Geolocation Representation from Large Language Models are Generic Enhancers for Spatio-Temporal Learning

TL;DR

This paper introduces a training-free method called LLMGeovec that uses large language models and map data to generate geolocation representations, enhancing various spatio-temporal learning tasks without high data costs.

Contribution

The paper presents a novel, training-free approach leveraging LLMs and map data to create universal geolocation representations that improve multiple spatio-temporal models.

Findings

LLMGeovec achieves global coverage for geolocation representation.

It significantly boosts performance across geographic prediction, time series forecasting, and graph-based models.

The method seamlessly integrates into existing models without additional training.

Abstract

In the geospatial domain, universal representation models are significantly less prevalent than their extensive use in natural language processing and computer vision. This discrepancy arises primarily from the high costs associated with the input of existing representation models, which often require street views and mobility data. To address this, we develop a novel, training-free method that leverages large language models (LLMs) and auxiliary map data from OpenStreetMap to derive geolocation representations (LLMGeovec). LLMGeovec can represent the geographic semantics of city, country, and global scales, which acts as a generic enhancer for spatio-temporal learning. Specifically, by direct feature concatenation, we introduce a simple yet effective paradigm for enhancing multiple spatio-temporal tasks including geographic prediction (GP), long-term time series forecasting (LTSF), and graph-based spatio-temporal forecasting (GSTF). LLMGeovec can seamlessly integrate into a wide spectrum of spatio-temporal learning models, providing immediate enhancements. Experimental results demonstrate that LLMGeovec achieves global coverage and significantly boosts the performance of leading GP, LTSF, and GSTF models. Our codes are available at \url{https://github.com/Umaruchain/LLMGeovec}.