Coastline and shoreline change assessment in sandy coasts based on machine learning models and high-resolution satellite images
Author affiliations
DOI:
https://doi.org/10.15625/2615-9783/18407Keywords:
Erosion; Unet; Support Vector Machine; Random Forest; Google EarthAbstract
Changes to the coastline or shoreline arise from the water's dynamic interaction with the land surface, which is triggered by ocean currents, waves, and winds. Various methods have been proposed to identify and monitor coastlines and shorelines, but their outcomes are uncertain. This study proposes indicators for identifying coastlines and shorelines in the fields and on the remote sensing data. Different pixel- and object-based machine learning (ML) models were built to automatically interpret coastlines and shorelines from high-resolution remote sensing images and monitor coastal erosion in Vietnam. Two pixel-based models using Random Forest and SVM structures and eight object-based models using U-Net, and U-Net3+ structures were trained. All models were trained using the high-resolution images gathered using Google Earth Pro as input data. The U-Net achieves the most remarkable performance of 98% with a loss function of 0.16 when utilizing an input-image size of 512×512.
Object-based models have shown higher performance in analyzing coastlines and shorelines with linear and continuous structures than pixel-based models. Additionally, the coastline is appropriate to evaluate coastal erosion induced by the effect of sea-level rise during storms. At the same time, the shoreline is suited to observe seasonal tidal fluctuations or the instantaneous movements of current waves. Under the pressure of tourist development, the coasts in Danang and Quang Nam provinces have been eroded in the last 10 years. River and ocean currents also cause erosion in the southern Cua Dai estuary. In the future, the trained U-Net model can be used to monitor the changes in coastlines and shorelines worldwide.
Downloads
References
Albawi S., Mohammed T.A., Al-Zawi S., 2018. Understanding of a convolutional neural network. Proc. 2017 Int. Conf. Eng. Technol. ICET 2017 2018-Janua, 1-6. https://doi.org/10.1109/ICEngTechnol.2017.8308186.
Alom M.Z., Taha T.M., Yakopcic C., Westberg S., Sidike P., Nasrin M.S., Hasan M., Van Essen B.C., Awwal A.A.S., Asari, V.K., 2019. A state-of-the-art survey on deep learning theory and architectures. Electron., 8, 1-67. https://doi.org/10.3390/electronics8030292.
Berhane T.M., Lane C.R., Wu Q., Autrey B.C., Anenkhonov O.A., Chepinoga V.V., Liu H., 2018. Decision-tree, rule-based, and random
forest classification of high-resolution multispectral imagery for wetland mapping and inventory. Remote Sens., 10(4), 580. https://doi.org/10.3390/rs10040580.
Boak E.H., Turner I.L., 2005. Shoreline Definition and Detection: A Review. J. Coast. Res., 214, 688-703. https://doi.org/10.2112/03-0071.1.
Cervantes J., Garcia-Lamont F., Rodríguez-Mazahua L. Lopez A., 2020. A comprehensive survey on support vector machine classification: Applications, challenges and trends. Neurocomputing, 408, 189-215.
Cham D.D., Nguyen H.S., Nguyen K.A., 2020. Coastal Vulnerability Assessments due to climate change in coastal sand-bar in Quang Binh, Quang Tri, Thua Thien Hue to propose sustainable likelihood. Science and Technics Publishing House, Hanoi, 364p.
Dai M., Leng X., Xiong B., Ji K., 2020. Sea-land segmentation method for SAR images based on improved BiSeNet. J. Radars, 9, 886-897. https://doi.org/10.12000/JR20089.
Dang K.B., Dang V.B., Bui Q.T., Nguyen V.V., Pham T.P.N., Ngo V.L., 2020a. A Convolutional Neural Network for Coastal Classification Based on ALOS and NOAA Satellite Data. IEEE Access, 8, 11824-11839. https://doi.org/10.1109/ACCESS.2020.2965231.
Dang K.B., Dang V.B., Ngo V.L., Vu K.C., Nguyen H., Nguyen D.A., Nguyen T.D.L., Pham T.P.N., Giang T.L., Nguyen H.D., Hieu Do T., 2022a. Application of deep learning models to detect coastlines and shorelines. J. Environ. Manage, 320, 115732. https://doi.org/10.1016/j.jenvman.2022.115732.
Dang K.B., Ha T., Nguyen T., Nguyen H.D., Truong Q.H., Vu T.P., 2022b. U-shaped deep-learning models for island ecosystem type classification a case study in Con Dao Island of Vietnam. One Ecosyst, 7, 23. https://doi.org/10.3897/oneeco.7.e79160.
Dang K.B., Ngo C.C., Ngo V.L., Dang V.B., 2022c. Coastal Vulnerability Assessment in Son Tra - Cua Dai region. VNU J. Sci. Earth Environ. Sci., 38,
-65. https://doi.org/10.25073/2588-1094/vnuees.4842.
Dang K.B., Nguyen M.H., Nguyen D.A., Phan T.T.H., Giang T.L., Pham H.H., Nguyen T.N., Van Tran T.T., Bui D.T., 2020b. Coastal wetland classification with deep u-net convolutional networks and sentinel-2 imagery: A case study at the Tien Yen estuary of Vietnam. Remote Sens., 12, 1-26. https://doi.org/10.3390/rs12193270.
Dang K.B., Nguyen T.T., Ngo H.H., Burkhard B., Müller F., Dang V.B., Nguyen H., Ngo V.L., Pham T.P.N., 2021. Integrated methods and scenarios for assessment of sand dunes ecosystem services. J. Environ. Manage, 289, 112485. https://doi.org/10.1016/j.jenvman.2021.112485.
Diakogiannis F.I., Waldner F., Caccetta P., Wu C., 2020. ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data. ISPRS J. Photogramm. Remote Sens., 162, 94-114. https://doi.org/10.1016/j.isprsjprs.2020.01.013.
Dong T., Shen Y., Zhang J., Ye Y., Fan J., 2019. Progressive cascaded convolutional neural networks for single tree detection with google earth imagery. Remote Sens, 11(15), 1786. https://doi.org/10.3390/rs11151786.
Doody J.P., 2005. Sand dune inventory of Europe. Proc. Dunes Estuaries Int. Conf. Nat. Restor. Pract. Eur. Coast. Habitats, 45-54.
Duong H.H., Ngo T.T.H., Tran V.P., Nguyen D.D., Avand M., Nguyen H.D., Amiri M., Van Le H., Prakash I., Binh Thai P., 2022. Development and application of hybrid artificial intelligence models for groundwater potential mapping and assessment. Vietnam Journal of Earth Sciences, 44(3), 410-429. https://doi.org/https://doi.org/10.15625/2615-9783/17240.
Escudero-Castillo M., Felix-Delgado A., Silva R., Mariño-Tapia I., Mendoza E., 2018. Beach erosion and loss of protection environmental services in Cancun, Mexico. Ocean Coast. Manag, 156, 183-197. https://doi.org/10.1016/j.ocecoaman.2017.06.015.
Fernández J.G., Abdellaoui I.A., Mehrkanoon S., 2020. Deep coastal sea elements forecasting using U-Net based models, 252, 27. 109445.
Gallina V., Torresan S., Zabeo A., Critto A., Glade T., Marcomini A., 2020. A multi-risk methodology for the assessment of climate change impacts in coastal zones. Sustain, 12(9), 3697. https://doi.org/10.3390/su12093697.
Gens R., 2010. Remote sensing of coastlines: detection, extraction and monitoring. Int. J. Remote Sens., 31, 1819-1836.
Gordana K., Avdan U., 2019. Evaluating Sentinel-2 Red-Edge Bands for Wetland Classification. Proceedings 18, 12. https://doi.org/10.3390/ecrs-3-06184.
Gulli A., 2017. Deep Learning with Keras - Implement neural networks with Keras on Theano and TensorFlow. Packt Publishing Ltd., Birmingham, UK, 318p.
Hanh P.T.T., Furukawa M., 2007. Impact of sea level rise on coastal zone of Vietnam. Bull. Coll. os Cience Univ. TGE Ryukyus, 84, 45-59.
Hanley M.E., Hoggart S.P.G.G., Simmonds D.J., Bichot A., Colangelo M.A., Bozzeda F., Heurtefeux H., Ondiviela B., Ostrowski R., Recio M., Trude R., Zawadzka-Kahlau E., Thompson R.C., 2014. Shifting sands? Coastal protection by sand banks, beaches and dunes. Coast. Eng., 87, 136-146. https://doi.org/10.1016/j.coastaleng.2013.10.020.
Hassan S.M., Sadek M.F., 2017. Geological mapping and spectral based classification of basement rocks using remote sensing data analysis: The Korbiai-Gerf nappe complex, South Eastern Desert, Egypt. J. African Earth Sci., 134, 404-418. https://doi.org/10.1016/j.jafrearsci.2017.07.006
Hatamizadeh A., Terzopoulos D., Myronenko A., 2020. Edge-Gated CNNs for Volumetric Semantic Segmentation of Medical Images, 8-17. https://doi.org/10.1101/2020.03.14.992115.
Heidler K., Mou L., Baumhoer C., Dietz A., Zhu X.X., 2022. HED-UNet: Combined Segmentation and Edge Detection for Monitoring the Antarctic Coastline. IEEE Trans. Geosci. Remote Sens., 60, 1-13. https://doi.org/10.1109/TGRS.2021.3064606.
Hoang T.T.H., Dang K.B., Anton V.R., 2022. Comprehensive assessment of coastal tourism potential in Vietnam. Vietnam J. Earth Sci., 44, 535-558. https://doi.org/https://doi.org/10.15625/2615-9783/17374.
Hoang V.L., Nguyen Tien Thanh, Vu T.T., Nguyen Thanh Tung, Nguyen L.A., Dao B.D., Le V.D., Tran N.D., Nguyen H.H., 2021. Holocene sediementation offshore Southeast Vietnam based on geophysical interpretation and sediment composition analysis. Vietnam J. Earth Sci., 43(3), 336-379. https://doi.org/https://doi.org/10.15625/2615-9783/16268.
Hu Q., Wu W., Xia T., Yu Q., Yang P., Li Z., Song Q., 2013. Exploring the use of google earth imagery and object-based methods in land use/cover mapping. Remote Sens., 5, 6026-6042. https://doi.org/10.3390/rs5116026.
Huang H., Lin L., Tong R., Hu H., Zhang Q., Iwamoto Y., Han X., Chen Y.W., Wu J., 2020. UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation. ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc. 2020-May, 1055-1059. https://doi.org/10.1109/ICASSP40776.2020.9053405.
Karatzoglou A., Meyer D., Hornik K., 2006. Support Vector Algorithm in R. J. Stat. Softw., 15, 1-28.
Kumar L., Afzal M.S., Afzal M.M., 2020. Mapping shoreline change using machine learning: a case study from the eastern Indian coast. Acta Geophys., 68, 1127-1143. https://doi.org/10.1007/s11600-020-00454-9.
Le H.A., Nguyen T.A., Nguyen D.D., Prakash I., 2020. Prediction of soil unconfined compressive strength using Artificial Neural Network
Model. Vietnam J. Earth Sci., 42(3), 255-264. https://doi.org/https://doi.org/10.15625/0866-7187/42/3/15342.
Le Q.T., Dang K.B., Giang T.L., Tong T.H.A., Nguyen V.G., Nguyen T.D.L., Yasir M., 2022. Deep learning model development for detecting coffee tree changes based on Sentinel-2 imagery in Vietnam. IEEE Access, 10, 109097-109107. https://doi.org/10.1109/ACCESS.2022.3203405.
Loi D.T., Khac D.V., Hung D.N., Dong N.T., Vinh D.X., Weber C., 2021. Monitoring of coastline change using Sentinel-2A and Landsat 8 data, a case study of Cam Pha city - Quang Ninh province. Vietnam J. Earth Sci., 43(3), 249-272. https://doi.org/https://doi.org/10.15625/2615-9783/16066.
Martínez C., Contreras-López M., Winckler P., Hidalgo H., Godoy E., Agredano R., 2018. Coastal erosion in central Chile: A new hazard? Ocean Coast. Manag., 156, 141-155. https://doi.org/10.1016/j.ocecoaman.2017.07.011.
Mineur F., Arenas F., Assis J., Davies A.J., Engelen A.H., Fernandes F., Malta E. Jan, Thibaut T., Van Nguyen T., Vaz-Pinto F., Vranken S., Serrão E.A., De Clerck O., 2015. European seaweeds under pressure: Consequences for communities and ecosystem functioning. J. Sea Res., 98, 91-108. https://doi.org/10.1016/j.seares.2014.11.004.
Moore A., 2001. Cross-validation for detecting and preventing overfitting. Sch. Comput. Sci. Carneigie Mellon, 1-27.
Nazeer M., Waqas M., Shahzad M.I., Zia I., Wu W., 2020. Coastline vulnerability assessment through landsat and cubesats in a coastal mega city. Remote Sens., 12, 1-24. https://doi.org/10.3390/rs12050749.
Nguyen C.N., Nguyen V.D., Ha T.G., Dinh Q. Van, Nguyen L.M., Huang B.-S., Pham T.T., Nguyen T.H., Le Q.K., Nguyen H.H., 2022a. Automatic earthquake detection and phase picking in Muong Te, Lai Chau region: an application of machine learning in observational seismology in Vietnam. Vietnam J. Earth Sci., 44(3), 430-446. https://doi.org/https://doi.org/10.15625/2615-9783/17253.
Nguyen D.T., Le T.T., Vuong A.T., Nguyen Q.V., 2020. Identify some aerodynamic parameters of a airplane using the spiking neural network.pdf. Vietnam J. Earth Sci., 42(3), 276-287. https://doi.org/https://doi.org/10.15625/0866-7187/42/3/15355.
Nguyen T.A., Ly H.B., Jaafari A., Pham T.B., 2020. Estimation of friction capacity of driven piles in clay using artificial Neural Network.pdf. Vietnam J. Earth Sci., 42(3), 265-275. https://doi.org/https://doi.org/10.15625/0866-7187/42/3/15182.
Nhu V.-H., Bui T.T., My L.N., Vuong H., Duc H.N., 2022. A new approach based on integration of random subspace and C4.5 decision tree learning method for spatial prediction of shallow landslides. Vietnam J. Earth Sci., 44(3), 327-342. https://doi.org/https://doi.org/10.15625/2615-9783/16929.
Nirmala B.J., Miriyala S., Ratnam D.V., Dutta G., 2022. Assessment of machine learning techniques for prediction of integrated water vapor using meteorological data. Vietnam J. Earth Sci., 44(4), 521-534. https://doi.org/https://doi.org/10.15625/2615-9783/17373.
Pajak M.J., Leatherman S., 2002. The high water line as shoreline indicator. J. Coast. Res., 18, 329-337.
Pham B.T., Prakash I., Khosravi K., Chapi K., Trinh P.T., Ngo T.Q., Hosseini S.V, Bui D.T., 2018. A comparison of Support Vector Machines and Bayesian algorithms for landslide susceptibility modelling. Geocarto Int., 123. https://doi.org/10.1080/10106049.2018.1489422.
Pham H.N., Dang K.B., Nguyen T.V., Tran N.C., Ngo X.Q., Nguyen D.A., Phan T.T.H., Nguyen T.T., Guo W., Ngo H.H., 2022. A new deep learning approach based on bilateral semantic segmentation models for sustainable estuarine wetland ecosystem management. Sci. Total Environ., 838, 155826. https://doi.org/10.1016/j.scitotenv.2022.155826.
Pham T.B., Nguyen D.D., Bui T.Q.A., Nguyen M.D., Vu T.T., Prakash I., 2022. Estimation of load-bearing capacity of bored piles using machine learning models. Vietnam J. Earth Sci., 44(4), 470-480. https://doi.org/https://doi.org/10.15625/2615-9783/17177.
Pham T.B., Singh S.K., Ly H.B., 2020. Using Artificial Neural Network (ANN) for prediction of soil coefficient of consolidation. Vietnam J. Earth Sci., 42, 311-319. https://doi.org/https://doi.org/10.15625/0866-7187/42/4/15008.
Phan H.M., Ye Q., Reniers A.J.H.M., Stive M.J.F., 2019. Tidal wave propagation along The Mekong deltaic coast. Estuar. Coast. Shelf Sci., 220, 73-98. https://doi.org/10.1016/j.ecss.2019.01.026.
Piragnolo M., Masiero A., Pirotti F., 2017. Comparison of Random Forest and Support Vector Machine classifiers using UAV remote sensing imagery. Geophys. Res. Abstr. EGU Gen. Assem., 19, 2017-15692.
Pollard E., Corns A., Henry S., Shaw R., 2020. Coastal Erosion and the Promontory Fort: Appearance and Use during Late Iron Age and Early Medieval County Waterford, Ireland. Sustainability, 12, 5794. https://doi.org/10.3390/su12145794.
Ronneberger O., Fischer P., Brox T., 2015. U-net: Convolutional networks for biomedical image segmentation. Lect. Notes Comput. Sci.
(including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), 9351, 234-241. https://doi.org/10.1007/978-3-319-24574-4_28.
Sowmya K., Sri M.D., Bhaskar A.S., Jayappa K.S., 2019. Long-term coastal erosion assessment along the coast of Karnataka, west coast of India. Int. J. Sediment Res., 34, 335-344. https://doi.org/10.1016/j.ijsrc.2018.12.007.
Stockdon H.F., et al., 2009. Extraction of lidar- based dune-crest elevations for use in examining the vulner- ability of beaches to inundation during hurricanes. J. Coast. Res., 53, 59-65.
Tian S., Zhang X., Tian J., Sun Q., 2016. Random forest classification of wetland landcovers from multi-sensor data in the arid region of
Xinjiang, China. Remote Sens., 8, 1-14. https://doi.org/10.3390/rs8110954.
Titus J.G., Richman C., 2001. Maps of lands vulnerble to sea level rise: Modeled elevations along the US Atlantic and Gulf coasts. Clim. Res., 18, 205-228. https://doi.org/10.3354/cr018205.
Tong X.Y., Xia G.S., Lu Q., Shen H., Li S., You S., Zhang L., 2020. Land-cover classification with high-resolution remote sensing images using transferable deep models. Remote Sens. Environ., 237, 111322. https://doi.org/10.1016/j.rse.2019.111322.
Toure S., Diop O., Kpalma K., Maiga A.S., 2019. Shoreline detection using optical remote sensing: A review. ISPRS Int. J. Geo-Information, 8(75), 21. https://doi.org/10.3390/ijgi8020075.
Tran V.Q., Prakash I., 2020. Prediction of soil loss due to erosion using support vector machine model. Vietnam J. Earth Sci., 42(3), 247-254. https://doi.org/https://doi.org/10.15625/0866-7187/42/3/15050.
Veettil B.K., Costi J., Marques W.C., Tran X.L., Quang N.X., Van D.D., Hoai P.N., 2020. Coastal environmental changes in Southeast Asia: A study from Quang Nam Province, Central Vietnam. Reg. Stud. Mar. Sci., 39, 101420. https://doi.org/10.1016/j.rsma.2020.101420.
Vinchon C., Idier D., Garcin M., Y. Balouin, Mallet C., Aubié S., Closset L., 2006. Response of the Coastline to Climate Change. Specific Report for the RESPONSE Project LIFE-Environment programm: Evolution of coastal risk (erosion and marine flooding) on the Aquitaine and Languedoc- Roussillon pilot regions. Final report. BRGM/RP-54718.
Vu V.P., Nguyen H., Hoang T.V., Nguyen B., Dao M.T., 2004. Some results of geomorphological research on the modern coast of Vietnam (in Vietnamese). VNU J. Sci. Earth Environ. Sci., 4, 73-81.
Xue Su Y., Xu H., Jiao Yan L., 2017. Support vector machine-based open crop model (SBOCM): Case of rice production in China. Saudi J. Biol. Sci., 24, 537-547. https://doi.org/10.1016/j.sjbs.2017.01.024.
Yadav A., Dodamani B.M., Dwarakish, 2017. Shoreline Change: A Review, in: Mangalore Institute of Technology & Engineering. Moodbidri. India, 5-10.
Yang W., Wang W., Zhang X., Sun S., Liao Q., 2019. Lightweight Feature Fusion Network for Single Image Super-Resolution. IEEE Signal Process. Lett., 26, 538-542. https://doi.org/10.1109/LSP.2018.2890770.
Downloads
Published
How to Cite
Issue
Section
