1,270
views
0
recommends
+1 Recommend
1 collections
    0
    shares

      UCL Press journals including UCL Open Environment have now moved website.

      You will now find the journal, all publications, reviews and submission information at https://journals.uclpress.co.uk/ucloe

       

      scite_
       
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Multi-Spatiotemporal Analysis of Changes in Mangrove Forests in Palawan, Philippines: Predicting Future Trends Using Support Vector Machine Algorithm and Markov Chain Model

      Preprint
      research-article
      This is not the latest version for this article. If you want to read the latest version, click here.
      Bookmark

            Revision notes

            Really appreciate the reviews of Banashree Thapa and Xiongjie Deng. Your suggestions, recommendations, and feedback are indeed crucially important and helpful toward the success of this publication. The authors will be forever grateful for your valuable contributions. 

            Reviewer: Banashree Thapa

            Reviewer’s Comments/Suggestion (Original Manuscript)

            Text(s) from the Original Manuscript

            Authors’ Responses (Revised Manuscript)

            Line 10: I think the authors meant "titled" not "entitled"

            manuscript entitled “Multi-spatiotemporal Analysis of the Changes…

            Changed as suggested

             

            Line 10

            manuscript entitled “Multi-spatiotemporal Analysis of the Changes…

            Line 16: Mangrove conservation isnt the right term I feel. One can not conserve mangroves using remote sensing, rather study mangroves and thus promote conservation

            Mangrove conservation using remote sensing is not just an interesting research idea…

            Changed the term as suggested

             

            Lines 16-17

             

            Mangrove forest management using remote sensing is not just an interesting research idea…

            Line 124: This sentence can be improved, reflecting the exact reasons why repeated, accurate on-ground sampling exercises cant be done. For instance, talking about the inaccessibility of mangrove forests, distance from monitoring locations etc, cost associated with the field visits and high technical skills required to navigate these ecosystems make in-situ sampling difficult for mangrove forests.

            Mangrove ecosystems form a complex structure, making extensive in-situ sampling difficult to do.

            Re-structured the sentence

             

            Lines 119-121

             

            Mangrove ecosystems form a complex structure (e.g., less accessible Rhizophora’s complex bifurcated and looping root structure) and the technical skills required and cost associated with the forest samplings make extensive in-situ sampling difficult.

            Line 125: If the above suggestions are accepted, then consider changing "however" to "thus"

            However, remote sensing techniques provide a convenient tool…

            Changed as suggested

             

            Line 121

             

            Thus, remote sensing techniques provide a convenient tool…

            Line 136-141: Consider rewording "The mangroves of Palawan have been protected under the direct human inventions through the International Union for Conservation of Nature (IUCN) protected area Category I-IV (Long and Giri 2011) and 1992 Republic Act No.7611, commonly known as the Strategic Environmental Plan for Palawan Act (SEP Law, FAO 2021); yet this unique ecosystem remains under threat due to climate change and associated rising sea levels (Gilman et al. 141 2008; Giri et al. 2011)."

            Additionally, although the mangroves of Palawan have been protected under the direct human inventions through the International Union for Conservation of Nature (IUCN) protected area Category I-IV (Long and Giri 2011) and 1992 Republic Act No.7611, commonly known as the Strategic Environmental Plan for Palawan Act (SEP Law, FAO 2021), this unique ecosystem remains under threat due to climate change and associated rising sea levels (Gilman et al. 2008; Giri et al. 2011).

            Considered the suggested sentence structure

             

            Lines 131-135

             

            The mangroves of Palawan have been protected under the direct human inventions through the International Union for Conservation of Nature (IUCN) protected area Category I-IV (Long and Giri 2011) and 1992 Republic Act No.7611, commonly known as the Strategic Environmental Plan for Palawan Act (SEP Law, FAO 2021); yet this unique ecosystem remains under threat due to climate change and associated rising sea levels (Gilman et al. 2008; Giri et al. 2011).

             

            Line 143: replace "for" with "in"

            Several land use/land cover (LULC) techniques have been developed and utilized for the last three

            Replaced the word as advised

             

            Line 137

             

            Several land use/land cover (LULC) techniques have been developed and utilized in the last three

            Line 161-163: sentence hard to understand; may consider rewording

            Through the Global Challenges Research Fund (GCRF) Blue Communities1 (BC), as part of its integrated Project 7 which focuses on describing patterns of changes in the environment through Earth observation satellites, this research aims to:

            Sentence was re-structured

             

            Lines 152-153

             

            Through the Global Challenges Research Fund (GCRF) Blue Communities1 (BC), this research aims to:

            Line 196-197: Repeated info as Introduction Para 2 Line 4

            Mangroves are susceptible to various effects of climate change such as sea-level rise (Ward et al. 2016).

            This sentence was deleted as it seemed a duplicate.

             

            Mangroves are susceptible to various effects of climate change such as sea-level rise (Ward et al. 2016).

            Line 285: If the abbreviation has not been elaborated before, then recommend you to write Electromagnetic spectrum here

            wavelength infrared (SWIR) region of the EM spectrum was due to the weak-scattering signal of the…

            Changed the abbreviated EM as recommended

             

            Line 277

             

            wavelength infrared (SWIR) region of the electromagnetic spectrum was

            Line 371: a brilliant explaination of the Markov tool, nice!

            A Markov Chain is a stochastic process that describes the likelihood of changing one state to another (Serfozo 2009; Arsanjania et al. 2013) through the implementation of neighborhood rules (Aitkenhead and Aalders 2009; Serfozo 2009).

            Appreciate the feedback 

            Line 378: replace "have been" with "is"

            et al. 2015; Abdulrahman and Ameen 2020) have beenconsiderably growing.

            Words were replaced as advised

             

            Line 362

             

            et al. 2015; Abdulrahman and Ameen 2020) isconsiderably growing.

            Line 425: consider adding "diagram of multi-temporal mangrove change detection"

            Figure 2. Schematic diagram of change detection and projection of mangrove forests in Palawan using the Landsat imageries and Markov Chain model.

             

            Figure 2’s title renamed

             

            Line 199

             

            Figure 2. Diagram of multi-temporal mangrove change detection in Palawan using the Landsat imageries, supervised Support Vector Machine classification, and Markov Chain model.

             

            Line 481: Figure description: please do mention the time frame as well

            Figure 5. Estimated total cover of non-mangrove areas in Palawan.

            Add time frame to Figure 5’s title as suggested.

             

            Line 455

             

            Figure 5. Estimated total cover of non-mangrove areas in Palawan from 1988 to 2020.

            Line 674: Please elaborate the ECAN abbreviation

            Within this law, the spatial basis for the implementation of its main goal is the ECAN Zonation

            ECAN abbreviation was spell out

             

            Lines 642-643

             

            Within this law, the spatial basis for the implementation of its main goal is the Environmentally Critical Areas Network (ECAN) Zonation

            Line 728: replace "caused" to "cause"

            These anthropogenic stresses were assumed to caused changes in the land use/land…

            Changed the verb as suggested

             

            Line 694

             

            These anthropogenic stresses were assumed to cause changes in the land use/land…

            Line 757: replace "may had" with "may be"

            positive outlook of the local communities may had influenced by the environmental regulatory…

            Replaced the words as suggested

             

            Line 721

             

            positive outlook of the local communities may beinfluenced by the environmental regulatory…

            Line 788: replace "becomes slightly shifting" to "starts to shift"

            COVID-19 pandemic become slightly shifting to an endemic approach, the tourism industry…

            Replaces words as suggested

             

            Line 784

             

            COVID-19 pandemic starts to shift to an endemic approach, the tourism industry…

            Line 814: Maybe you meant "vitally important" instead of "viably important"

            Integrating mangrove forest projection at regional scales is viably important to determine…

            Changed the word as suggested

             

            Line 750

             

            Integrating mangrove forest projection at regional scales is vitally important to determine…

             

             

             

            Reviewer: Xiongjie Deng

            Reviewer’s Comments/Suggestion (Original Manuscript)

            Text(s) from Original Manuscript

            Authors’ Responses (Revised Manuscript)

            “modeling” in line 420 but “modelling” in lines 87, 380,

            classification and predictive modeling underwent…

            All the words “modeling”

            Were changed to “modelling” for consistency

             

            For example, Line 194,

             

            classification and predictive modelling underwent…

            Figure 2, etc.; “e.g.” are in italic type in line 128 and 146, etc., but are in roman type in line 151 and 153, etc. I would be really delighted if the authors could keep the style consistent across the whole article.

             

            All the “e.g., and i.e.” in italic style were changed to non-italic style

             

            For example, Lines 98, 99, 100, 101, 102, 114, 232, 334)

            Besides, for the entire article, I think it would be better to add a comma behind “et al.” and the author’s name, for example, (Brown et al., 2006; Mukherjee et al., 2014) (line 94), (Ball and Pidsley, 1995) (line 96).

            salinities of 2 parts per thousand (Ball and Pidsley 1995),

            All the in-text citation, such as Ball and Pidsley 1995 were now changed into Vancouver-style in-text reference formation

             

            For example, Line 95

            Line 85: I think “may had” should be “may have”.

            did not capture the environmental factors that may had influenced the…

            Changed words as suggested

             

            Line 85

             

            did not capture the environmental factors that may have influenced the…

            Line 100: I think the comma behind “intrusion” is redundant.

            phenomena, e.g., flood, storm erosion, and salt intrusion,(Mendoza…

            Comma was removed after the word “intrusion”

             

            Line 99

             

            phenomena, e.g., flood, storm erosion, and salt intrusion [1…

            Line 124: The phrase “to do” may be wordy, consider removing it.

            making extensive in-situsampling difficult to do.

            Re-structured the sentence as advised by Thapa. Removed the words “to do”

             

            Line 121

             

            samplings make extensive in-situ sampling difficult.

            Line 149: Perhaps there should be a comma between “technique” and “training”; consider modifying “time consuming” to “time-consuming”.

            technique training samples must be extracted, which can be time consuming when using multi-…

            Placed comma between “technique” and “training” and modified the word “time consuming”

             

            Lines 142-143

             

            Technique, training samples must be extracted, which can be time-consumingwhen using multi-…

            Line 148 - 150: It confused me that you specified “Landsat imagery”. I agree that extracting training samples is time-consuming when using supervised classification methods, but I do not think it is only for Landsat imagery, so I would advise you to modify “Landsat imagery” to a more general term, like remotely sensed imagery.

            which can be time consuming when using multi-temporal Landsat imagery.

            Changed the “Landsat imagery” into “remotely sensed imagery” to denote generalization

             

            Line 143

             

            which can be time-consuming when using multi-temporal remotely sensed imagery.

            Line 154: I think you should add “of” between “one” and “many”.

            Yang 2020) is one many prediction techniques that are able to assess…

            Placed the word “of” as suggested

             

            Line 146

             

            [38, 39] is one of many prediction techniques that are able to assess…

            Line 167: Perhaps you should modify “(c)” to “(3)” since you used “(1)” and “(2)” before.

            and (c) implement change projections of the mangrove forests…

            Changed “(c)” to “(3)” as suggested

             

            Line 156

             

            and (3) implement change projections of the mangrove forests…

            Line 178: I think “borders” should be “border”.

            Malaysian Sabah Island bordersthe eastern and southern…

            Removed “s” in “borders”

             

            Line 167

             

            Malaysian Sabah Island border the eastern and southern…

            Line 193: It seems the “ecosystem” should be in plural format.

            coastal and marine ecosystem in the Philippines…

            Placed “s” in “ecosystem” as suggested

             

            Line 182

             

            coastal and marine ecosystems in the Philippines…

            Line 226, 243, 249, 259, 272, 391: It looks like you typed the letter “x” instead of the multiplication sign “×”.

             

             

            Replaced the letter “x” with the multiplication sign “”, for all the equations

             

            Lines 236, 242, 252, 264

             

             

            Line 254: The “Lmin – (Lmax Lmin)” confused me, I guess you want to explain Qmin and Qmax here?

            metadata files; Lmin – (Lmax Lmin)correspond…

            Typo-error was made, replaced the Lmin and Lmax with Qmin and Qmax

             

            Line 247

             

            metadata files; Qmin and Qmax correspond

            Line 319: Perhaps “was” should be “were”.

            data available was poor in quality.

            Changed the verb form as suggested

             

            Line 309

             

            data available were poor in quality.

            Line 344: The comma behind “where” may be unnecessary.

            where, ||x – x´||2 is the squared Euclidean…

            Removed the comma

             

            Line 332

             

            where ||x – x´||2 is the squared Euclidean…

            Line 358, 360: Please keep both “Kappa” consistent.

            kappa coefficient values (Congalton 1991

            All the “kappa” words were replaced with “Kappa”, starts with capital letter, for consistency

             

            Line 346

             

            Kappa coefficient values [81].

            Line 361: It seems that “qualify” does not agree with the subject.

            which qualify them as significant covariates

            Removed these sentence as deemed irrelevant/creating confusion or not too important

            Line 420 – 426: I would advise you to move this part to the beginning of Section 2.

            The entire methodological process of mangrove classification and predictive modeling underwent three major processes: (1) Raw data and pre-processing, (2) Image classification and change detection, and (3) Mangrove change projection (Figure 2).

            Th whole part was moved from Lines 420-426 to Lines 194-200

             

            The entire methodological process of mangrove classification and predictive modelling underwent three major processes: (1) Raw data and pre-processing, (2) Image classification and change detection, and (3) Mangrove change projection (Figure 2).

            Figure 2: In the left box, I would advise you to modify “7 ETM+” to “Landsat 7 ETM+”; you mentioned LULC classification using SVM in this figure, but in the title, you missed this part, so I would advise you to describe it more specifically.

            Landsat 4-5 TM, 7 ETM+, and Landsat 8 OLI

             

            Add the word “Landsat” in “7 ETM+” as suggested

             

            Line 197, Figure 2

             

            Landsat 4-5 TM, Landasat7 ETM+, and Landsat 8 OLI

             

            Line 438: Perhaps “were” should be “was”.

            the mangrove forests cover in Palawan were still…

            Replaced verb as appropriate

             

            Line 412

             

            the mangrove forests cover in Palawan was still…

            Line 445: Perhaps “are” should be “is”.

            are generally found in Puerto Princesa Bay…

            Replaced verb as appropriate

             

            Line 419

             

            is generally found in Puerto Princesa Bay…

            Figure 4: As I understand, the left y-axis is for Palawan, and the right y-axis is for the other three cities. If so, I would advise you to specify it in the title of this figure, or consider mapping them separately. The original figure is confusing to me.

            Figure 4. Composite representation of area statistics of mangroves in Palawan, Puerto Princesa City, Taytay, and Aborlan.

             

            Specified the what the y or x axis is pointing by integrating additional information in Figure 4’s title.

             

            Lines 430-431

             

            Figure 4. Composite representation of area statistics of mangroves in Palawan (left y-axis), Puerto Princesa City, Taytay, and Aborlan (right y-axis).

            Figure 5: I would advise you to add ticks to the y-axis.

             

            Added ticks to the y-axis as suggested

             

            Line 454, Figure 5

            Figure 6: Please add a legend to indicate bars in different colours.

            Figure 6. Representation of mangrove forest areas in Palawan based on the previous estimates and the results of this study.

             

            Mentioned the bar-legned in the figure’s title.

             

            Lines 481-482, Figure 6

             

            Figure 6. Representation of mangrove forest areas in Palawan based on the previous estimates (gray bars) and the results of this study (blue bars).

            Line 493: I think it would be more precise to say “SPOT satellite sensor’s data” or “SPOT satellite sensor’s images”.

            the Satellite Pour I’Observation de la Terre (SPOT) satellite sensor to delineate…

            Precisely wrote SPOT, as suggested

             

            Line 467

             

            the Satellite Pour I’Observation de la Terre (SPOT) satellite sensor’s images to delineate…

            Line 494: Perhaps “Based on”.

            Based from the mangrove data…

            Changed “from” to “on” as suggested

             

            Line 468

             

            Based on the mangrove data…

            Line 521: “in” may be unnecessary.

            in between 2013, 2014, and 2016. 

            Removed the preposition “in”

             

            Line 492

             

            between 2013, 2014, and 2016. 

            Table 2: Is it normal that the estimates in 2018 and 2020 from this study are exactly the same in Puerto Princesa City and Taytay?

            6,601.8*   7,103.6*

            6,601.8*   7,103.6*

             

            Typo-error, changed the numbers. Checked the main data.

             

            Line 492, Table 2

             

            6,709.4*   7,285.1*

            6,601.8*   7,103.6*

            Line 537, 538: The first sentence is ambitious to me, I guess you tried to mean that the total mangrove forests extent in Puerto Princesa City at 3,201.8 ha in 2003 was estimated by Pagkalinawan and Ramos (2013)? If so, I would advise you to modify the place of the term “in 2003” because if it presents at the beginning of the sentence, it may mislead readers that Pagkalinawan and Ramos conducted their research in 2003.

            In 2003, Pagkalinawan and Ramos (2013) estimated the total mangrove forests extent in Puerto Princesa City at 3,201.8 ha.

            Removed “in 2003” to eliminate confusion

             

            Line 507

             

            [27] estimated the total mangrove forests extent in Puerto Princesa City at 3,201.8 ha.

            Line 562 - 564: I only found “WRSP/R” information in Table 2; I would advise you to add cloud cover percentages of the two images you mentioned to make this sentence more compelling.

            During this period, the cloud covers in two of the six scenes (refer to the Supplementary Informations Table 1: WRS Path 116/Row 052 and WRS Path 118/Row 054) made marginal spectral confusion between different features.

            Added cloud cover estimates, as suggested. Rephrased the sentence.

             

            Lines 530-533

             

            During this period, the cloud covers in two of the six scenes (refer to the Supplementary Information Table 2: WRS Path 116/Row 052 [cloud cover=3, cloud land cover=13] and WRS Path 118/Row 054 [cloud cover=8, cloud land cover=20]) made marginal spectral confusion between different features.

            Figure 8 (a) and (b), (c) and (d): It will be better if the x-axis of (b) and (d) can align with the x-axis of (a) and (c), respectively.

             

            Alignments for all the graphs in Figure 8 were done

            Line 757: I think “had” is not in the correct form.

            positive outlook of the local communities may had influenced by the environmental regulatory…

            Changed “had” with “be” as the previous seemed the incurred form of verb used

             

            Line 721

             

            positive outlook of the local communities may beinfluenced by the environmental regulatory…

            Line 763: It seems that “presumed” does not appear to be in the proper form.

            (https://puertoprincesa.ph/?q=tourism/february-14-love-affair-nature), they may presumedthat this

            Changed with the correct form of verb

             

            Line 726

             

            [106], they presume that this

            Line 764: I think the “is” after “there” is not in the correct form.

            However, there is still no…

            Removed “is’ and replaced with “was” as advised

             

            Line 727

             

            However, there was still no…

            Line 774: It seems the “and” before “infrastructure” is unnecessary.

            deforestation, forest regeneration,and infrastructure, industrial, and residential developments).

            “and” was removed as suggested

             

            Line 737

             

            deforestation, forest regeneration, infrastructure, industrial, and residential developments).

            Line 788: The word “shifting” may be in the wrong form.

            COVID-19 pandemic become slightly shifting to an endemic approach, the tourism…

            Changed to “starts to shift to”

             

            Line 750

             

            COVID-19 pandemic starts to shift to an endemic approach, the tourism…

            Line 805: I think it would be more precise to add “an” before “increase”.

            Our analysis has shown the high likelihood of increase in…

            Add “an” before the word “increase” as suggested

             

            Line 768

             

            Our analysis has shown the high likelihood of an increase in…

            Line 812: It seems that “continues” should be “continue”.

            emissions continues.Furthermore, other threats such as coastal conversion…

            Changed to correct formed of verb “continues” to “continue” Line 775

             

            emissions continue.Furthermore, other threats such as coastal conversion…

            Line 819 - 823: You state that integrating Cellular Automata in Markov Chain modelling can evaluate the impacts of different policies. Still, I suggest you to explain why you recommend future research should integrate the Cellular Automata in Markov Chain modelling more specifically, for example, you can provide more details about the advantages, capabilities, and effectiveness of Cellular Automata in mangroves-related research to assess policies.

            management, ecological sustainability, and policy intervention. However, since we did not create this type of model to directly assess our current policies, we recommend that future research should integrate the Cellular Automata in Markov Chain modelling. This way, research bodies can evaluate the impacts of different policies (e.g., 1992 SEP Law, 1981 Mangrove Swamp Forest Reserve) in the future state of mangroves in Palawan.

            Restructured as advised. Added some extra information.

             

            Lines 882-785

             

            However, since we did not create this type of model to directly assess our current policies, we recommend that future research should integrate the Cellular Automata-Markov model since it provides land cover data needed at different time steps (i.e., pre- and post-policy intervention) (e.g., [42]).

            Line 830: Two “also” in a sentence seem unnecessary.

            Also, it would also be necessary to investigate the pressures of different socio-economic activities of…

            Removed repeated word “also”

             

             Line 794

             

            It would also be necessary to investigate the pressures of different socio-economic activities of…

             

             

             

            APA referencing format need to change to Vancouver

             

            Referencing style change to Vancouver format

             

            Abstract

            Multi-temporal remote sensing imagery can be used to explore how mangrove assemblages are changing over time and facilitate critical interventions for ecological sustainability and effective management. This study aims to explore the spatial dynamics of mangrove extents in Palawan, Philippines, specifically in Puerto Princesa City (PPC), Taytay, and Aborlan, and facilitate future prediction for Palawan using the Markov Chain model. The multi-date Landsat imageries during the period 1988–2020 were used for this research. The Support Vector Machine algorithm was sufficiently effective for mangrove feature extraction to generate satisfactory accuracy results (>70% Kappa coefficient values; 91% average overall accuracies). In Palawan, a 5.2% (2,693 ha) decrease was recorded during 1988–1998 and an 8.6% increase in 2013–2020 to 4,371 ha. In PPC, 95.9% (2,758 ha) increase was observed during 1988–1998 and 2.0% (136 ha) decrease during 2013–2020. The mangroves in Taytay and Aborlan both gained an additional 2,138 ha (55.3%) and 228 ha (16.8%) during 1988–1998 but also decreased from 2013 to 2020 by 3.4% (247 ha) and 0.2% (3 ha), respectively. However, projected results suggest that the mangrove areas in Palawan will likely increase in 2030 (to 64,946 ha) and 2050 (to 66,972 ha). This study demonstrated the capability of the Markov Chain model in the context of ecological sustainability involving policy intervention. However, since this research did not capture the environmental factors that may had influenced the changes in mangrove patterns, it is suggested the addition of Cellular Automata in future Markovian mangrove modelling.

            Content

            Author and article information

            Journal
            UCL Open: Environment Preprint
            UCL Press
            15 January 2023
            Affiliations
            [1 ] Western Philippines University, College of Fisheries and Aquatic Sciences
            [2 ] Remote Sensing Group, Plymouth Marine Laboratory
            Author notes
            Author information
            https://orcid.org/0000-0002-0779-5534
            Article
            10.14324/111.444/000157.v2
            6548b67f-5a10-4c33-8b48-0150dfff60f3

            This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY) 4.0 https://creativecommons.org/licenses/by/4.0/, which permits unrestricted use, distribution and reproduction in any medium, provided the original author and source are credited.

            History
            : 4 July 2022
            : 16 March 2023
            Funding
            Global Challenges Research Fund, Blue Communities, under the United Kingdom Research and Innovation NE/P021107/1
            Categories

            The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.
            Earth & Environmental sciences
            Change detection,Image classification, Landsat,Land use/land cover,Markov Chain Model,Spatial dynamics,Support Vector Machine,Environmental modelling,Environmental protection,Environmental science

            Comments

            Date: 16 March 2023

            Handling Editor: Dr Jesús Aguirre Gutiérrez

            Editorial decision: Accept. This revised article has been accepted following peer review and it is suitable for publication in UCL Open: Environment.

            2023-03-20 10:36 UTC
            +1
            2023-03-17 14:17 UTC
            +1
            2023-03-17 14:14 UTC
            +1

            Comment on this article