Abstract
Geographical continuous fields are usually represented by means of sample points or zonal attribute sets, which leads to discontinuities in attribute values, or unrealistic homogeneities. The solution is to interpolate and extrapolate from known values, according to some constraints upon the estimation. Then, a new estimation method is proposed, based on finite difference method results, and the Hopfield neural network. This new method meets our statistical and morphological constraints.
Similar content being viewed by others
References
D. Pariente, R. Laurini. Interpolation and Extrapolation of Statistical Spatio-Temporal Data Based on Neural Networks. In:Proceedings of EUROSTAT/DOSES Workshop on New Tools for Spatial Analysis, Lisbon, Portugal, November 17–20, 1993. Lisbonne: ISEGI, 10 pages, 1993.
D. Pariente, S. Servigne. Approximation spatiotemporelle sous contraintes: apport des méthodes neuronales. In :Actes du Colloque sur le Neuromimétisme, Lyon, 20–23 Juin, 1994. Villeurbanne : Association Internationale pour le Développement de la Recherche Interdisciplinaire, pp 239–244, 1994.
N.S.N. Lam. Spatial Interpolation Methods: A Review.The American Cartographer, Vol. 10, Nℴ 2, pp 129–149, 1983.
J.J. Hopfield. Neurons with Graded Response Have Collective Properties like Those of Two-State Neurons.Proceedings of the National Academy of Sciences USA, Vol. 81, pp 3088–3092, 1984.
J.-M. Jolion, B. Rosenfeld.Pyramidal Framework for Early Vision. Kluwer Ed., 1994.
D. Pariente. Estimation, Modélisation et Langage de Déclaration et de Manipulation de Champs Spatiaux Continus.Thèse Sc.:Institut National des Sciences Appliquées, Lyon, 189 pages, 1994 (to be published).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Pariente, D., Servigne, S. & Laurini, R. A neural method for geographical continuous field estimation. Neural Process Lett 1, 28–31 (1994). https://doi.org/10.1007/BF02310940
Issue Date:
DOI: https://doi.org/10.1007/BF02310940