Geolocation Representation from Large Language Models are Generic Enhancers for Spatio-Temporal Learning
This provides a low-cost, generic enhancer for spatio-temporal learning tasks, addressing a gap in geospatial AI for researchers and practitioners.
The authors tackled the lack of universal representation models in geospatial domains by developing LLMGeovec, a training-free method that uses large language models and OpenStreetMap data to derive geolocation representations, which significantly boosts performance in tasks like geographic prediction, long-term time series forecasting, and graph-based spatio-temporal forecasting.
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}.