Geographical Pattern Analysis of GIS Images With Deep Learning and Voronoi Network

Nidaa Kareem, PhD Student, Department of Software, College of Information Technology, University of Babylon, IraqFollow
Tawfiq A. Al-Assadi, Professor, Department of Software, College of Information Technology, University of Babylon, IraqFollow

ORCID

Nidaa Kareem: https://orcid.org/0009-0006-2163-2711

Article Type

Original Study

Abstract

Localization is not enough for the analysis of spatial patterns; a principled geometric and statistical framework is required. This paper proposes an integrated spatial intelligence system combining deep learning, computational geometry, and spatial statistics, which is a unified and interpretable system. It is based on segmentation localization that accurately localizes the centroid of each object without the disadvantages of the bounding box. These centroids form a natural Voronoi tessellation of regions of spatial influence intrinsic to the data instead of imposing any artificial restrictions. A geometry-based density formulation is used to improve representation, which includes Voronoi cell areas and neighborhood relationships, representing strong, scale-adaptive spatial concentrations. Furthermore, the multi-task neural network could learn discriminative geometric features (shape complexity, relative scale) and integrate this information with the density measure, as well as with structural and semantic representations. Moreover, spatial autocorrelation (Moran's I and LISA) confirms the presence of global and local heterogeneity and clustering. The flexible, generalizable framework can achieve 99.47% accuracy with a mere two features, area and side count, distinguishing between structured, random, and irregular patterns, which could be useful for traffic monitoring, urban studies, environmental modelling, and GIS.

Keywords

Spatial analysis, Voronoi diagram, Deep learning, GIS, Moran's I, LISA

How to Cite This Article

Kareem, Nidaa and Al-Assadi, Tawfiq A. (2026) "Geographical Pattern Analysis of GIS Images With Deep Learning and Voronoi Network," Journal of Intelligent Informatics, Networking, and Cybersecurity: Vol. 2 : Iss. 2 , Article 9.
Available at: https://doi.org/10.65445/3106-1192.1020