Geomechanics and Engineering

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Landslide mapping using a combination of sentinel-2 multi spectral instruments and GIS data at Namwon, Jeollabuk-do, South Korea

  • Hwan-Hui Lim (Water Infrastructure Research Center, K-water Research Institute) ;
  • Seung-Min Lee (The 21st Infantry Division of the Republic of Korea Armed Forces) ;
  • Enok Cheon (Water Infrastructure Research Center, K-water Research Institute) ;
  • Eu Song (Landslide Team, Department of Forest Environment and Conservation, National Institute of Forest Science) ;
  • Jun-Seo Jeon (Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Seung-Rae Lee (Water Infrastructure Research Center, K-water Research Institute)
  • Received : 2024.03.05
  • Accepted : 2024.11.11
  • Published : 2024.11.25
⟨ Previous Next ⟩

Abstract

With the recent development of satellite, aerial, and remote sensing technologies, it is easy to produce landslide inventory maps over a large area. In this study, the object-based framework was designed to address the limitations inherent in the pixel-based deep learning (DL) methodology. This framework explores the potential of combining Sentinel-2 MultiSpectral Instrument (MSI) satellite imagery and digital elevation models (DEMs) to enhance shallow landslide mapping across diverse terrains comprehensively. The study area for analysis and verification was selected as Jucheon-myeon, Namwon-si, and Jeollabuk-do, where significant large-scale landslides and slope failures occurred in 2020. As a result, the application of this framework led to the classification of 68 candidate sites spanning an area of 0.5 hectares or more. Site surveying was conducted on 20 random sites with a 1ha or more scale. Furthermore, six sites were selected where satellite imagery could discern the damaged areas. At these locations, the damaged area estimated by the framework was compared with the actual observed damaged area to assess accuracy. These rapid and cost-effective landslide mapping techniques can accurately estimate the location and extent of landslides and enhance the precision of sensitivity models and land management strategies.

Keywords

Acknowledgement

This paper was supported by the Ministry of Land, Infrastructure and Transport of the Korean government (Project No.: RS-2020-KA157130) and Korea Electric Power Corporation (Grant number: R22XO05-05).

References

  1. Amatya, P., Kirschbaum, D. and Stanley, T. (2019), "Use of very high-resolution optical data for landslide mapping and susceptibility analysis along the Karnali highway", Remote Sens., 11, 2284. https://doi.org/10.3390/rs11192284.
  2. Amatya, P., Kirschbaum, D., Stanley, T. and Tanyas, H. (2021), "Landslide mapping using object-based image analysis and open source tools", Eng. Geol., 282, 106000. https://doi.org/10.1016/j.enggeo.2021.106000.
  3. Baatz, M. and Schape, A. (2000), "Multiresolution segmentation- an optimization approach for high quality multi-scale image segmentation‖", Agewandte Geoinfomatik Symposium., 12-23.
  4. Barlow, J., Franklin, S. and Martin, Y. (2006), "High spatial resolution satellite imagery, DEM derivatives, and image segmentation for the detection of mass wasting processes", Photogramm. Eng. Rem. S., 6, 687-692. https://doi.org/10.14358/PERS.72.6.687.
  5. Ben-Dor, E. (2002), "Quantitative remote sensing of soil properties. 173-243".
  6. Benz, Ursula C., Peter, H., Gregor, W., Iris, L., Markus, H. (2004), "Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information", ISPRS J. Photogramm. Rem. S., 58(3-4), 239-258. https://doi.org/10.1016/j.isprsjprs.2003.10.002.
  7. Castro, R. and Chuvieco, E. (1998), "Modeling forest fire danger from geographic information systems", Geocarto Int., 13(1), 15-23. https://doi.org/10.1080/10106049809354624.
  8. Comert, R., Avdan, U., Gorum, T. and Nefeslioglu, H.A. (2019), "Mapping of shallow landslides with object-based image analysis from unmanned aerial vehicle data", Eng. Geol., 260, 105264. https://doi.org/10.1016/j.enggeo.2019.105264.
  9. Cracknell, A.P.. (2001), "The exciting and totally unanticipated success of the AVHRR in applications for which it was never intended", Adv. Sp. Res., 28(1), 233-240. https://doi.org/10.1016/S0273-1177(01)00349-0.
  10. Deng, Y., Wu, C., Li, M. and Chen, R. (2015), "RNDSI: A ratio normalized difference soil index for remote sensing of urban/suburban environments", Int. J. Appl. Earth Observ. Geoinformation, 39, 40-48. https://doi.org/10.1016/j.jag.2015.02.010.
  11. Gao, B.C. (1996), "NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space", Remote Sens. Environ., 58(3), : 257-266. https://doi.org/10.1016/S0034-4257(96)00067-3.
  12. Gao, Y.A.N., Mas, J.F., Kerle, N. and Navarrete Pacheco, J.A. (2011), "Optimal region growing segmentation and its effect on classification accuracy", Int. J. Remote Sens., 32(13), 3747-3763. https://doi.org/10.1080/01431161003777189
  13. Ghiasi, V., Pauzi, N.I.M., Karimi, S. and Yousefi, M. (2023), "Landslide risk zoning using support vector machine algorithm", Geomech. Eng., 34(3), 267, https://doi.org/10.12989/gae.2023.34.3.267.
  14. Goa, Y.A.N., Mas, J.F. and Navarrete Pacheco, J.A. (2011), "Optimal region growing Segmentation And Its Effect on Classification Accuracy‖", Int. J. Remote Sens., 32(13), 3747-3763. https://doi.org/10.1080/01431161003777189.
  15. Guzzetti, F., Mondini, A.C., Cardinali, M., Fiorucci, F., Santangelo, M. and Chang, K.T. (2012), "Landslide inventory maps: new tools for an old problem", Earth Sci. Rev., 112, 42-66. https://doi.org/10.1016/j.earscirev.2012.02.001.
  16. He, K., Ma, G., Hu, X., Liu, B. and Han, M. (2022), "The July 2, 2017, Lantian landslide in Leibo, China: mechanisms and mitigation measures", Geomech. Eng., 28(3), 283-298. https://doi.org/10.12989/gae.2022.28.3.283
  17. Holbling, D., Abad, L., Dabiri, Z., Prasicek, G., Tsai, T.T. and Argentin, A.L. (2020), "Mapping and analyzing the evolution of the Butangbunasi landslide using landsat time series with respect to heavy rainfall events during typhoons", Appl. Sci., 10, 630. https://doi.org/10.3390/app10020630.
  18. Hua, Y., Wang, X., Li, Y., Xu, P. and Xia, W. (2021), "Dynamic development of landslide susceptibility based on slope unit and deep neural networks", Landslides, 18, 281-302. https://doi.org/10.1007/s10346-020-01444-0.
  19. Huang, F., Zhang, J., Zhou, C., Wang, Y., Huang, J. and Zhu, L. (2020), "A deep learning algorithm using a fully connected sparse autoencoder neural network for landslide susceptibility prediction", Landslides, 17, 217-229. https://doi.org/10.1007/s10346-019-01274-9.
  20. Hussain, M., Chen, D., Cheng, A., Wei, H. and Stanley, D. (2013), "Change detection from remotely sensed images: From pixel-based to object-based approaches", ISPRS J. Photogramm. Rem. S., 80, 91-106. https://doi.org/10.1016/j.isprsjprs.2013.03.006.
  21. Jakob, M., Hungr, O. and Jakob, D.M. (2005), Debris-flow hazards and related phenomena.
  22. Jitt-Aer, K., Wall, G., Jones, D. and Teeuw, R. (2022), "Use of GIS and dasymetric mapping for estimating tsunami-affected population to facilitate humanitarian relief logistics: a case study from Phuket, Thailand", Nat. Hazards, 113(1), 185-211.
  23. Keyport, R.N., Oommen, T., Martha, T.R., Sajinkumar, K.S. and Gierke, J.S. (2018), "A comparative analysis of pixel-and object-based detection of landslides from very high-resolution images", Int. J. Appl. Earth Obs. Geoinf., 64, 1-11. https://doi.org/10.1016/j.jag.2017.08.015.
  24. Korea Forest Service. (2020), Landslide damage status. http://sansatai.forest.go.kr/gis/main.do;jsessionid=JZOrYq15hn0d19d74MGj7yGHjYXvAP1oYh2NcaUiC81TqDXOVaN19nppMaMcVfXM.ext-fdiswas1_servlet_ldm#mhms7. Accessed August 31 2020.
  25. Kucharczyk, M., Hay, G.J., Ghaffarian, S. and Hugenholtz, C.H. (2020), "Geographic object-based image analysis: a primer and future directions", Remote Sens., 12(12), 2012. https://doi.org/10.3390/rs12122012.
  26. Lee., D.H., Cheon, E., Lim, H.H., Choi, S.K., Kim, Y.T. and Lee, S.R. (2021), "An artificial neural network model to predict debris-flow volumes caused by extreme rainfall in the central region of South Korea", Eng. Geol., 281, 105979. https://doi.org/10.1016/j.enggeo.2020.105979.
  27. Liu, L.L., Yang, C. and Wang, X.M. (2021), "Landslide susceptibility assessment using feature selection-based machine learning models", Geomech. Eng., 25(1), 1-16. https://doi.org/10.12989/gae.2021.25.1.001.
  28. Lohmus, K., Oja, T. and Lasn, R. (1989), "Specific root area: a soil characteristic", Plant Soil, 119, 245-249.
  29. Lu, P., Stumpf, A., Kerle, N., and Casagli, N. (2011), "Object-oriented change detection for landslide rapid mapping", IEEE Geosci. Remote Sens. Lett., 8(4), 701-705. https://doi.org/10.1109/LGRS.2010.2101045.
  30. Mahlein, A.K., Rumpf, T., Welke, P., Dehne, H.W., Plumer, L., Steiner, U. and Oerke, E.C. (2013), "Development of spectral indices for detecting and identifying plant diseases", Remote Sens. Environ., 128, 21-30. https://doi.org/10.1016/j.rse.2012.09.019.
  31. Major, D.J., Baret, F. and Guyot, G. (1990), "A ratio vegetation index adjusted for soil brightness", Int. J. Remote Sens., 11(5), 727-740. https://doi.org/10.1080/01431169008955053.
  32. Maqsoom, A., Aslam, B., Khalil, U., Kazmi, Z.A., Azam, S. Mehmood, T. and Nawaz, A. (2022), "Landslide susceptibility mapping along the China Pakistan Economic Corridor (CPEC) route using multi-criteria decision-making method", Model. Earth Syst. Environ., 8, 1519-1533.
  33. Martha, T.R., Kerle, N., Jetten, V., van Westen, C.J. and Kumar, K.V. (2010), "Characterising spectral, spatial and morphometric properties of landslides for semi-automatic detection using object-oriented methods", Geomorphology, 116(1-2), 24-36. https://doi.org/10.1016/j.geomorph.2009.10.004.
  34. Meneses-Tovar, C.L. (2011), "NDVI as indicator of degradation", Unasylva.
  35. Moosavi, V., Talebi, A. and Shirmohammadi, B. (2014), "Producing a landslide inventory map using pixel-based and object-oriented approaches optimized by Taguchi method", Geomorphology, 204, 646-656. https://doi.org/10.1016/j.geomorph.2013.09.012.
  36. Nanehkaran, Y.A., Mao, Y., Azarafza, M., Kockar, M.K. and Zhu, H.H. (2021), "Fuzzy-based multiple decision method for landslide susceptibility and hazard assessment: A case study of Tabriz, Iran", Geomech. Eng., 24(5), 407-418. https://doi.org/10.12989/gae.2021.24.5.407.
  37. Nitze, I., Schulthess, U. and Asche, H. (2012), "Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification", Proceedings of the 4th GEOBIA, Rio de Janeiro, Brazil.
  38. Oruc, M., Marangoz, A.M. and Buyuksalih, G. (2004), "Comparison of pixel-based and object-oriented classification approaches using Landsat-7 ETM spectral bands", Istanbul, Turkyie.
  39. Park, D.W., Vasu, N.N., Lee, S.R., Kang, S.H. and Park, J.Y. (2016), "Coupled model for simulation of landslides and debris flows at local scale", Nat. Hazards, 81(3), 1653-1682.
  40. Qin, R., Huang, X., Gruen, A. and Schmitt, G. (2015), "Object-based 3-D building change detection on multitemporal stereo images", IEEE J. Select. Topics Appl. Earth Observ. Remote Sens., 8(5), 2125-2137. https://doi.org/10.1109/JSTARS.2015.2424275.
  41. Rindraharisaona, E.J., Rechou, A., Fontaine, F.R., Barruol, G., Stamenoff, P., Boudevillain, B. and Delcher, E. (2022), "Seismic signature of rain and wind inferred from seismic data", Earth Sp. Sci., 9(10), e2022EA002328. https://doi.org/10.1029/2022EA002328.
  42. Scaioni, M., Longoni, L., Melillo, V. and Papini, M. (2014), "Remote sensing for landslide investigations: an overview of recent achievements and perspectives", Remote Sens., 6(10), 9600-9652. https://doi.org/10.3390/rs6109600.
  43. Sentinel Hub, Sinergise Ltd., https://www.sentinel-hub.com.
  44. Sur, U., Singh, P., Meena, S.R. and Singh, T.N. (2022), "Predicting landslides susceptible zones in the Lesser Himalayas by ensemble of per pixel and object-based models", Remote Sens., 14(8), 1953. https://doi.org/10.3390/rs14081953.
  45. Syed, A.H. (2015), "Segmentation and Classification of Remotely Sensed Images: Object-based image analysis", Rochester Institute of Technology.
  46. Trimble Germany GmbH (2021), "Trimble Documentation eCognition Developer 10.1 Reference Book", Trimble Germany GmbH: Munich, Germany.
  47. Troya-Galvis, A., Gancarski, P., Passat, N. and Berti-Equille, L. (2005), "Unsupervised quantification of under-and over-segmentation for object-based remote sensing image analysis", IEEE J. Select. Topics Appl. Earth Observ. Remote Sens., 8(5) : 1936-1945. https://doi.org/10.1109/JSTARS.2015.2424457.
  48. Troya-Galvis, A., Gancarski, P., Passat, N. and Berti-Equille, L. (2015), "Unsupervised quantification of under-and over-segmentation for object-based remote sensing image analysis", IEEE J. Select. Topics Appl. Earth Observ. Remote Sens., 8(5), 1936-1945. https://doi.org/10.1109/JSTARS.2015.24244573.
  49. Tucker, C.J. (1979), "Red and photographic infrared linear combinations for monitoring vegetation", Remote Sens. Environ., 8(2), 127-150. https://doi.org/10.1016/0034-4257(79)90013-0.
  50. Wu, C. (2004), "Normalized spectral mixture analysis for monitoring urban composition using ETM+ imagery", Remote Sens. Environ., 93(4), : 480-492. https://doi.org/10.1016/j.rse.2004.08.003.
  51. Zerrouki, N. and Bouchaffra, D. (2014, October), "Pixel-based or object-based: Which approach is more appropriate for remote sensing image classification", Proceedings of the 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), IEEE.
  52. Zhao, L., Huang, Y., Xiong, M. and Ye, G. (2020), "Reliability and risk assessment for rainfall-induced slope failure in spatially variable soils", Geomech. Eng., 22(3), 207-217. https://doi.org/10.12989/gae.2020.22.3.207.