Towards Automated Cadastral Map Improvement: A Clustering Approach for Error Pattern Recognition

Positional accuracy in cadastral data is fundamental for secure land tenure and efficient land administration. However, many land administration systems, experience difficulties to meet accuracy standards, particularly in areas with digitized historical maps, leading to disruptions in land transactions. This study investigates the use of unsupervised clustering algorithms in order to identify and characterize systematic spatial error patterns in cadastral maps. We compare Fuzzy c-means (FCM), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and Gaussian Mixture Models (GMM) in clustering error vectors derived from 500 homologous points. These points were obtained by comparing cadastral data with a higher-accuracy land survey within a 7 km² area in Ioannina, Greece, known for its inaccuracies in the Greek National Cadastre. The optimal number of clusters for each algorithm was determined. Results show that DBSCAN and GMM successfully captured a central area of random errors surrounded by a region exhibiting a systematic, counter-clockwise rotational error, whereas FCM did not capture this pattern. DBSCAN, with its ability to isolate noise points in the center of the study area, provided the most interpretable results. This clustering approach can be integrated into automated cadastral map improvement methods, contributing to progressive cadastral renewal efforts.