Hex2vec -- Context-Aware Embedding H3 Hexagons with OpenStreetMap Tags

TL;DR

This paper introduces Hex2vec, a novel method for learning vector representations of urban regions based on OpenStreetMap tags, enabling semantic analysis of land-use and urban functions.

Contribution

It is the first approach to embed OSM regions with respect to urban land-use, using a Skip-gram model on hexagonally divided city regions.

Findings

Semantic structures of map characteristics are captured in the embeddings.

Region similarity detection reveals meaningful urban patterns.

A region typology was created through clustering analysis.

Abstract

Representation learning of spatial and geographic data is a rapidly developing field which allows for similarity detection between areas and high-quality inference using deep neural networks. Past approaches however concentrated on embedding raster imagery (maps, street or satellite photos), mobility data or road networks. In this paper we propose the first approach to learning vector representations of OpenStreetMap regions with respect to urban functions and land-use in a micro-region grid. We identify a subset of OSM tags related to major characteristics of land-use, building and urban region functions, types of water, green or other natural areas. Through manual verification of tagging quality, we selected 36 cities were for training region representations. Uber's H3 index was used to divide the cities into hexagons, and OSM tags were aggregated for each hexagon. We propose the hex2vec method based on the Skip-gram model with negative sampling. The resulting vector representations showcase semantic structures of the map characteristics, similar to ones found in vector-based language models. We also present insights from region similarity detection in six Polish cities and propose a region typology obtained through agglomerative clustering.