Advertisement

Automatic Landslides Mapping in the Principal Component Domain Open image in new window

  • Kamila PawłuszekEmail author
  • Andrzej Borkowski
Conference paper

Abstract

The availability of digital elevation model (DEM) delivered by airborne laser scanning (ALS) opens new horizons in the geomorphological research, especially in the landslide studies. This detailed geomorphological information allows for mapping of landslide affected areas using DEM data only. In order to map landslide areas in the automatic manner using machine learning classification algorithms and only DEM, generation of several DEM derivatives is needed. These first and second order derivatives provide information about specific properties of the terrain. However, involving a set of topographic features in the machine learning process increases significantly time of computations. Moreover, the topographic features are correlated since they are generated using the same DEM. The objective of this study is an in-depth exploration of the topographic information provided by the DEM data as well as the reduction of the computational time while the automatic landslide mapping. For this reason, a set of DEM derivatives have been generated and transformed into the principal component domain. The Principal Component Analysis (PCA) is a procedure that converts the set of correlated features into a set of linearly uncorrelated components using the orthogonal transformation. For the automatic landslide detection, the support vector machine (SVM) algorithm was used. The achieved results were compared with the existing landslide inventory map and overall accuracy and kappa coefficient were calculated. For the non-reduced original topographic model, we received 73% of overall accuracy. For the PCA-reduced models, accuracy parameters are not significantly worse. For instance, using only 7 principal components, which provide 90% of the total variability of the original topographic features, we received the overall accuracy of 72% while the computation time was reduced.

Keywords

Landslide inventory mapping DEM-derivatives Principal component analysis Support vector machine 

References

  1. Abdi H, Williams LJ (2010) Principal component analysis. Wiley Interdisc Rev Comput Stat 2(4):433–459. doi: 10.1002/wics.101 CrossRefGoogle Scholar
  2. Borkowski A, Perski Z, Wojciechowski T, Jóźków G, Wójcik A (2011) Landslides mapping in Rożnów Lake vicinity, Poland using airborne laser scanning data. Acta Geodynamica et Geomaterialia 8(3):325–333Google Scholar
  3. Carrara A, Merenda L (1976) Landslide inventory in northern Calabria, southern Italy. Geol Soc Am Bull 87(8):1153–1162. doi: 10.1130/0016-7606(1976)87<1153:liincs>2.0.co;2 CrossRefGoogle Scholar
  4. Chen W, Li X, Wang Y, Chen G, Liu S (2014) Forested landslide detection using Lidar data and the random forest algorithm: a case study of the Three Gorges, China. Remote Sens Environ 152:291–301. doi: 10.1016/j.rse.2014.07.004 CrossRefGoogle Scholar
  5. Crosta GB, Frattini P, Agliardi F (2013) Deep seated gravitational slope deformations in the European Alps. Tectonophysics 605:13–33. doi: 10.1016/j.tecto.2013.04.028 CrossRefGoogle Scholar
  6. Eeckhaut M, Poesen J, Verstraeten G, Vanacker V, Nyssen J, Moeyersons J, Van Beek L, Vandekerckhove L (2007) Use of LIDAR-derived images for mapping old landslides under forest. Earth Surf Proc Land 32(5):754–769. doi: 10.1002/esp.1417 CrossRefGoogle Scholar
  7. Evans J, Oakleaf J, Cushman S, Theobald D (2015) An ArcGIS Toolbox for surface gradient and geomorphometric modeling, version 2.0-0Google Scholar
  8. Galli M, Ardizzone F, Cardinali M, Guzzetti F, Reichenbach P (2008) Comparing landslide inventory maps. Geomorphology 94(3):268–289. doi: 10.1016/j.geomorph.2006.09.023 CrossRefGoogle Scholar
  9. Gorczyca E, Wrońska-Wałach D, Długosz M (2013) Landslide hazards in the Polish Flysch Carpathians: example of Łososina Dolna Commune. In Geomorphological impacts of extreme weather, Springer Netherlands, pp 237–250. doi: 10.1007/978-94-007-6301-2_15 CrossRefGoogle Scholar
  10. Guzzetti F, Mondini AC, Cardinali M, Fiorucci F, Santangelo M, Chang KT (2012) Landslide inventory maps: new tools for an old problem. Earth Sci Rev 112(1):42–66. doi: 10.1016/j.earscirev.2012.02.001 CrossRefGoogle Scholar
  11. Hsu CW, Chang CC, Lin CJ (2003) A practical guide to support vector classification. Available at: http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf (last access: 26 Sept 2016)
  12. Jenness J, Brost B, Beier P (2013) Land facet corridor designer: topographic position index tools. Available at: http://www.jennessent.com/downloads/Land_Facet_Tools.pdf (last access: 26 Sept 2016)
  13. Mahalingam R, Olsen MJ, O’Banion MS (2016) Evaluation of landslide susceptibility mapping techniques using lidar-derived conditioning factors (Oregon case study). Geomatics Nat Hazards Risk 1–24. doi: 10.1080/19475705.2016.1172520 CrossRefGoogle Scholar
  14. Martha TR, van Westen CJ, Kerle N, Jetten V, Kumar KV (2013) Landslide hazard and risk assessment using semi-automatically created landslide inventories. Geomorphology 184:139–150. doi: 10.1016/j.geomorph.2012.12.001 CrossRefGoogle Scholar
  15. McKean J, Roering J (2004) Objective landslide detection and surface morphology mapping using high resolution airborne laser altimetry. Geomorphology 57(3):331–351. doi: 10.1016/s0169-555x(03)00164-8 CrossRefGoogle Scholar
  16. Moosavi V, Talebi A, Shirmohammadi B (2014) Producing a landslide inventory map using pixel-based and object-oriented approaches optimized by Taguchi method. Geomorphology 204:646–656. doi: 10.1016/j.geomorph.2013.09.012 CrossRefGoogle Scholar
  17. Pawłuszek K, Borkowski A (2016) Landslides identification using airborne laser scanning data derived topographic terrain attributes and support vector machine classification. Int Arch Photogramm Remote Sens Spatial Inf Sci XLI-B8:145–149. doi: 10.5194/isprs-archives-XLI-B8-145-2016 CrossRefGoogle Scholar
  18. Pawłuszek K, Ziaja M, Borkowski A (2014) Accuracy assessment of the height component of the airborne laser scanning data collected in the ISOK system for the Widawa River Valley (in Polish). Acta Scientiarum Polonorum. Geodesia et Descriptio Terrarum 13(3–4). Available at: http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.baztech-a1b0f405-cffd-4d91-b1e2-33e49dd0eb50
  19. Peng L, Niu R, Huang B, Wu X, Zhao Y, Ye R (2014) Landslide susceptibility mapping based on rough set theory and support vector machines: a case of the Three Gorges area, China. Geomorphology 204:287–301. doi: 10.1016/j.geomorph.2013.08.013 CrossRefGoogle Scholar
  20. Richardson M (2009) Principal component analysis. URL: http://www.dsc.ufcg.edu.br/~hmg/disciplinas/posgraduacao/rn-copin-2014.3/material/SignalProcPCA.pdf (last access: 26 Sept 2016)
  21. Santangelo Á, Cardinali Á, Rossi Á, Mondini AC, Guzzetti F (2010) Remote landslide mapping using a laser rangefinder binocular and GPS. Nat Hazards Earth Syst Sci 10(12):2539–2546. doi: 10.5194/nhess-10-2539-2010 CrossRefGoogle Scholar
  22. Starkel L (1972) An outline of the relief of the polish Carpathians and its importance for human management. Problemy Zagospodarowania Ziem Górskich 10:75–150 (in Polish)Google Scholar
  23. Tarolli P (2014) High-resolution topography for understanding earth surface processes: opportunities and challenges. Geomorphology 216:295–312. doi: 10.1016/j.geomorph.2014.03.008 CrossRefGoogle Scholar
  24. Van Den Eeckhaut M, Hervás J (2012) State of the art of national landslide databases in Europe and their potential for assessing landslide susceptibility, hazard and risk. Geomorphology 139:545–558. doi: 10.1016/j.geomorph.2011.12.006 CrossRefGoogle Scholar
  25. Van Den Eeckhaut M, Kerle N, Poesen J, Hervás J (2012) Object-oriented identification of forested landslides with derivatives of single pulse LiDAR data. Geomorphology 173:30–42. doi: 10.1016/j.geomorph.2012.05.024 CrossRefGoogle Scholar
  26. Van Westen CJ, Castellanos E, Kuriakose SL (2008) Spatial data for landslide susceptibility, hazard, and vulnerability assessment: an overview. Eng Geol 102(3):112–131. doi: 10.1016/j.enggeo.2008.03.010 CrossRefGoogle Scholar
  27. Vapnik V (2013) The nature of statistical learning theory. Springer Science & Business Media. doi: 10.1007/978-1-4757-2440-0 CrossRefGoogle Scholar
  28. Varnes DJ (1984) IAEG Commission on Landslides and other Mass-Movements—Landslide hazard zonation: a review of principles and practice. The UNESCO Press, Paris, pp 1–63. doi: 10.1007/bf02594720 CrossRefGoogle Scholar
  29. Wójcik A, Wojciechowski T, Wódka M, Krzysiek U (2015) Landslide inventory map of landslide in Gródek nad Dunajcem in the scale of 1: 10000. Municipality of Łososina dolna, district: nowosądecki, province: małopolskie. URL: http://geoportal.pgi.gov.pl/portal/page/sopo (access on 6 July 2016)
  30. Woźniak A (2013) Precipitation in the polish Carpathian Mountains in 2010 compared to the period 1881–2010. Prace Geograficzne 133:35–48 (in Polish)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Institute of Geodesy and GeoinformaticsWroclaw University of Environmental and Life SciencesWroclawPoland

Personalised recommendations