Linking Hydraulic Modeling with a Machine Learning Approach for Extreme Flood Prediction and Response

Round 1

Reviewer 1 Report

Please find the comments in the attached file.

Comments for author File: Comments.pdf

Author Response

Please check attached file.

Author Response File: Author Response.docx

Reviewer 2 Report

Floods are among the most harmful natural catastrophes in the world, often resulting in loss of human lives and properties. The Emergency Action Plan (EAP) is extremely important for areas prone to floods. However, the construction of flood maps and accordingly the EAP is time consuming using conventional methods. To obtain more effective flood maps, novel methods with better ability are desired. The author proposed an approach to linking hydraulic modeling with random forest for extreme flood prediction and response. This paper is technically sound, and the methods, analyses and results are clearly presented. I recommend acceptance of this paper.

Author Response

Thanks for your review our paper!

Reviewer 3 Report

Thanks this was an interesting paper and an important topic.  many studies are done on flood mapping, but few look at issues and downstream impact of structure failures. 

Table 2, it's not clear to me why  3 row's have yellow highlight, reservoir water levels: 35.24, 47.78, 53.35

Section 4.2- flood map generation, what is the advantage of taking the cross sectional DSMBRK simulation results to create TIN then DEM for max WSE. Why not a spline or kriging interpolation since you are essentially creating a water surface?

in your flood map prediction, did you try to predict a flood map of a known return period and compare your prediction to the output from HEC-1?

Flood Hazard calculation - how did you assign population into the grid units? 

Author Response

Please check attached file.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

2. What is the definition of extreme flooding in your study area?

▶ The extreme flooding in this study affects the whole Seoul city. And, the dam inflow used in this study was estimated based on the assumption of extreme rainfall in upstream basin. The floods due to discharge or break of dam are generally significantly larger than natural flood. Because, the unexpected peak flow and high velocity of flood wave could be shown in floods that caused by dam operation or collapse.

You should add something in your paper to provide information for readers, not only for reviewers.

 

(In Sec. 5.2.) “Because the design of levee in Seoul city was conducted based on flood of 200 year return period, flood risk analysis was performed based on the flood of 200~ 4000 year return periods and PMF (dam-break) condition.”

Please consider you above sentence, 4000 years is too long.

 

I hope you can add a discussion part to present the following information (not only write to me !). In discussion part, you can compare your study with other previous studies even though it is different study area.

Existing studies appear to have performed flood susceptibility analysis by using various socio-economic factors and topographic factors. However, in this study, flood vulnerability is obtained by simply overlapping data on accessibility of population, hospitals and fire departments based on a rapidly predicted flood map. Although it is relatively simple method, it has the advantage of quickly determining the risk of flooding in emergency situations. In this study, a numerical analysis model is essential because basic learning data are required for flood prediction.

 

In order to apply this technique to other watersheds, accurate stream cross-section data are required to perform the DAMBRK simulation. The enough topographic data is also needed for drawing flood map with GIS program. For flood risk analysis, the population data, other data that can affect flood response are also required.

 

Move this part to discussion section

“(5) Existing method could consume a lot of time for showing flood map with consideration of dam operation or collapse. The technique proposed in this paper has the advantage of displaying a flood map faster than the previous method that using GIS program. However, there is a disadvantage that it is necessary to build a database for various flood scenarios for this purpose. This shortcoming can be solved through data processing automation that can quickly build a flood database. In addition, unlike previous studies, this study not only displays a flood map, but also presents a flood risk level by using flood maps that rapidly generated, population, and accessibility to hospitals and fire stations data. The result of flood risk analysis in district units will be used in extreme flood situation in Seoul city.”

Author Response

please check attached file.

Author Response File: Author Response.docx

Round 3

Reviewer 1 Report

The authors have substantially improved the manuscript.

The manuscript can be accepted after authors revise something in Discussion part.

 In this part, authors should cite some published works to strengthen their sentences.

For example: "Existing method could consume a lot of time for showing flood map with consideration of dam operation or collapse (cite some published papers here)."

Author Response

Please check attached file. 

Thank you.

Author Response File: Author Response.docx