Geo2Vec: Shape- and Distance-Aware Neural Representation of Geospatial Entities

TL;DR

Geo2Vec introduces a unified, shape- and distance-aware neural embedding for diverse geospatial entities, improving representation quality and efficiency in GeoAI applications by directly modeling geometry in the original space.

Contribution

It presents a novel SDF-inspired method that adaptively samples and encodes geospatial shapes, enabling unified, geometry-aware embeddings for all entity types without decomposition.

Findings

Outperforms existing methods in shape and location representation

Captures topological and distance relationships effectively

Achieves greater efficiency in real-world GeoAI tasks

Abstract

Spatial representation learning is essential for GeoAI applications such as urban analytics, enabling the encoding of shapes, locations, and spatial relationships (topological and distance-based) of geo-entities like points, polylines, and polygons. Existing methods either target a single geo-entity type or, like Poly2Vec, decompose entities into simpler components to enable Fourier transformation, introducing high computational cost. Moreover, since the transformed space lacks geometric alignment, these methods rely on uniform, non-adaptive sampling, which blurs fine-grained features like edges and boundaries. To address these limitations, we introduce Geo2Vec, a novel method inspired by signed distance fields (SDF) that operates directly in the original space. Geo2Vec adaptively samples points and encodes their signed distances (positive outside, negative inside), capturing geometry without decomposition. A neural network trained to approximate the SDF produces compact, geometry-aware, and unified representations for all geo-entity types. Additionally, we propose a rotation-invariant positional encoding to model high-frequency spatial variations and construct a structured and robust embedding space for downstream GeoAI models. Empirical results show that Geo2Vec consistently outperforms existing methods in representing shape and location, capturing topological and distance relationships, and achieving greater efficiency in real-world GeoAI applications. Code and Data can be found at: https://github.com/chuchen2017/GeoNeuralRepresentation.