Application of Neural Network Models and ANFIS for Water Level Forecasting of the Salve Faccha Dam in the Andean Zone in Northern Ecuador

Round 1

Reviewer 1 Report

The paper is interesting and well written. Methodology and results are consistent.  I only  suggest to redraw figure 5 and 6 which have labels out of the range.  In conclusion paragraph I would add a sentence to remark why form a point of view of  basin characteristic rainfall is not a necessary predictors.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

The article is interesting and refers to the increasingly popular topic of modeling hydrological processes.

However, it requires some revisions before publication.

The paper concludes that precipitation was not a factor in predicting reservoir water levels.

In my opinion, this is the result of an error adopted at the methodological stage. The precipitation station is located in one (the smallest) of the six catchments. So the inflow to the reservoir is from a much larger area.

Moreover, what is the retention role of the lakes that are located in catchment areas 1 and 2 ? (missing from Figure 1)

According to the scheme (Figure 1), there is probably another (7?) catchment area missing in the northeastern part that reaches the reservoir directly. Such a situation enlarges the drainage area of the reservoir, which further influences the course of water levels. Please explain it.

It would be more reliable to analyze water flows than precipitation-which is subject to evaporation and retention.

The authors state that neural networks are intended to assist reservoir operators.

Why have other methods of modeling water levels not been considered in this context? Please refer to the publication: "Lake water-level fluctuation forecasting using machine learning models: a systematic review", Environmental Science and Pollution Research, 2020

Please reformat the text: no chapter Discussion

Figure 1: Leyend (?)

Figure 6: Different font size (axis description)

Figure 8: a) A), b) B)

Table 3. Performance

Figure 9. Precipitation

References: according to the journal's scheme, the numbering should not have square brackets.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

This is my second review of this article.

The authors have made the necessary corrections and in places debatable, answered the doubts in detail. 

I recommend the article for publication.