Advertisement

Central European Journal of Operations Research

, Volume 27, Issue 3, pp 783–795 | Cite as

Application of different radial basis function networks in the illegal waste dump-surface modelling

  • Polona Pavlovčič-PrešerenEmail author
  • Bojan Stopar
  • Oskar Sterle
Original Paper

Abstract

In quality assessment of digital elevation models (DEMs), geodetic field measurements have an important, but also a limited, role. They can achieve high accuracy, but the acquisition of data is time consuming, expensive and, in areas with a high-resolution DEM accessibility, non-effective. Therefore, field measurements are only performed at discrete selected points to evaluate the quality of the DEM used for further studies. The aim of this article is to show that differences in heights from field measurements and from a DEM can be used for height-deviation-surface modelling and for possible improvements in the available DEM. The procedure is related to situations where significant changes in the landscape occur. For surface modelling, this research included several radial basis function networks (RBFNs). From simulations, knowledge was acquired of appropriate results based on varying amounts of input data as well as on different neural network activation functions. This study indicates the potential use of geodetic field measurements in the improvement of a local DEM by RBFNs.

Keywords

Digital elevation model (DEM) Field measurements Surface modelling Radial basis function networks (RBFNs) 

Notes

Acknowledgements

The research was partially funded by the Slovenian Research Agency in the frame of research Program P2-0227(A), Geoinformation infrastructure and sustainable spatial development of Slovenia.

References

  1. Abyaneh Z (2014) Evaluation of multivariate linear regression and artificial neural networks in prediction of water quality parameters. J Environ Health Sci 12(40):1–8.  https://doi.org/10.1186/2052-336X-12-40 Google Scholar
  2. Adamowski J, Chan HF (2011) A wavelet neural network conjunction model for groundwater level forecasting. J Hydrol 407(1–4):28–40.  https://doi.org/10.1016/j.jhydrol.2011.06.013 CrossRefGoogle Scholar
  3. Berk S, Komadina Ž, Marjanović M, Radovan D, Stopar B (2003) Combined solution of the EUREF GPS campaigns on the territory of Slovenia (in Slovene). Geod Vestn 47(4):414–422Google Scholar
  4. Broomhead DS, Lowe D (1988) Multivariable functional interpolation and adaptive networks. Compl Syst 2:321–355Google Scholar
  5. Carlisle BH (2005) Modelling the spatial distribution of DEM error. T GIS 9(4):521–540.  https://doi.org/10.1111/j.1467-9671.2005.00233.x CrossRefGoogle Scholar
  6. Chen S, Cowan CFN, Grant PM (1991) Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans Neural Netw 2(2):302–309.  https://doi.org/10.1109/72.80341 CrossRefGoogle Scholar
  7. Costa JP, Pronzato L and Thierry E (2000) A comparison between kriging and radial basis function networks for nonlinear prediction. https://www.eurasip.org/Proceedings/Ext/NSIP99/Nsip99/papers/155.pdf. Accessed 15 March 2018
  8. Du KI, Swamy NS (2013) Neural networks and statistical learning. Springer, LondonGoogle Scholar
  9. Erol B, Erol S (2013) Learning-based computing techniques in geoid modelling from precise height transformation. Comput Geosci 52:95–107.  https://doi.org/10.1016/j.cageo.2012.09.010 CrossRefGoogle Scholar
  10. Ferrari S, Stengel RF (2005) Smooth function approximation using neural networks. IEEE Trans Neural Netw 16(1):24–38.  https://doi.org/10.1109/TNN.2004.836233 CrossRefGoogle Scholar
  11. Giebel S, Rainer M (2013) Neural network calibrated stochastic processes: forecasting financial assets. Cent Eur J Oper Res 21(2):277–293.  https://doi.org/10.1007/s10100-011-0234-3 CrossRefGoogle Scholar
  12. Gillin CP, Bailey SW, McGuire KJ, Prisley SP (2015) Evaluation of Lidar-derived DEMs through terrain analysis and field comparison. Photogramm Eng Rem Sens 81(5):387–396.  https://doi.org/10.14358/pers.81.5.387 CrossRefGoogle Scholar
  13. Harkouss Y, Fahs W, Ayache M (2011) A new algorithm for structure optimization of wavelet neural networks. Int J Comput Sci Issues 8(2):108–117Google Scholar
  14. Höhle J, Potuckova M (2011) Assessment of the quality of digital terrain models. European Spatial Data Research, Frankfurt, Report No. 60Google Scholar
  15. Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366.  https://doi.org/10.1016/0893-6080(89)90020-8n CrossRefGoogle Scholar
  16. Kosmatin-Fras M, Kerin A, Mesarič M, Peterman V, Grigillo D (2016) Assessment of the quality of digital terrain model produced from unmanned aerial system imagery. Int Soc Photogramm Spatial Inf Sci 41(B1):893–899.  https://doi.org/10.5194/isprsarchives-XLI-B1-893-2016 Google Scholar
  17. Markopoulos AP, Georgiopoulos S, Manolakos DE (2016) On the use of back propagation and radial basis function neural networks in surface roughness prediction. J Ind Eng Int 12(3):389–400.  https://doi.org/10.1007/s40092-016-0146-x CrossRefGoogle Scholar
  18. MATLAB and Statistics Toolbox Release (2015b) The MathWorks Inc. Natick, MassachusettsGoogle Scholar
  19. Orr M (1995) Regularization in the selection of radial basis function centers. Neural Comput 7(3):606–623CrossRefGoogle Scholar
  20. Pavlovčič-Prešeren P, Stopar B (2013) Wavelet neural network employment for continuous GNSS orbit function construction: application for the assisted-GNSS principle. Appl Soft Comput 13(5):2526–2536.  https://doi.org/10.1016/j.asoc.2012.11.034 CrossRefGoogle Scholar
  21. Pribičević B (2000) The use of geologica l, geophysical and geodetical databases in determination of the shape of geoid in the Republic of Slovenia. Dissertation, University of LjubljanaGoogle Scholar
  22. Rao YS, Deo R, Nalini J, Pillai AM, Muralikrishnan S, Dadhwal VK (2014) Quality assessment of TanDEM-X DEMs using airborne LiDAR, photogrammetry and ICESat elevation data. ISPRS Ann Photogramm Remote Sens Spatial Inf Sci 2(8):187–192.  https://doi.org/10.5194/isprsannals-II-8-187-2014 CrossRefGoogle Scholar
  23. Shahin MA, Maier HR, Jaksa MB (2004) Data division for developing neural networks applied to geotechnical engineering. J Comput Civ Eng ASCE 18(2):105–114CrossRefGoogle Scholar
  24. Snehmani Singh MK, Gupta RD, Ganju A (2013) DTM generation and avalanche hazard mapping using large format digital photogrammetric data and geomatics technique. J Remote Sens GIS 4(2):4–13Google Scholar
  25. Su J, Bork E (2006) Influence of vegetation, slope, and LiDAR sampling angle on DEM accuracy. Photogramm Eng Rem Sens 72(11):1265–1274CrossRefGoogle Scholar
  26. Zainuddin Z, Ong P (2007) Function approximation using artificial neural networks. Int J Syst Appl Eng Dev 4(1):173–178. http://www.naun.org/main/UPress/saed/saed-23.pdf. Accessed 15 March 2018

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Faculty of Civil and Geodetic EngineeringUniversity of LjubljanaLjubljanaSlovenia

Personalised recommendations