Abstract
A Spatial Analysis Neural Network (SANN) algorithm was applied for the analysis of geospatial data, on the basis of nonparametric statistical analysis and the concepts of traditional Artificial Neural Networks. SANN consists of a number of layers in which the neurons or nodes between layers are interconnected successively in a feed-forward direction. The Gaussian Kernel Function layer has several nodes, and each node has a transfer or an activation function that only responds (or activates) when the input pattern falls within its receptive field, which is defined by its smoothing parameter or width. The activation widths are functions of the model structural parameters, including the number of the nearest neighbor points P and a control factor F. The estimation method is based on two operational modes, namely, a training-validation mode in which the model structure is constructed and validated, and an interpolation mode. In this paper we discuss the effect of varying F and P upon the accuracy of the estimation in a two-dimensional domain for different input field sizes, using spatial data of wheat crop yield from Eastern Colorado. Crop yield is estimated as a function of the two-dimensional Cartesian coordinates (easting and northing). The results of the research led to the conclusion that optimal values of F and P depend on the sample size, i.e., for small data sets F=1.5 and P=7 while for large data sets F=2.5 and P=9. In addition, the accuracy of the interpolated field varies with the sample size. As expected for small sample sizes, the interpolated field and its variability may be significantly underestimated.
Similar content being viewed by others
REFERENCES
Ahmed, S., and De Marsily, G., 1987, Comparison of geostatistical methods for estimating transmissivity using data on transmissivity and specific capacity: Water Resourc. Res., v. 23, no. 9, p. 1717–1737.
ASCE Task Committee on Geostatistical Techniques, 1990, Review of Geostatistics in Geohydrology: I. Basis Concepts, J. of Hydraulic Engineering, v. 116, no. 5, p. 612–632.
Aziz, A. R. A., and Wong, K. F. V., 1992, Neural network approach to the determination of aquifer parameters: Ground Water, v. 30, no. 2, p. 164–166.
Bedient, P. B., and Huber, W. C., 1992, Hydrology and flood plains analysis: Addison-Wesley, Reading, MA, 692 p.
Bishop, C. M., 1995, Neural networks for pattern recognition: Clarendon Press, Oxford, 482 p.
Bonafe, A., Galeati, G., and Sforna, M., 1994, Neural networks for daily mean flow forecasting: Hydr. Engr. Software V: ComputationalMechanics Publications, Southampton, UK, Vol. 1, p. 131–138.
Creutin, J. D. and Obled, C., 1982, Objective analyses and mapping techniques for rainfall fields: An objective comparison, Water Resources Res., v. 18p. 413–431.
Dawson, C.W., and Wilby, R., 1998, An artificial neural network approach to rainfall-runoffmodeling: Hydrol. Sci., v. 43, no. 1, p. 47–66.
Fernando, D. A. K., and Jayawardena, A.W., 1998, Runoff forecasting using RBF networks with OLS algorithm: J. Hydrol. Eng. ASCE, v. 3, no. 3, p. 203–209.
French, M. N., Krajewski, W. F., and Cuykendal, R. R., 1992, Rainfall forecasting in space and time using a neural network: J. Hydrol., v. 137, p. 1–37.
Goovaerts, P., 2000, Geostatistical approaches for incorporating elevation into the spatial interpolation of rainfall: J. Hydrol., v. 228, p. 113–129.
Govindaraju, R. and Rao, A. R., 2000, Artificial neural networks in hydrology: Kluwer Academic, Dordrecht, 329 p.
Hayken, S. S., 1994, Neural networks: A comprehensive foundation: MacMillan College, New York, 696 p.
Hjelmfelt, A. T. and Wang, M., 1996, Predicting runoff using artificial neural networks: Surf. Water Hydrol., p. 233–244.
Hoeksema, R. J., Clapp, R. B., Thomas, A. L., Hunley, A. E., Farrow, N. D., and Dearstone, K. C., 1989, Cokriging model for estimation of water table elevation: Water Resour. Res., v. 25, no. 3, p. 429–438.
Hsu, K., Gao, X., Sorooshian, S., and Gupta, H.V., 1997, Precipitation estimation from remotely sensed information using artificial neural networks: J. Appl. Meteorol., v. 36, no. 9, p. 1176–1190.
Hsu, K., Gupta, H. V., and Sorooshian, S., 1995, Artificial neural network modeling of the rainfall-runoff process: Water Resour. Res., v. 31, no. 10, p. 2517–2530.
Islam, S. and Kothari, R., 2000, Artificial neural networks in remote sensing of hydrologic processes: J. Hydrol. Eng. ASCE, v. 5, no. 2, p. 138–144.
Kuligowski, R. J., and Barros, A. P., 1998, Experiments in short-term precipitation forecasting using artificial neural networks: Mon. Weather Rev., v. 126, no. 2, p. 470–482.
Kyriakidis, P. C. and Journel, A. G., 1999, Geostatistical space-time models: A review: Math. Geol., v. 31, no. 6, p. 651–684.
Luthi, S. M. and Bryant, I. D., 1997, Well-log correlation using a back-propagation neural network: Math. Geol., v. 29, no. 3, p. 413–425.
Maier, H. R., and Dandy, G. C., 1996, The use of artificial neural networks for the prediction of water quality parameters: Water Resour. Res., v. 32, no. 4, p. 1013–1022.
Masters, T., 1994. Advanced algorithms for neural networks: A C++ source book: Wiley, New York p. 158–191.
McCuen, R. H., 1998, Hydrologic analysis and design, 2nd Edition, Prentice Hall, New Jersey, 814 pp.
Moody, J. E., and Darken, D. J., 1989, Fast learning in networks of locally-tuned processing units: Neural Comput., 1, p. 281–294.
Musavi, M. T., Chan, K. H., Hummels, D. M., Kalantri, K., and Ahmed, W., 1992, A probabilistic model for evaluation of neural networks classifiers: Pattern Recognit., v. 25, no. 10, p. 1241–1251.
Olea, R. A., 1984, Sampling design optimization for spatial functions: Math. Geol., v. 16, no. 4, p. 369–392.
Rizzo, D.M., and Dougherty, D. E., 1994, Characterization of aquifer properties using artificial neural networks: Neural kriging: Water Resour. Res., v. 30, no. 2, p. 483–497.
Saha, A., and Keeler, J. D., 1990, Algorithms for better representation and faster learning in radial basis function networks, inAdvances in Neural Information Processing Systems 2, Touretzky, D. S., et al., eds., Morgan Kaufmann, San Mantec, CA, v. 2, p. 482–489.
Salas, J. D., Markus, M., and Tokar, A. S., 2000, Streamflow forecasting based on artificial neural networks, Chapter 4 inArtificial neural networks in hydrology, G. Rao and A. R. Rao, eds., Kluwer Academic Publishers, London, p. 23–51.
Sanchez, L., Arroyo, V., Garcia, J., Koev, K. and Revilla, J., 1998, Use of neural networks in design of coastal sewage systems: J. Hydr. Eng. ASCE, v. 124, no. 5, p. 457–464.
Shin, H. S., and Salas, J. D., 2000, Spatial analysis of hydrologic and environmental data based on artificial neural networks, Chapter 13 inArtificial neural networks in hydrology, G. Rao and A. R. Rao, eds., Kluwer Academic Publishers, London, p. 259–286.
Singer, D. A., and Kouda, R., 1996, Application of a feedforward neural network in the search for Kuroko deposits in the Hokuroku Distric, Japan: Math. Geol., v. 28, no. 8, p. 1017–1023.
Smith, J., and Eli, R. N., 1995, Neural-network models of rainfall-runoff process: J. Water Resour. Plang. Mgmt. ASCE, v. 121, no. 6, p. 499–508.
Specht, D. F., 1991, A general regression neural network: IEEE Trans. Neural Netw., v. 2, no. 6, p. 568–576.
Tabios, G. Q., and Salas, J. D., 1985, A comparative analysis of techniques for spatial analysis interpolation of precipitation: Water Resour. Bull., v. 21, no. 3, p. 365–380.
Tokar, A. S., and Johnson, P. A., 1999, Rainfall-runoff modeling using artificial neural networks: ASCE J. Hydrol. Engr., v. 4, no. 3, p. 232–239.
Tsoukalas, L. H., and Uhrig, R. E., 1997, Fuzzy and neural approaches in engineering: Wiley Interscience; New York, 587 p.
Zimmerman, D., Pavlik, C., Ruggles, A., and Armstrong, M. P., 1999, An experimental comparison of ordinary and universal Kriging and inverse distance weighting: Math. Geol., v. 31, no. 4, p. 375–390.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Martinez, A., Salas, J.D. & Green, T.R. Sensitivity of Spatial Analysis Neural Network Training and Interpolation to Structural Parameters. Mathematical Geology 36, 721–742 (2004). https://doi.org/10.1023/B:MATG.0000039543.89653.57
Issue Date:
DOI: https://doi.org/10.1023/B:MATG.0000039543.89653.57