Abstract
An artificial neural network (ANN) toolbox is created within GIS software for spatial interpolation, which will help GIS users to train and test ANNs, perform spatial analysis, and display results as a single process. The performance is compared to that of the open source Fast Artificial Neural Network library and conventional interpolation methods by creating digital elevation models (DEMs) given that nearly exact solutions exist. Simulation results show that the advanced backpropagations such as iRprop speed up the learning, while they can get stuck in a local minimum depending on initial weight sets. Besides, the division of input–output examples into training and test data affects the accuracy, particularly when the distribution of the examples is skewed and peaked, and the number of data is small. ANNs, however, show the similar performance to inversed distance weighted or kriging and outperform polynomial interpolations as a global interpolation method in high-dimensional data. In addition, the neural network residual kriging (NNRK) model, which combines the ANN toolbox and kriging within GIS software, is performed. The NNRK outperforms conventional methods and well captures global trends and local variations. A key outcome of this work is that the ANN toolbox created within the de facto standard GIS software is applicable to various spatial analysis including hazard risk assessment over a large area, in particular when there are multiple potential causes, the relationship between risk factors and hazard events is not clear, and the number of available data is small given its performance for DEM generation.
Similar content being viewed by others
References
Almhdi KM, Valigi P, Gulbinas V, Westphal R, Reuter R (2007) Classification with artificial neural networks and support vector machines: application to oil fluorescence spectra. Eur Assoc Remote Sens Lab (EARSeL) eProceeding 6(2):115–129
Amini J (2008) Optimum learning rate in back-propagation neural network for classification of satellite images (IRS-1D). Sci Iran 15(6):558–567
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, USA
Borne KD (2005) UMUC data mining lecture 2. http://polaris.umuc.edu/its/CSMN/csmn667/lecture02.ppt. Accessed 2 Apr 2014
Caudill M (1988) Neural networks primer, part III. AI Expert 3(6):53–59
Ceravolo F, Felice MD, Pizzuti S (2009) Combining back-propagation and genetic algorithms to train neural networks for ambient temperature modeling in Italy. In: Giacobini et al. (ed) Applications of evolutionary computing. Springer, Berlin, pp 123–131
Chaturvedi DK (2008) Soft computing: techniques and its applications in electrical engineering. Springer, Berlin
Dechpichai P (2010) Nonlinear neural network for conditional mean and variance forecasts. Dissertation, University of Wollongong, Wollongong
Demyanov V, Kanevski M, Chernov S, Savelieva E, Timonin V (1998) Neural network residual kriging application for climatic data. J Geogr Inf Decis Anal 2(2):215–232
Demyanov V, Soltano S, Kanevski M, Canu S, Maignan M, Savelieva E, Timonin V, Pisarenko V (2001) Wavelet analysis residual kriging vs. neural network residual kriging. Stoch Env Res Risk Assess 15:18–32
Ding Y, Dong L, Wang L, Wu G (2010) A high order neural network to solve crossbar switch problem. In: Wong KW, Mendis BSU, Bouzerdoum A (eds) ICONIP 2010, part II. LNCS, vol 6444, Australia, pp 692–699
Doane DP, Seward LE (2011) Measuring skewness: a forgotten statistic? J Stat Educ 19(2):45–63
Dorofki M, Elshafie AH, Jaafar O, Karim OA, Mastura S (2012) Comparison of artificial neural network transfer functions abilities to simulate extreme runoff data. In: International conference on environment, energy and biotechnology (IPCBEE), vol 33, pp 39–44
Duch W, Jankowski N (2001) Transfer functions: hidden possibilities for better neural networks. In: Proceeding of the 9th European symposium on artificial neural networks (ESANN), Brugge, pp 81–87
ESRI (2014) ArcGIS resource center. http://resources.arcgis.com/. Accessed 2 Apr 2014
Hammerstrom D (1993) Working with neural networks. IEEE Spectr 30(7):46–53
Han J, Moraga C (1995) The influence of the sigmoid function parameters on the speed of backpropagation learning. In: Mira J, Sandoval F (eds) From natural to artificial neural computation. Springer, Berlin, pp 195–201
Han KY, Choi HG, Kim DI, Kim JE (2008) Flow forecasting using neural networks model in Nakdong river basin. Korean Soc Water Environ 2:798–800
Hecht-Nielsen R (1987) Kolmogorov’s mapping neural network existence theorem. In: Proceedings of IEEE 1st annual international conference on neural networks, pp 11–13
Hettiarachchi P, Hall MJ, Minns AW (2005) The extrapolation of artificial neural networks for the modelling of rainfall–runoff relationships. J Hydroinf 7(4):291–296
Huang GB (2003) Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Trans Neural Netw 14(2):274–281
Igel C, Husken M (2000) Improving the Rprop learning algorithm. In: Proceedings of the 2nd international symposium on neural computation (NC 2000), pp 115–121
Jayalakshmi T, Santhakumaran A (2011) Statistical normalization and back propagation for classification. Int J Comput Theory Eng 3(1):89–93
Jeong DI, Kim YO (2005) Rainfall–runoff models using artificial neural networks for ensemble streamflow prediction. Hydrol Process 19(19):3819–3835
Joanes DN, Gill CA (1998) Comparing measures of sample skewness and kurtosis. J R Stat Soc 47(1):183–189
Johnson VM, Rogers LL (1998) Using artificial neural networks and the genetic algorithm to optimize well field design: phase I final report. Lawrence Livermore National Laboratory, Livermore
Kachru K, Chamy M, Chowdhury S (2002) Interpolation of sparse digital elevation model using back propagation neural networks. Indian Cartogr 22:219–226
Kanevsky M, Arutyunyan R, Bolshov L, Demyanov V, Maignan M (1996) Artificial neural networks and spatial estimation of chernobyl fallout. Geoinformatics 7(1–2):5–11
Kao JJ (1996) A xerion-based perl program to train a neural network for grid pattern recognition. Comput Geosci 22(9):1033–1049
Karabork H, Baykan OK, Altuntas C, Yildz F (2008) Estimation of unknown height with artificial neural network on digital terrain model. ISPRS Int Arch Photogr Remote Sens Spat Inf Sci 37:115–117
Kia MB, Pirasteh S, Pradhan B, Mahmud AR, Sulaiman WNA, Moradi A (2012) An artificial neural network model for flood simulation using GIS: Johor River Basin, Malaysia. Environ Earth Sci 67(1):251–264
Kostal B (1994) An analysis of stopping criteria in artificial neural networks. Master's Thesis, Air Force Institite of Technology, OH, United State
Lee S, Evangelista DG (2006) Earthquake-induced landslide-susceptibility mapping using an artificial neural network. Nat Hazards Earth Syst Sci 6:687–695
Lou YF, Brunn P (1998) An offset error compensation method for improving ANN accuracy when used for position control of precision machinery. Neural Comput Appl 7(1):90–95
Maier HR, Jain A, Dandy GC, Sudheer KP (2010) Methods used for the development of neural networks for the prediction of water resource variables in river systems: current status and future directions. Environ Model Softw 25(8):891–909
Malmgren H, Borga M, Niklasson LF (2000) Artificial neural networks in medicine and biology. In: Proceedings of the ANNIMAB-1 conference, Göteborg
Masters T (1993) Practical neural network recipes in C++. Academic Press, San Diego
Merwin DA, Cromley RG, Civco DL (2002) Artificial neural networks as a method of spatial interpolation for digital elevation models. Cartogr Geogr Inf Sci 29(2):99–110
Minns AW (1996) Extended rainfall–runoff modelling using artificial neural networks. In: Proceedings of the 2nd international conference on hydroinformatics, Rotterdam, pp 207–213
Netzel P (2011) Implementation of ANN in GRASS—an example of using ANN for spatial interpolation. In: Geoinformatics FCE CTU 2011, Prague, Czech Republic, 19–20 May 2011
Nissen S (2003) Implementation of a fast artificial neural network library (FANN). Department of Computer Science, University of Copenhagen, Denmark
Nissen S (2007) Large scale reinforcement learning using Q-SARSA(λ) and cascading neural networks. Dissertation, University of Copenhagen, Denmark
NIST/SEMATECH (2012) E-handbook of statistical methods. http://www.itl.nist.gov/div898/handbook/. Accessed 2 Apr 2014
Park S, Choi C, Kim B, Kim J (2013) Landslide susceptibility mapping using frequency ratio, analytic hierarchy process, logistic regression, and artificial neural network methods at the Inje area, Korea. Environ Earth Sci 68(5):1443–1464
Patel N (2003) Data mining. In: Lecture note, MIT open courseware. http://ocw.mit.edu/courses/sloan-school-of-management/15-062-data-mining-spring-2003/lecture-notes/NeuralNet2002.pdf. Accessed 2 Apr 2014
Pradhan B, Lee S (2009) Landslide risk analysis using artificial neural network model focussing on different training sites. Int J Phys Sci 4(1):1–15
Pradhan B, Lee S (2010a) Delineation of landslide hazard areas on Penang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network models. Environ Earth Sci 60(5):1037–1054
Pradhan B, Lee S (2010b) Landslide susceptibility assessment and factor effect analysis: backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modeling. Environ Model Softw 25(6):747–759
Pradhan B, Lee S, Buchroithner MF (2010a) A GIS-based back-propagation neural network model and its cross-application and validation for landslide susceptibility analyses. Comput Environ Urban Syst 34(3):216–235
Pradhan B, Youssef AM, Varathrajoo R (2010b) Approaches for delineating landslide hazard areas using different training sites in an advanced artificial neural network model. Geospat Inf Sci 13(2):93–102
Quan HC, Lee BG, Cho EI (2008) Landslide susceptibility analysis in Jeju using artificial neural network (ANN) and GIS. J Environ Sci 17(6):679–687
Rajurkar MP, Kothyari UC, Chaube UC (2002) Artificial neural networks for daily rainfall–runoff modeling. Hydrol Sci J 47(6):865–877
Riedmiller M (1994) Advanced supervised learning in multi-layer perceptrons—from backpropagation to adaptive learning algorithms. Comput Stand Interfaces 16(3):265–278
Riedmiller M, Braun H (1993) A direct adaptive method for faster backpropagation learning: the Rprop algorithm. In: Proceedings of the IEEE international conference on neural networks, San Francisco, pp 586–591
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. In: Rumelhart DE, McClelland JL, The PDP Research Group (eds) Parallel distributed processing: explorations in the microstructure of cognition. MIT Press, Cambridge, pp 318–362
Sathya R, Abraham A (2013) Comparison of supervised and unsupervised learning algorithms for pattern classification. Int J Adv Res Artificial Intell 2(2):34–38
Sen A, Gümüsay MU, Kavas A, Bulucu U (2008) Programming an artificial neural network tool for spatial interpolation in GIS—a case study for indoor radio wave propagation of WLAN. Sensors 8(9):5996–6014
Shahin MA, Jaksa MB, Maier HR (2008) State of the art of artificial neural networks in geotechnical engineering. Electron J Geotech Eng 8:1–26
Tu JV (1996) Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 49(11):1225–1231
Vahidnia MH, Alesheikh AA, Alimohammadi A, Hosseinali F (2010) A GIS-based neuro-fuzzy procedure for integrating knowledge and data in landslide susceptibility mapping. Comput Geosci 36(9):1101–1114
Wang S, Li F (2008) Spatial interpolation of DEM using BP artificial neural networks. In: International conference on earth observation data processing and analysis, pp 1–8
Williams RJ (1986) The logic of activation functions. In: Rumelhart DE, McClelland JL, The PDP Research Group (eds) Parallel distributed processing: explorations in the microstructure of cognition. MIT Press, Cambridge, pp 423–443
Wilson DR, Martinez TR (2003) The general inefficiency of batch training for gradient descent learning. Neural Netw 16:1429–1451
Yanar TA, Akyürek Z (2007) Artificial neural networks as a tool for site selection within GIS. In: International institute for geo-information science and earth observation (ITC). 5th International symposium for spatial data quality 2007, Enschede, the Netherlands
Yang CC, Prasher SO, Landry JA, Ramaswamy HS, Ditommaso A (2000) Application of artificial neural networks in image recognition and classification of crop and weeds. Can Agric Eng 42(3):147–152
Yoon H, Hyun Y, Lee KK (2007) Forecasting solute breakthrough curves through the unsaturated zone using artificial neural networks. J Hydrol 335(1–2):68–77
Yoon H, Jun SC, Hyun Y, Bae GO, Lee KK (2011) A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. J Hydrol 396(1–2):128–138
Zadeh MR, Amin S, Khalili D, Singh VP (2010) Daily outflow prediction by multilayer perceptron with logistic sigmoid and tangent sigmoid activation functions. Water Resour Manag 24(11):2673–2688
Zemouri R, Gouriveau R, Patic PC (2010) Improving the prediction accuracy of recurrent neural network by a PID controller. Int J Syst Appl Eng Dev 4(2):19–34
Acknowledgments
This research was supported by a grant (NEMA-BAEKDUSAN-2012-1-3) from the Volcanic Disaster Preparedness Research Center sponsored by National Emergency Management Agency of Korea. We would like to express our appreciation to professor Jacek Mańdziuk for his kindest advices and Steffen Nissen for his reply on our questions about the FANN.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, S., An, H., Yu, S. et al. Creating an advanced backpropagation neural network toolbox within GIS software. Environ Earth Sci 72, 3111–3128 (2014). https://doi.org/10.1007/s12665-014-3216-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12665-014-3216-7