Journal cover Journal topic
Abstracts of the ICA
Journal topic
Articles | Volume 1
https://doi.org/10.5194/ica-abs-1-99-2019
https://doi.org/10.5194/ica-abs-1-99-2019
15 Jul 2019
 | 15 Jul 2019

Spatial Component Models with Artificial Neural Networks for Spatially Constrained Regionalization

Michael Govorov, Giedrė Beconytė, and Gennady Gienko

Keywords: Artificial Neural Network, kriging, Generalized Linear Mixed Model, Spatial Component Model, spatial effect, deep learning, regionalization

Abstract. The authors have investigated into different geostatistical point data modeling approaches for regionalization purposes that employ the Artificial Neural Network (ANN) techniques. Regionalization is a spatially constrained adjacency classification problem. In this study, regionalization is viewed as classification of spatial objects (non-uniformly distributed points) into a smaller number of geographic regions defined by their spatial and attributive characteristics or regionalized variables. For regionalization, we take into consideration the non-stationarity and autocorrelation properties of the spatial data.

Publications Copernicus
Download
Citation