Mapping shoreline change using machine learning: a case study from the eastern Indian coast

• Autorzy: Kumar, Lalit , Afzal, Mohammad Saud , Afzal, Mohammad Mashhood
• Języki publikacji: EN

Abstrakty

EN

The continuous shift of shoreline boundaries due to natural or anthropogenic events has created the necessity to monitor the shoreline boundaries regularly. This study investigates the perspective of implementing artifcial intelligence techniques to model and predict the realignment in shoreline along the eastern Indian coast of Orissa (now called Odisha). The modeling consists of analyzing the satellite images and corresponding reanalysis data of the coastline. The satellite images (Landsat imagery) of the Orissa coastline were analyzed using edge detection flters, mainly Sobel and Canny. Sobel and canny flters use edge detection techniques to extract essential information from satellite images. Edge detection reduces the volume of data and flters out worthless information while securing signifcant structural features of satellite images. The image diferencing technique is used to determine the shoreline shift from GIS images (Landsat imagery). The shoreline shift dataset obtained from the GIS image is used together with the metrological dataset extracted from Modern-Era Retrospective analysis for Research and Applications, Version 2, and tide and wave parameter obtained from the European Centre for Medium-Range Weather Forecast for the period 1985–2015, as input parameter in machine learning (ML) algorithms to predict the shoreline shift. Artifcial neural network (ANN), k-nearest neighbors (KNN), and support vector machine (SVM) algorithm are used as a ML model in the present study. The ML model contains weights that are multiplied with relevant inputs/features to obtain a better prediction. The analysis shows wind speed and wave height are the most prominent features in shoreline shift prediction. The model’s performance was compared, and the observed result suggests that the ANN model outperforms the KNN and SVM model with an accuracy of 86.2%.

Słowa kluczowe

PL

zmiany linii brzegowej; przetwarzanie obrazu; sztuczna sieć neuronowa; wykrywanie krawędzi; nauczanie maszynowe

EN

shoreline changes; image processing; artificial neural network; edge detection; machine learning

• Czasopismo: Acta Geophysica
• Rocznik: 2020
• Tom: Vol. 68, no. 4
• Strony: 1127--1143
• Opis fizyczny: Bibliogr. 112 poz.

Twórcy

autor

Kumar, Lalit

• Department of Civil Engineering, Indian Institute of Technology, Kharagpur, West Bengal, India

autor

Afzal, Mohammad Saud

• Department of Civil Engineering, Indian Institute of Technology, Kharagpur, West Bengal, India,

autor

Afzal, Mohammad Mashhood

• Birlasoft Limited, Tower 3 Assotech Business Cresterra Plot no 22, Noida-Greater Noida Expy, Sector 135, Noida, Uttar Pradesh, India

Bibliografia

• 1. Acharjya PP, Das R, Ghoshal D (2012) Study and comparison of different edge detectors for image segmentation. Glob J Comput Sci Technol 12:29–32
• 2. Afzal MS, Bihs H, Kumar L (2020) Computational fluid dynamics modeling of abutment scour under steady current using the level set method. Int J Sediment Res 35:355–364
• 3. Ahangarha M, Seydi ST, Shahhoseini R (2019) Hyperspectral change detection in wetland and water-body areas based on machine learning. In: International archives of the photogrammetry, remote sensing & spatial information sciences, geospatial conference 2019—joint conferences of SMPR and GI research, vol XLII-4/W18, pp 19–24
• 4. Ahmadian AS, Simons RR (2018) Estimation of nearshore wave transmission for submerged breakwaters using a data-driven predictive model. Neural Comput Appl 29(10):705–719
• 5. Alesheikh AA, Ghorbanali A, Nouri N (2007) Coastline change detection using remote sensing. Int J Environ Sci Technol 4(1):61–66
• 6. Alexakis DD, Agapiou A, Hadjimitsis DG, Retalis A (2012) Optimizing statistical classification accuracy of satellite remotely sensed imagery for supporting fast flood hydrological analysis. Acta Geophys 60(3):959–984
• 7. Altman NS (1992) An introduction to kernel and nearest-neighbor nonparametric regression. Am Stat 46(3):175–185
• 8. Arce-Medina E, Paz-Paredes JI (2009) Artificial neural network modeling techniques applied to the hydrodesulfurization process. Math Comput Model 49(1–2):207–214
• 9. Bagheri M, Ibrahim ZZ, Mansor SB, Manaf LA, Badarulzaman N, Vaghefi N (2019) Shoreline change analysis and erosion prediction using historical data of Kuala Terengganu, Malaysia. Environ Earth Sci 78(15):477
• 10. Barman NK, Chatterjee S, Khan A et al (2014) Trends of shoreline position: an approach to future prediction for Balasore shoreline, Odisha, India. Open J Mar Sci 5(01):13
• 11. Bazile R, Boucher MA, Perreault L, Leconte R (2017) Verification of ECMWF system 4 for seasonal hydrological forecasting in a northern climate. Hydrol Earth Syst Sci 21(11):5747
• 12. Bosilovich MG, Chen J, Robertson FR, Adler RF (2008) Evaluation of global precipitation in reanalyses. J Appl Meteorol Climatol 47(9):2279–2299
• 13. Bosilovich MG, Robertson FR, Takacs L, Molod A, Mocko D (2017) Atmospheric water balance and variability in the MERRA-2 reanalysis. J Clim 30(4):1177–1196
• 14. Bouguerra H, Tachi SE, Derdous O, Bouanani A, Khanchoul K (2019) Suspended sediment discharge modeling during flood events using two different artificial neural network algorithms. Acta Geophys 67(6):1649–1660
• 15. Bruun P (1962) Sea-level rise as a cause of shore erosion. J Waterw Harb Div 88(1):117–132
• 16. Canny JF (1986) A theory of edge detection. IEEE Trans Pattern Anal Mach Intell 8:147–163
• 17. Chalabi A, Mohd-Lokman H, Mohd-Suffian I, Karamali K, Karthigeyan V, Masita M (2006) Monitoring shoreline change using ikonos image and aerial photographs: a case study of kuala terengganu area, Malaysia. In: ISPRS Commission VII mid-term symposium “Remote sensing: from pixels to processes”, Enschede, The Netherlands, pp 8–11
• 18. Chudzian P (2011) Radial basis function kernel optimization for pattern classification. In: Burduk R, Kurzyński M, Woźniak M, Żołnierek A (eds) Computer recognition systems, vol 4. Springer, Berlin, pp 99–108
• 19. Coltori M (1997) Human impact in the holocene fluvial and coastal evolution of the Marche region, central Italy. Catena 30(4):311–335
• 20. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
• 21. Dada OA, Agbaje AO, Adesina RB, Asiwaju-Bello YA (2019) Effect of coastal land use change on coastline dynamics along the Nigerian Transgressive Mahin mud coast. Ocean Coast Manag 168:251–264
• 22. De Jong SM, Van der Meer FD (2007) Remote sensing image analysis: including the spatial domain, vol 5. Springer, Berlin
• 23. de Rosnay P, Munoz-Sabater J, Albergel C, Isaksen L, English S, Drusch M, Wigneron JP (2020) SMOS brightness temperature forward modelling and long term monitoring at ECMWF. Remote Sens Environ 237(111):424
• 24. Dee DP, Uppala SM, Simmons A, Berrisford P, Poli P, Kobayashi S, Andrae U, Balmaseda M, Balsamo G, Bauer DP et al (2011) The era-interim reanalysis: configuration and performance of the data assimilation system. Q J R Meteorol Soc 137(656):553–597
• 25. Dellepiane S, De Laurentiis R, Giordano F (2004) Coastline extraction from sar images and a method for the evaluation of the coastline precision. Pattern Recogn Lett 25(13):1461–1470
• 26. Di Silvio G, Nones M (2014) Morphodynamic reaction of a schematic river to sediment input changes: analytical approaches. Geomorphology 215:74–82
• 27. Dickens K, Armstrong A (2019) Application of machine learning in satellite derived bathymetry and coastline detection. SMU Data Sci Rev 2(1):1–25
• 28. Dolan R, Fenster MS, Holme SJ (1991) Temporal analysis of shoreline recession and accretion. J Coast Res 7:723–744
• 29. Dutta D, Mandal A, Afzal MS (2020) Discharge performance of plan view of multi-cycle w-form and circular arc labyrinth weir using machine learning. Flow Meas Instrum 73:101740
• 30. ECMWF (2018) European centre for medium-range weather forecasts. https://www.ecmwf.int/en/research/modelling-and-prediction/marine
• 31. Elko N, Sallenger A, Guy K, Stockdon H, Morgan K (2002) Barrier island elevations relevant to potential storm impacts: 1. Techniques. US Geological Survey Open File Report, pp 02–287
• 32. Esteves LS, Williams JJ, Dillenburg SR (2006) Seasonal and interannual influences on the patterns of shoreline changes in Rio Grande do Sul, southern Brazil. J Coast Res 22:1076–1093
• 33. Fadel S, Ghoniemy S, Abdallah M, Sorra HA, Ashour A, Ansary A (2016) Investigating the effect of different kernel functions on the performance of SVM for recognizing Arabic characters. Int J Adv Comput Sci Appl 7(1):446–450
• 34. Garg A, Huang H, Kushvaha V, Madhushri P, Kamchoom V, Wani I, Koshy N, Zhu HH (2019) Mechanism of biochar soil pore–gas–water interaction: gas properties of biochar-amended sandy soil at different degrees of compaction using knn modeling. Acta Geophys 68:207–217
• 35. Gatys LA, Ecker AS, Bethge M (2015) A neural algorithm of artistic style. arXiv:150806576
• 36. Gazi AH, Afzal MS (2020) A new mathematical model to calculate the equilibrium scour depth around a pier. Acta Geophys 68(1):181–187
• 37. Gazi AH, Afzal MS, Dey S (2019) Scour around piers under waves: current status of research and its future prospect. Water 11(11):2212
• 38. Gelaro R, McCarty W, Molod A, Suarez M, Takacs L, Todling R (2014) The NASA modern era reanalysis for research and applications, Version-2 (MERRA-2). AGUFM 2014:NG32A–01
• 39. Gelaro R, McCarty W, Suárez MJ, Todling R, Molod A, Takacs L, Randles CA, Darmenov A, Bosilovich MG, Reichle R et al (2017) The modern-era retrospective analysis for research and applications, version 2 (merra-2). J Clim 30(14):5419–5454
• 40. Govindaraju RS (2000) Artificial neural networks in hydrology. i: preliminary concepts. J Hydrol Eng 5(2):115–123. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(115)
• 41. Govindaraju RS (2000) Artificial neural networks in hydrology. ii: hydrologic applications. J Hydrol Eng 5(2):124–137. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(124)
• 42. Green B (2002) Canny edge detection tutorial. Retrieved 6 Mar 2005
• 43. Gregory K (2004) River channel management. Hodder Education, London
• 44. Guerrero M, Latosinski F, Nones M, Szupiany RN, Re M, Gaeta MG (2015) A sediment fluxes investigation for the 2-d modelling of large river morphodynamics. Adv Water Resour 81:186–198
• 45. Gunawardena Y, Ilic S, Pinkerton H, Romanowicz R (2009) Nonlinear transfer function modelling of beach morphology at Duck, North Carolina. Coast Eng 56(1):46–58
• 46. Gunn SR et al (1998) Support vector machines for classification and regression. ISIS Tech Rep 14(1):5–16
• 47. Halpern BS, McLeod KL, Rosenberg AA, Crowder LB (2008) Managing for cumulative impacts in ecosystem-based management through ocean zoning. Ocean Coast Manag 51(3):203–211
• 48. Harley MD, Kinsela MA, Sánchez-García E, Vos K (2019) Shoreline change mapping using crowd-sourced smartphone images. Coast Eng 150:175–189
• 49. Hashemi M, Ghadampour Z, Neill S (2010) Using an artificial neural network to model seasonal changes in beach profiles. Ocean Eng 37(14–15):1345–1356
• 50. Houser C, Hapke C, Hamilton S (2008) Controls on coastal dune morphology, shoreline erosion and barrier island response to extreme storms. Geomorphology 100(3–4):223–240
• 51. Howarth PJ, Wickware GM (1981) Procedures for change detection using landsat digital data. Int J Remote Sens 2(3):277–291
• 52. Hsu HH, Hoskins BJ (1989) Tidal fluctuations as seen in ECMWF data. Q J R Meteorol Soc 115(486):247–264
• 53. Hsu CW, Chang CC, Lin CJ et al (2003) A practical guide to support vector classification. Department of Computer Science National Taiwan University
• 54. Hu LY, Huang MW, Ke SW, Tsai CF (2016) The distance function effect on k-nearest neighbor classification for medical datasets. SpringerPlus 5(1):1304
• 55. Jan J, Hung SL, Chi S, Chern J (2002) Neural network forecast model in deep excavation. J Comput Civ Eng 16(1):59–65
• 56. Jangir B, Satyanarayana A, Swati S, Jayaram C, Chowdary V, Dadhwal V (2016) Delineation of spatio-temporal changes of shoreline and geomorphological features of Odisha coast of India using remote sensing and gis techniques. Nat Hazards 82(3):1437–1455
• 57. Kennedy AD, Dong X, Xi B, Xie S, Zhang Y, Chen J (2011) A comparison of MERRA and NARR reanalyses with the DOE ARM SGP data. J Clim 24(17):4541–4557
• 58. Kesikoğlu MH, Çiçekli SY, Kaynak T (2020) The identification of coastline changes from landsat 8 satellite data using artificial using artificial neural networks and K-nearest neighbor. Turk J Eng 4(1):47–56
• 59. Khaledian M, Isazadeh M, Biazar S, Pham Q (2020) Simulating Caspian sea surface water level by artificial neural network and support vector machine models. Acta Geophys 68:553–563
• 60. Kim IH, Lee HS, Song DS (2013) Time series analysis of shoreline changes in Gonghyunjin and Songjiho Beaches, South Korea using aerial photographs and remotely sensed imagery. J Coast Res 65:1415–1420
• 61. Kumar TS, Mahendra R, Nayak S, Radhakrishnan K, Sahu K (2010) Coastal vulnerability assessment for Orissa State, east coast of India. J Coast Res 26:523–534
• 62. Larson M, Capobianco M, Hanson H (2000) Relationship between beach profiles and waves at Duck, North Carolina, determined by canonical correlation analysis. Mar Geol 163(1–4):275–288
• 63. Lee YK, Eom J, Do JD, Kim BJ, Ryu JH (2019) Shoreline movement monitoring and geomorphologic changes of beaches using Lidar and UAVs Images on the Coast of the East Sea, Korea. J Coast Res 90(sp1):409–414
• 64. Li R, Liu JK, Felus Y (2001) Spatial modeling and analysis for shoreline change detection and coastal erosion monitoring. Mar Geod 24(1):1–12
• 65. Markose VJ, Rajan B, Kankara R, Selvan SC, Dhanalakshmi S (2016) Quantitative analysis of temporal variations on shoreline change pattern along Ganjam district, Odisha, East Coast of India. Environ Earth Sci 75(10):929
• 66. MERRA-2 (2017) Modern era retrospective-analysis for research and applications. https://gmao.gsfc.nasa.gov/reanalysis/MERRA-2/
• 67. Mishra M, Chand P, Pattnaik N, Kattel DB, Panda G, Mohanti M, Baruah UD, Chandniha SK, Achary S, Mohanty T (2019) Response of long-to short-term changes of the Puri coastline of Odisha (India) to natural and anthropogenic factors: a remote sensing and statistical assessment. Environ Earth Sci 78(11):338
• 68. Monalisha M, Panda G (2018) Coastal erosion and shoreline change in Ganjam coast along East Coast of India. J Earth Sci Clim Change 9:467
• 69. Montaño J, Coco G, Antolínez JA, Beuzen T, Bryan KR, Cagigal L, Castelle B, Davidson MA, Goldstein EB, Ibaceta R et al (2020) Blind testing of shoreline evolution models. Sci Rep 10(1):1–10
• 70. Morton R (1996) Geoindicators of coastal wetlands and shorelines. Geoindicators: assessment rapid environmental changes in earth systems. AA Balkema, Rotterdam, pp 207–230
• 71. Mukhopadhyay A, Mukherjee S, Mukherjee S, Ghosh S, Hazra S, Mitra D (2012) Automatic shoreline detection and future prediction: a case study on Puri Coast, Bay of Bengal, India. Eur J Remote Sens 45(1):201–213
• 72. Murthy VS, Gupta S, Mohanta D (2009) Distribution system insulator monitoring using video surveillance and support vector machines for complex background images. Int J Power Energy Convers 1(1):49–72
• 73. Nandi S, Ghosh M, Kundu A, Dutta D, Baksi M (2016) Shoreline shifting and its prediction using remote sensing and gis techniques: a case study of Sagar Island, West Bengal (India). J Coast Conserv 20(1):61–80
• 74. Nowakowski A (2015) Remote sensing data binary classification using boosting with simple classifiers. Acta Geophys 63(5):1447–1462
• 75. Peponi A, Morgado P, Trindade J (2019) Combining artificial neural networks and gis fundamentals for coastal erosion prediction modeling. Sustainability 11(4):975
• 76. Pescaroli G, Nones M, Galbusera L, Alexander D (2018) Understanding and mitigating cascading crises in the global interconnected system. Int J Disaster Risk Reduction 30:159–163
• 77. Piasecki A, Jurasz J, Adamowski JF (2018) Forecasting surface water-level fluctuations of a small glacial lake in Poland using a wavelet-based artificial intelligence method. Acta Geophys 66(5):1093–1107
• 78. Pierini JO, Lovallo M, Telesca L, Gómez EA (2013) Investigating prediction performance of an artificial neural network and a numerical model of the tidal signal at Puerto Belgrano, Bahia Blanca Estuary (Argentina). Acta Geophys 61(6):1522–1537
• 79. Puskarczyk E (2019) Artificial neural networks as a tool for pattern recognition and electrofacies analysis in Polish palaeozoic shale gas formations. Acta Geophys 67(6):1991–2003
• 80. Rajawat A, Chauhan H, Ratheesh R, Rode S, Bhanderi R, Mahapatra M, Kumar M, Yadav R, Abraham S, Singh S et al (2015) Assessment of coastal erosion along the Indian Coast on 1: 25,000 scale using satellite data of 1989–1991 and 2004–2006 time frames. Curr Sci 109:347–353
• 81. Ramesh R, Purvaja R, Senthil Vel A (2011) National assessment of shoreline change: Odisha coast. NCSCM/ MoEF Report 2011-01, 57 p., available at http://www.ncscm.org/reports.php
• 82. Ramesh R, R P, Vel S (2017) A shoreline change assessment for Odisha Coast; National Centre for Sustainable Coastal Management (NCSCM). Govt. of Odisha Report. National Centre for Sustainable Coastal Management (NCSCM). Accessed on 11 Nov 2017
• 83. Reichle RH, Koster RD, De Lannoy GJ, Forman BA, Liu Q, Mahanama SP, Touré A (2011) Assessment and enhancement of merra land surface hydrology estimates. J Clim 24(24):6322–6338
• 84. Rienecker MM, Suarez MJ, Gelaro R, Todling R, Bacmeister J, Liu E, Bosilovich MG, Schubert SD, Takacs L, Kim GK et al (2011) Merra: Nasa’s modern-era retrospective analysis for research and applications. J Clim 24(14):3624–3648
• 85. Ronco P, Fasolato G, Nones M, Di Silvio G (2010) Morphological effects of damming on lower Zambezi river. Geomorphology 115(1–2):43–55
• 86. Ryan T, Sementilli P, Yuen P, Hunt B (1991) Extraction of shoreline features by neural nets and image processing. Photogramm Eng Remote Sens 57(7):947–955
• 87. Saluja S, Singh AK, Agrawal S (2013) A study of edge-detection methods. Int J Adv Res Comput Commun Eng 2(1):994–999
• 88. Satapathy SC, Udgata SK, Biswal BN (2012) Proceedings of the international conference on frontiers of intelligent computing: theory and applications (FICTA), vol 199. Springer, Berlin
• 89. Schalkoff RJ (1997) Artificial neural networks, vol 1. McGraw-Hill, New York
• 90. Shen S, Ostrenga D, Vollmer B, Li A, Meyer D (2019) MERRA-2 data and analytic services at NASA GES DISC for climate extremes study. In: 16th AOGS-Annual meeting of asia oceania geosciences society, July 28, 2019–August 02, 2019, Singapore
• 91. Shen S, Ostrenga DM, Bosilovich MG, Li AW, Meyer DJ (2020) Near 40 years MERRA-2 data at NASA GES DISC-opportunity and challenge to support extremes study. In: 100th AMS Annual Meeting, January 12, 2020–January 16, 2020, Boston, United States
• 92. Shrivakshan G, Chandrasekar C (2012) A comparison of various edge detection techniques used in image processing. Int J Comput Sci Issues: IJCSI 9(5):269
• 93. Simeoni U, Corbau C (2009) A review of the delta po evolution (Italy) related to climatic changes and human impacts. Geomorphology 107(1–2):64–71
• 94. Small C, Nicholls RJ (2003) A global analysis of human settlement in coastal zones. J Coast Res 19:584–599
• 95. Sobel I, Feldman G (1968) A 3 ×× 3 isotropic gradient operator for image processing. A talk at the Stanford artificial project, pp 271–272
• 96. Stockdon HF, Doran KS, Sallenger AH Jr (2009) Extraction of lidar-based dune-crest elevations for use in examining the vulnerability of beaches to inundation during hurricanes. J Coast Res 53:59–65
• 97. Suanez S, Cariolet JM, Cancouët R, Ardhuin F, Delacourt C (2012) Dune recovery after storm erosion on a high-energy beach: Vougot Beach, Brittany (France). Geomorphology 139:16–33
• 98. The Indian Tide Tables-Part 1,1995: Indian and Selected Foreign Ports (1994) Surveyor general of India, printed by survey of India, Dehradun
• 99. Tsekouras GE, Trygonis V, Maniatopoulos A, Rigos A, Chatzipavlis A, Tsimikas J, Mitianoudis N, Velegrakis AF (2018) A hermite neural network incorporating artificial bee colony optimization to model shoreline realignment at a reef-fronted beach. Neurocomputing 280:32–45
• 100. USGS (2017) United states geological survey. https://earthexplorer.usgs.gov
• 101. Valiela I (2004) Global coastal change. Blackwell, Oxford
• 102. Valipour M, Tian D (2018) Comparing soil moisture dynamics in climate reanalyses, land surface models, and remote sensing retrievals over the continental united states. In: AGU Fall Meeting Abstracts
• 103. Valipour M, Banihabib M, Behbahani S (2012) Monthly inflow forecasting using autoregressive artificial neural network. J Appl Sci 12(20):2139–2147
• 104. Valipour M, Banihabib ME, Behbahani SMR (2013) Comparison of the arma, arima, and the autoregressive artificial neural network models in forecasting the monthly inflow of dez dam reservoir. J Hydrol 476:433–441
• 105. Vapnik V (1963) Pattern recognition using generalized portrait method. Autom Remote Control 24:774–780
• 106. Vapnik VN, Chervone AY (1965) On a class of pattern-recognition learning algorithms. Autom Remote Control 25(6):838
• 107. Varrani A, Nones M, Gupana R (2019) Long-term modelling of fluvial systems at the watershed scale: examples from three case studies. J Hydrol 574:1042–1052
• 108. Vijayarani S, Vinupriya M (2013) Performance analysis of Canny and Sobel edge detection algorithms in image mining. Int J Innov Res Comput Commun Eng 1(8):1760–1767
• 109. Vincent OR, Folorunso O et al (2009) A descriptive algorithm for sobel image edge detection. In: Proceedings of informing science & IT education conference (InSITE), vol 40. Informing Science Institute California, pp 97–107
• 110. Wang J, Li B, Gao Z, Wang J (2019) Comparison of ECMWF significant wave height forecasts in the China sea with buoy data. Weather Forecast 34(6):1693–1704
• 111. White K, El Asmar HM (1999) Monitoring changing position of coastlines using Thematic Mapper imagery, an example from the Nile Delta. Geomorphology 29(1–2):93–105
• 112. Zhang X, Wang Z (2010) Coastline extraction from remote sensing image based on improved minimum filter. In: 2010 second IITA international conference on geoscience and remote sensing, vol 2. IEEE, pp 44–47

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021)

Identyfikatory

DOI

10.1007/s11600-020-00454-9