Analysis of S2 (Spherical) Geometry Library Algorithm for GIS Geocoding Engineering

Ekawati, Risma; Suprihadi, Untung

doi:10.12928/telkomnika.v16i1.6985

Cited by 2 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we used S2 geometry to represent geographic locations. It is a hierarchical discretization method for Earth's surface that recursively divides Earth's surface into four quadrants using the Hilbert curve, enabling a natural multi-level spatial representation [29,50,51]. The series of geographic grids obtained by partitioning Earth's surface using the S2 geometry are called S2 cells [50].…”

Section: S2 Geometry and Grid Divisionmentioning

confidence: 99%

A Hierarchy-Aware Geocoding Model Based on Cross-Attention within the Seq2Seq Framework

Liang,

Chang,

Quan

et al. 2024

IJGI

View full text Add to dashboard Cite

Geocoding converts unstructured geographic text into structured spatial data, which is crucial in fields such as urban planning, social media spatial analysis, and emergency response systems. Existing approaches predominantly model geocoding as a geographic grid classification task but struggle with the output space dimensionality explosion as the grid granularity increases. Furthermore, these methods generally overlook the inherent hierarchical structure of geographical texts and grids. In this paper, we propose a hierarchy-aware geocoding model based on cross-attention within the Seq2Seq framework, incorporating S2 geometry to model geocoding as a task for generating grid labels and predicting S2 tokens (labels of S2 grids) character-by-character. By incorporating a cross-attention mechanism into the decoder, the model dynamically perceives the address contexts at the hierarchical level that are most relevant to the current character prediction based on the input address text. Results show that the proposed model significantly outperforms previous approaches across multiple metrics, with a median and mean distance error of 41.46 m and 93.98 m, respectively. Furthermore, our method achieves superior results compared to others in regions with sparse data distribution, reducing the median and mean distance error by 16.27 m and 7.52 m, respectively, suggesting that our model has effectively mitigated the issue of insufficient learning in such regions.

show abstract