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.
This is a preview of subscription content, log in via an institution to check access.
Source: the authors
Source: the authors
Source: the authors
Source: the authors
Source: the authors
Similar content being viewed by others
References
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
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
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):414–422
Broomhead DS, Lowe D (1988) Multivariable functional interpolation and adaptive networks. Compl Syst 2:321–355
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
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
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
Du KI, Swamy NS (2013) Neural networks and statistical learning. Springer, London
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
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
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
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
Harkouss Y, Fahs W, Ayache M (2011) A new algorithm for structure optimization of wavelet neural networks. Int J Comput Sci Issues 8(2):108–117
Höhle J, Potuckova M (2011) Assessment of the quality of digital terrain models. European Spatial Data Research, Frankfurt, Report No. 60
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
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
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
MATLAB and Statistics Toolbox Release (2015b) The MathWorks Inc. Natick, Massachusetts
Orr M (1995) Regularization in the selection of radial basis function centers. Neural Comput 7(3):606–623
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
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 Ljubljana
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
Shahin MA, Maier HR, Jaksa MB (2004) Data division for developing neural networks applied to geotechnical engineering. J Comput Civ Eng ASCE 18(2):105–114
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):4–13
Su J, Bork E (2006) Influence of vegetation, slope, and LiDAR sampling angle on DEM accuracy. Photogramm Eng Rem Sens 72(11):1265–1274
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
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.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Pavlovčič-Prešeren, P., Stopar, B. & Sterle, O. Application of different radial basis function networks in the illegal waste dump-surface modelling. Cent Eur J Oper Res 27, 783–795 (2019). https://doi.org/10.1007/s10100-018-0586-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10100-018-0586-z