Cloud-Based Machine Learning for Flood Policy Recommendations in Makassar City, Indonesia

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

General comments

 Floods are the leading cause of natural disaster losses. Globally, some countries are more prone to flooding than others. One region that is particularly prone to frequent and severe natural disasters due to flooding is South East Asia. The Association of Southeast Asian Nations includes Cambodia, Laos, Thailand, Vietnam, Brunei, Malaysia, Indonesia, the Philippines, Singapore and Myanmar. Among these countries, Indonesia is the fourth most flood-prone country in the world and the first most flood-prone country in Southeast Asia. Several cities in Indonesia are prone to flooding. One of these is Makassar City, an industrial city and port city in eastern Indonesia and the capital and largest city of South Sulawesi province. The city of Makassar experiences at least one flood a year. The development of a long-term resilience plan is a prerequisite for the mitigating of the effects of flooding. The main approach that a city can take to assess flood risk is to map areas that are susceptible to flooding based on their geography and the comprehensive flood risk assessment. The article focuses its interest on a holistic approach for a comprehensive understanding of the impacts of flooding, including the physical and economic dimensions of the problem. Although the study area is a large city (Makassar) in Indonesia, the methodology used by the authors can be a motivation for studies in other flood-prone regions of the world. Consequently, the subject of the study is interesting, and it is relevant to other countries with flood-prone regions. However, the manuscript is not well written. It needs sufficient work to be publishable. Therefore, I recommend acceptance of the manuscript after major revisions. For details please, see the comments below.

 1.        The manuscript must be written according to the Instructions for Authors of the Journal. See website for details https://www.mdpi.com/journal/water/instructions and also, the “Reference List and Citations Style Guide for MDPI Journals” at the website: https://www.mdpi.com/authors/references.

2.        References are not in the correct format for this journal.

3.        For documents co-authored by a large number of persons (more than 10 authors), you can either cite all authors, or cite the first ten authors, then add a semicolon and add ‘et al.’ at the end.

4.        A general check of the references is needed (References list).

5.        English needs quite a bit of work, both in grammar and in wording. Perhaps working with an independent English-speaking scholar would help in the improving of the text.

6.        I suggest the authors adopt the globally accepted terms of "flood map" and "inundation map".

7.        The abstract is not well written. It needs to be reworded, made more coherent and include the objectives of the research, the main results obtained and the main conclusions drawn. In the present case, there is some confusion about what exactly the study is trying to do.

8.        According to the journal's instructions for authors, three to ten relevant keywords must be added after the abstract. These keywords must be specific to the article, but reasonably common within the discipline. My suggestion to authors is that they should try to revise the keywords in their manuscript. I kindly propose as keywords: Flood Policy; Flood Map; Inundation map; Makassar city, Indonesia; (add more keywords).

9.        I think that the manuscript would become more interesting for the international reader if it included a chapter on the measures taken so far by the local government of Makassar City or the central government of the country to prevent flooding problems and the weaknesses in their implementation.

10.    In the abstract, the authors use the term "Indonesian tropical cities" (Line 25). But then they do not use the term again in the main text, nor do they explain what it means. I think the authors should help the international reader to understand who these cities are and what makes them different from the rest of the country's cities.

11.    Introduction is weak and needs improvement. In particular, it should (a) place the study in a broader context and emphasize why it is important, (b) describe its objectives, (c) define the purpose of the study and its significance, (d) carefully examine the current state of the research field and the main publications cited, (e) summarize the main objective of the study, and finally, (f) highlight the main conclusions. In the present case the object of the study is obscure. For example, the authors state elsewhere that “The research aims to quantify the affected area, identify the predominant inundated land cover, and assess the efficiency of Makassar's drainage system and urban land use plan (Lines 30+31), elsewhere that “The main objective of this study is to measure the actual flood-inundated area and promote a policy recommendation (Lines 61+62) and elsewhere that “The study focused on assessing the flood-prone areas in Makassar during the February monsoonal flood using machine learning tools”. Please give a precise definition of the subject of the study.

12.    Moreover, the manuscript must mention similar studies in the study area. In my opinion, the authors have to provide an adequate background and have to find and add recent citations. I propose, kindly, the following citations:

(a)    Sudirman; Trisutomo, S.; Barkey, R.A.; Mukti Ali, M. Watershed Identification and its Effect toward Flood (case study: Makassar CITY). Int. J. Adv. Res. 2018, 6(5), 513-519. doi:10.21474/IJAR01/7059.

(b)   Halim, H.; Arifin, A.; Nonci, N.; Zainuddin, R.; Anriani, H.B.; Kamaruddin, S.A. Flood disaster and risk anticipation strategy. IOP Conf. Ser.: Earth Environ. Sci 2019, 235 , 012032. doi:10.1088/1755-1315/235/1/012032.

(c)    Djamaluddin, I; Indrayani, P.; Caronge, M.A. A GIS analysis approach for flood vulnerability and risk assessment index models at sub-district scale. IOP Conf. Ser.: Earth Environ. Sci. 2020 ,419, 012019. doi:10.1088/1755-1315/419/1/012019

(d)   Indrayani, P.; Djamaluddin, I.; Cai, Y. Employing a local framework and GIS to evaluate the flood risk index maps of Makassar City, Indonesia. Arab J Geosci 2023, 16, 568. doi:10.1007/s12517-023-11664-y

13.    Figure 1. In higher analysis.

14.    Figures 2 and 7 are not easy to understand. The sub-district names are hard to read.

15.    Figure 3. Please delete "Flood and drainage" at the top of the figure. This is not necessary.

16.    Figure 4 – x-axis: “Flooded area Km²” should be “Flooded area (Km²)”

17.    Figure 5 – y-axis: “Slope (degree)” should be “Slope (⁰)”

COMMENT: In the SI system, the unit for measuring angles is degrees. Its symbol is "⁰".

 

Specific comments

 

Line 59

Clarify the term “actual flood inundation area”. What does it mean?

Line 104

“Fig.1.” should be “Figure 1”.

Line 114

“The VV polarization….”

should be

“The Vertical Transmit-Vertical Receive Polarisation (VV)….”

Lines 154 – 158

“To validate the flood distribution predictions generated by machine learning algorithms, a comprehensive approach was taken. This involved interviewing local citizens in flood-prone areas to gather firsthand accounts and utilizing digital platforms to access news reports and social media data related to recent floods. By comparing these real- world observations with the machine-learning predictions, the overall accuracy of the flood models was assessed.”

COMMENT: This part of the main text is very short. It needs more development and more information. Please provide details of the procedure you have followed.

Lines 163 – 164

“Furthermore, the flood area was slightly underestimated, with an accuracy of 91%.”

COMMENT: This sentence is not understood.

Line 168

“….February monsoonal flood.”

should be

“….February 2023 monsoonal flood.”

Lines 180 – 183

The authors state “The resulting amalgamation of data, as illustrated in Figure 2, is an invaluable resource for policymakers, urban planners, and disaster response teams, enabling them to make informed decisions and take proactive measures in mitigating future flood-related crises in Makassar.”

COMMENT: The study is based on only one flood event, that of February 2023. Do the authors believe that a single event is sufficient for policymakers, urban planners, and disaster response teams to arrive at decisions without considering other factors and events?

Lines 185 – 186

“Figure 2. Flood inundation area overlay with a). Drainage b). Land use land cover (LULC) c). Slope 185 d). Elevation.”

COMMENT: This caption is not understood.

Comments on the Quality of English Language

English needs quite a bit of work, both in grammar and in wording. Perhaps working with an independent English-speaking scholar would help in the improving of the text.

Author Response

Dear Reviewer 1

Thank you very much for your time and comments on our manuscript. Please find the revised one, the manuscript has been English proofread by proofreader services

Regards,

Rimba

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

This manuscript lacks a literature review section, which provides limited information about existing studies to support the novelty of this study. For example,

What are the existing studies about flood mapping in this area?

What are the existing studies about the approaches for flood mapping and what are their limitations?

Accordingly, there is no comparison with flood mapping created by other approaches/algorithms, why your algorithms are better than others.

 

In terms of the validation, it is mentioned in section 2.4 that interviewing local citizens and accessing news reports and social media data. However, there are no detailed validation results. How does the map fit to the facts collected?

Comments on the Quality of English Language

no obvious typos or grammar errors.

Author Response

Dear Reviewer 2

 

thank you very much for your time and comments on our manuscript. please find the revised one.

Regards,

Rimba

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

 

General comments

 This is the second time I have reviewed this manuscript. Last time I had found serious problems (see my review report) and had suggested acceptance after major revisions. The authors have accepted all the comments and have made a serious and worthwhile further effort to improve the manuscript considerably. However, further efforts are still needed to make the manuscript suitable for publication. I recommend acceptance of the manuscript after minor revisions. Please, see the comments below.

 Specific comments

 Lines 26 – 28

“Flood policy recommendations should be considered to reduce flood exposure. Examining the flood inundation area would help to provide a suitable flood policy. However, the main obstacle in creating flood maps is the accuracy of flood inundation areas”.

COMMENT: This part of the abstract does not match the rest of the text.

Lines 61 – 62

“Widodo et al. found a high potential risk of flooding due to land use changes in the Makassar neighbourhood region[5]”

should be

“Widodo et al. [5] found a high potential risk of flooding due to land use changes in the Makassar neighbourhood region.”

Lines 62 - 63

“Musliadi et al. modelled the potential flood depth of the Tallo watershed in Makassar using the Log-Pearson type III method on rainfall data[6]”.

should be

“Musliadi et al. [6] modelled the potential flood depth of the Tallo watershed in Makassar using the Log-Pearson type III method on rainfall data”.

Lines 64 – 65

“Thoban and Hizbaron conducted research with the spatial multi-criteria evaluation (SMCE) to find the resilience level of the Makassar community to flooding[7]”.

should be

“Thoban and Hizbaron [7] conducted research with the spatial multi-criteria evaluation (SMCE) to find the resilience level of the Makassar community to flooding”.

Lines 65 – 67

“Djamaluddin et al. and Indrayani et al. predicted flood vulnerability in Makassar City by considering social, physical, economic, and environmental aspects [8,9]”.

should be

“Djamaluddin et al. [8] and Indrayani et al. [9] predicted flood vulnerability in Makassar City by considering social, physical, economic, and environmental aspects”.

Lines 67 – 68

“Sudirman et al. identified the watershed that high probability to flood by considering the surface runoff [10]”.

should be

“Sudirman et al. [10] identified the watershed that high probability to flood by considering the surface runoff”.

Lines 84 – 85

“Mehmood et al. utilised the GEE cloud platform to detect floods by Landsat images [13]”.

should be

“Mehmood et al. [13] utilised the GEE cloud platform to detect floods by Landsat images”.

Lines 88 – 91

“Nghia et al. extracted flood in the downstream Mekong River in Vietnam through SAR images in GEE [15]. Tsuganskaya et al. utilised SAR in the GEE platform to extract flood inundation in the vegetated  area [16].

should be

“Nghia et al. [15] extracted flood in the downstream Mekong River in Vietnam through SAR images in GEE. Tsuganskaya et al. [16] utilised SAR in the GEE platform to extract flood inundation in the vegetated area.

Lines 97 – 101

“Rimba and Miura utilised ALOS Palsar data to detect flood inundation for rapid response to flood disasters in Japan [17], and Tay et al. employed SAR images to detect the impact of typhoons in Japan [18]. Saleh et al. utilised Sentinel-1 SAR imagery to detect flood inundation in Penang [19]. Bernhard employed six years of SAR data to monitor floods in Greece [20]”.

should be

“Rimba and Miura [17] utilised ALOS Palsar data to detect flood inundation for rapid response to flood disasters in Japan, and Tay et al. [18] employed SAR images to detect the impact of typhoons in Japan. Saleh et al. [19] utilised Sentinel-1 SAR imagery to detect flood inundation in Penang. Bernhard [20] employed six years of SAR data to monitor floods in Greece”.

Figure 3 – y-axis

“flood inundation (km²⁾”

should be

“Flood inundation (km²⁾”

Line 289

“…from 0 to 0.3°. A substantial…”

should be

“…from 0° to 0.3°. A substantial…”

Line 291

“…that the 0.2 to 0.3° slope range…”

should be

“…that the 0.2° to 0.3° slope range…”

Line 296

“…within the 0 to 0.3° range…”

should be

“…within the 0° to 0.3° range…”

Figure 6 – y-axis

“flood inundation (km²⁾”

should be

“Flood inundation (km²⁾”

Lines 491 – 492

“Sudirman WATERSHED IDENTIFICATION AND ITS EFFECT TOWARD FLOOD (CASE STUDY: MAKASSAR CITY). Int. J. 491 Adv. Res. 2018, 6, 513–519, doi:10.21474/IJAR01/7059”.

should be

Sudirman; Trisutomo, S.; Barkey, R.A.; Mukti Ali, M. Watershed Identification and its Effect toward Flood (case study: Makassar CITY). Int. J. Adv. Res. 2018, 6(5), 513-519. doi:10.21474/IJAR01/7059.

 

Author Response

Thank you very much for your valuable comments to improve the quality of our paper. We have revised the manuscript accordingly to your valuable inputs. Please refer to the table to find the changes, the revised version is denoted as red fonts.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

all questions were addressed. Thanks.

Author Response

Thank you very much for your valuable comments to improve the quality of our paper.