problem accepting it
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
The paper entitled 'Application of the k-prototype clustering approach for the definition of geostatistical estimation domains' proposes the use of the k-prototype algorithm to define the assessment domain that meets the principles of geostatistical assessment. I believe the structure of the article is appropriate, the literature review is comprehensive, and the conclusions are supported by research. My biggest caveat to the work, however, is the level of innovation - the authors applied a well-known method to a practical problem, and it was proven to be usable (however, the purpose of the Special Issue was to show the practical application of the optimization method, which I believe has been achieved). I also thnik that the current version of the work lacks the pseudocode of the method used and information on how the prototypes of each cluster were determined at the beginning phase of the algorithm.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 3 Report
My comments have been taken into account, therefore I recommend accepting the paper.
