Abstract
This study focuses on the comparison of machine learning algorithms for classifying the mangrove species of Malad creek, Mumbai, India using pixel-based and object-based approaches. As mangrove forests are complex in structure and require high resolution remotely sensed images for classifying them at the species level, traditional classification methods of remote sensing may not be suitable. In order to find an appropriate method, pixel-based random forest and K Nearest Neighbor classifiers and object-based random forest and K Nearest Neighbor classifiers were tested and compared using WorldView – 2 images. In addition, the best resolution RGB images from Google Earth were classified using random forest and K Nearest Neighbor algorithms in object-based approach and compared. The classification results showed that both object-oriented and pixel-based methods could identify the major mangrove species at the community level. However, the performance of object-based random forest classifier was better than other classification approaches in both WorldView-2 and Google Earth images with overall accuracies of 92.53% and 80.72% and kappa coefficients of 0.89 and 0.73. The overall results showed the potential of random forest classifier in object-based method for classifying the mangroves at the species level.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abutaleb K, Newete S, Mangwanya S, Adam E, Byrne M (2020) Mapping eucalypts trees using high resolution multispectral images: A study comparing Worldview 2 vs SPOT 7. Egypt J Remote Sens Space Sci. https://doi.org/10.1016/j.ejrs.2020.09.001
Alongi DM (2002) Present state and future of the world’s mangrove forests. Environ Conserv 29(3):331–349. https://doi.org/10.1017/S0376892902000231
Alongi DM (2012) Carbon sequestration in mangrove forests. Carbon Manag 3(3):313–322. https://doi.org/10.4155/cmt.12.20
Bandaranayake WM (1998) Traditional and medicinal uses of mangroves. Mangrove Salt Marshes 2:133–148. https://doi.org/10.1023/A:1009988607044
Belgiu M, Drăguţ L (2016) Random forest in remote sensing: A review of applications and future directions. ISPRS J Photogramm Remote Sens 114:24–31. https://doi.org/10.1016/j.isprsjprs.2016.01.011
Blaschke T (2010) Object based image analysis for remote sensing. ISPRS J Photogramm Remote Sens 65(1):2–16. https://doi.org/10.1016/j.isprsjprs.2009.06.004
Breiman L (2001) Random Forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324
Breiman L (1999) Random forests—random features. Technical Report 567, Statistics Department, University of California, Berkeley
Camps-Valls G, Bruzzone L (2009) Kernel methods for remote sensing data analysis. John Wiley & Sons, Ltd.
Castilla G, Hay GJ (2008) Image objects and geographic objects. In: Blaschke T, Lang S, Hay GJ (eds) Object-Based image analysis: Spatial concepts for knowledge-driven remote sensing applications. Springer: Berlin, Germany, pp. 91–110.
Chen G, Weng Q, Hay GJ, He Y (2018) Geographic object-based image analysis (GEOBIA): Emerging trends and future opportunities. Giscience Remote Sens 55:159–182. https://doi.org/10.1080/15481603.2018.1426092
Chen Y, Chen Q, Jing C (2019) Multi-resolution segmentation parameters optimization and evaluation for VHR remote sensing image based on mean NSQI and discrepancy measure. J Spat Sci 66:1–26. https://doi.org/10.1080/14498596.2019.1615011
Congalton RG (1991) A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens Environ 37(1):35–46. https://doi.org/10.1016/0034-4257(91)90048-B
Das Gupta R, Shaw R (2013) Changing perspectives of mangrove management in India – An analytical overview. Ocean Coast Manag 80:107–118. https://doi.org/10.1016/j.ocecoaman.2013.04.010
Duhl TR, Guenther A, Helmig D (2012) Estimating urban vegetation cover fraction using Google Earth images. J Land Use Sci 7(3):311–329. https://doi.org/10.1080/1747423X.2011.587207
Duke NC, Menecke JO, Dittmann S, Ellison AM, Anger K, Berger U, Canicci S, Diele K, Ewel KC, Field CD, Koedam N, Lee SY, Marchand C, Nordhaus I, Guebas FD (2007) A World Without Mangroves? Science 317:41–42. https://doi.org/10.1126/science.317.5834.41b
Everitt JH, Yang C, Sriharan S (2008) Using High Resolution Satellite Imagery to Map Black Mangrove on the Texas Gulf Coast. J Coast Res 246:1582–1586. https://doi.org/10.2112/07-0987.1
Fu B, Wang Y, Campbell A, Li Y, Zhang B, Yin S, Xing Z, Jin X (2017) Comparison of object-based and pixel-based Random Forest algorithm for wetland vegetation mapping using high spatial resolution GF-1 and SAR data. Ecol Indic 73:105–117. https://doi.org/10.1016/j.ecolind.2016.09.029
Giri S, Muhopadhyay A, Hazra S, Mukherjee S, Roy D, Ghosh S, Ghosh T, Mitra D (2014) A study on abundance and distribution of mangrove species in Indian Sundarban using remote sensing technique. J Coast Conserv 18(4):359–367. https://doi.org/10.1007/s11852-014-0322-3
Gowda KC, Krishna G (1979) The condensed nearest neighbor rule using the concept of mutual nearest neighborhood. IEEE Trans Inf Theory 25(4):488–490. https://doi.org/10.1109/TIT.1979.1056066
Gupta K, Mukhopadhyay A, Giri S, Chandra A, Majumdar SD, Samanta S, Mitra D, Samal RN, Pattnaik AJ, Hazra S (2018) An index for discrimination of mangroves from non-mangroves using LANDSAT 8 OLI imagery. MethodsX 5:1129–1139. https://doi.org/10.1016/j.mex.2018.09.011
Heumann BW (2011) An Object-Based Classification of Mangroves Using a Hybrid Decision Tress-Support Vector Machine Approach. Remote Sens 3(11):2440–2460. https://doi.org/10.3390/rs3112440
Houborg R, McCabe MF (2018) A hybrid training approach for leaf area index estimation via cubist and random forests machine-learning. ISPRS J Photogramm Remote Sens 135:173–188. https://doi.org/10.1016/j.isprsjprs.2017.10.004
Jennerjahn TC, Ittekkot V (2002) Relevance of mangroves for the production and deposition of organic matter along tropical continental margin. Sci Nat 89:23–30. https://doi.org/10.1007/s00114-001-0283-x
Jhonnerie R, Siregar VP, Nababan B (2017) Comparison of Random Forest Algorithm which implemented on object and pixel based classification for mangrove land cover mapping. Appl Sci Technol 1(1):293–302
Kathiresan K, Bingham BL (2001) Biology of Mangroves and Mangrove Ecosystem. Adv Mar Biol 40:85–251. https://doi.org/10.1016/S0065-2881(01)40003-4
Koh HL, Teh SY, Raja Barizan RS (2018) Mangrove forests: Protection against and resilience to coastal disturbances. J Trop For Sci 30(5):446–460. https://doi.org/10.26525/jtfs2018.30.5.446460
Kussul N, Lemoine G, Gallego J, Skakun S, Lavreniuk M (2015) Parcel based classification for agricultural mapping and monitoring using multi-temporal satellite image sequence. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan 165–168. https://doi.org/10.1109/IGARSS.2015.7325725
Lapini A, Pettinato S, Santi E, Paloscia S, Fontanelli G, Garzelli A (2020) Comparison of Machine Learning Methods Applied to SAR Images for Forest Classification in Mediterranean Areas. Remote Sens 12:369. https://doi.org/10.3390/rs12030369
Li M, Ma L, Blaschke T, Cheng L, Tiede D (2016) A systematic comparison of different object-based classification techniques using high spatial resolution imagery in agricultural environments. Int J Appl Earth Obs Geoinf 49:87–98. https://doi.org/10.1016/j.jag.2016.01.011
Li H, Han Y, Chen J (2020) Combination of Google Earth imagery and Sentinel-2 data for mangrove species mapping. J Appl Remote Sens 14(1):010501. https://doi.org/10.1117/1.JRS.14.010501
Liu D, Xia F (2010) Assessing object-based classification: advantages and limitations. Remote Sens Lett 1(4):187–194. https://doi.org/10.1080/01431161003743173
Lopez-Angarita J, Roberts CM, Tilley A, Hawkins JP, Cooke RG (2016) Mangroves and people: Lessons from a history of use and abuse in four Latin American countries. For Ecol Manag 368:151–162. https://doi.org/10.1016/j.foreco.2016.03.020
Ludwig A, Meyer H, Nauss T (2016) Automatic classification of Google Earth images for a larger scale monitoring of bush encroachment in South Africa. Int J Appl Earth Obs Geoinf 50:89–94. https://doi.org/10.1016/j.jag.2016.03.003
Macnae W (1968) A general account of the fauna and flora of mangrove swamps and forests in the Indo-West-Pacific region. Adv Mar Biol 6:73–270. https://doi.org/10.1016/S0065-2881(08)60438-1
Marois DE, Mitsch WJ (2015) Coastal protection from tsunamis and cyclones provided by mangroves wetlands – a review. Int J Biodivers Sci Ecosyst Serv Manag 11(1):71–83. https://doi.org/10.1080/21513732.2014.997292
Maxwell AE, Warner TA, Fang F (2018) Implementation of machine-learning classification in remote sensing: an applied review. Int J Remote Sens 39(9):2784–2817. https://doi.org/10.1080/01431161.2018.1433343
Mesner N, Ostir K (2014) Investigating the impact of spatial and spectral resolution of satellite images on segmentation quality. J Appl Remote Sens 8(1):083696. https://doi.org/10.1117/1.JRS.8.083696
Odindi J, Adam E, Ngubane Z, Mutanga O, Slotow R (2014) Comparison between WorldView-2 and SPOT-5 images in mapping the bracken fern using the random forest algorithm. J Appl Remote Sens 8(1):083527. https://doi.org/10.1117/1.JRS.8.083527
Osti R, Tanaka S, Tokioka T (2009) The importance of mangrove forest in tsunami disaster mitigation. Disasters 33(2):203–213. https://doi.org/10.1111/j.1467-7717.2008.01070.x
Pal M (2005) Random forest classifier for remote sensing classification. Int J Remote Sens 26(1):217–222. https://doi.org/10.1080/01431160412331269698
Peng L, Liu K, Cao J, Zhu Y, Li F, Liu L (2020) Combining GF-2 and RapidEye satellite data for mapping mangrove species using ensemble machine-learning methods. Int J Remote Sens 41(3):813–838. https://doi.org/10.1080/01431161.2019.1648907
Pham LTH, Brabyn L (2017) Monitoring mangrove biomass change in Vietnam using SPOT images and an object-based approach combined with machine learning algorithms. ISPRS J Photogramm Remote Sens 128:86–97. https://doi.org/10.1016/j.isprsjprs.2017.03.013
Pham TD, Yokoya N, Bui DT, Yoshino K, Friess DA (2019) Remote Sensing Approaches for Monitoring Mangrove Species, Structure, and Biomass: Opportunities and Challenges. Remote Sens 11:230. https://doi.org/10.3390/rs11030230
Quynh Trang NT, Toan LQ, Huyen Ai TT, Vu Giang N, Viet Hoa P (2016) Object-based vs. Pixel-based classification of mangrove forest mapping in Vien An Dong commune, Ngoc Hien district, Ca Mau province using VNREDSat-1 images. Adv Remote Sens 5:284–295. https://doi.org/10.4236/ars.2016.54022
Rahman M, Ullah R, Lan M, Sri Sumantyo JTS, Kuze H, Tateishi R (2013) Comparison of Landsat image classification methods for detecting mangrove forests in Sundarbans. Int J Remote Sens 34(4):1041–1056. https://doi.org/10.1080/01431161.2012.717181
Rajkumar S Y, Ketan M, Harshad S and Kamboj R.D (2017) Age and Growth relation of mangrove Avicennia marina (Forssk.) Vierh. in Gulf of Kachchh (GoK), India. App Sci Rep 17 (1):18–23. https://doi.org/10.15192/PSCP.ASR.2017.17.1.1823
Richards JA, Jia X (2006) Remote Sensing Digital Image Analysis: An Introduction. Springer 4th edition
Rotich B, Mwangi E, Lawry S (2016) Where land meets the sea: A global review of the governance and tenure dimensions of coastal mangrove forests. Technical report, CIFOR, Bogor, Indonesia; USAID Tenure and Global Climate Change Program, Washington, DC
Song C, Nigatu L, Beneye Y, Abdulahi A, Zhang L, Wu D (2018) Mapping the vegetation of the Lake Tana basin, Ethiopia, using Google Earth images. Earth Syst Sci Data 10(4):2033–2041. https://doi.org/10.5194/essd-10-2033-2018
Thampanya U, Vermaat JE, Sinsakul S, Panapitukkul N (2006) Coastal erosion and mangrove progradation of Southern Thailand. Estuar Coast Shelf Sci 68:75–85. https://doi.org/10.1016/j.ecss.2006.01.011
Valderrama-Landeros L, Flore-de-Santiago F, Kovacs JM, Flores-Verdugo F (2018) An assessment of commonly employed satellite-based remote sensors for mapping mangrove species in Mexico using an NDVI-based classification scheme. Environ Monit Assess 190(23):1–13. https://doi.org/10.1007/s10661-017-6399-z
Vijay V, Biradar RS, Inamdar AB, Deshmukhe G, Baji S, Pikle M (2005) Mangrove mapping and change detection around Mumbai (Bombay) using remotely sensed data. Indian J Mar Sci 34(3):310–315
Wan L, ZhangH LG, Lin H (2019) A small-patched convolutional neural network for mangrove mapping at species level using high-resolution remote-sensing image. Ann GIS 25(1):45–55. https://doi.org/10.1080/19475683.2018.1564791
Wang L, Wayne P, Sousa P, Gong G, Biging S (2004) Comparison of IKONOS and QuickBird images for mapping mangrove species on the Caribbean coast of Panama. Remote Sens Environ 91(3–4):432–440. https://doi.org/10.1016/j.rse.2004.04.005
Wang T, Zhang H, Lin H, Fang C (2016) Textural-spectral feature-based species classification of mangroves in Mai Po nature reserve from worldview-3 imagery. Remote Sens 8(24). https://doi.org/10.3390/rs8010024
Watanabe S, Sumi K, Ise T (2020) Identifying the vegetation type in Google Earth images using a convolutional neural network: a case study for Japanese bamboo forests. BMC Ecol 20:65. https://doi.org/10.1186/s12898-020-00331-5
Weih RC, Riggan ND (2017) Object-based classification vs Pixel-based classification: Comparative importance of multi-resolution imagery. Proceedings of GEOBIA: Geographic Object-Based Image Analysis, Ghent, Belgium, 29 June–2 July
Whiteside TG, Boggs GS, Maier SW (2011) Comparing object-based and pixel-based classifications for mapping savannas. Int J Appl Earth Obs Geoinf 13(6):884–893. https://doi.org/10.1016/j.jag.2011.06.008
Whiteside T, Ahmad W (2005) A comparison of object-oriented and pixel-based classification methods for mapping land cover in northern Australia. Proceeding of Spatial intelligence, innovation and praxis: The national biennial Conference of the Spatial Science Institute, Melbourne
Funding
The study is supported by Indian Institute of Space Science and Technology and WorldView data was procured for a project funded by Mangrove Foundation, Mumbai.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Nagarajan, P., Rajendran, L., Pillai, N.D. et al. Comparison of machine learning algorithms for mangrove species identification in Malad creek, Mumbai using WorldView-2 and Google Earth images. J Coast Conserv 26, 44 (2022). https://doi.org/10.1007/s11852-022-00891-2
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11852-022-00891-2