Foundation Models for Geospatial Reasoning: Assessing Capabilities of Large Language Models in Understanding Geometries and Topological Spatial Relations

TL;DR

This study evaluates large language models' ability to understand and reason with geospatial geometries and topological relations, revealing promising accuracy levels and highlighting potential for developing geo-foundation models.

Contribution

It introduces a systematic assessment of LLMs in geospatial reasoning, comparing different approaches and demonstrating GPT-4's superior performance in understanding spatial relations.

Findings

GPT-4 with few-shot prompting achieved over 0.66 accuracy.

Embedding and prompt engineering approaches both achieved over 0.6 accuracy.

GPT models can interpret inverse topological relations and translate vernacular descriptions.

Abstract

Applying AI foundation models directly to geospatial datasets remains challenging due to their limited ability to represent and reason with geographical entities, specifically vector-based geometries and natural language descriptions of complex spatial relations. To address these issues, we investigate the extent to which a well-known-text (WKT) representation of geometries and their spatial relations (e.g., topological predicates) are preserved during spatial reasoning when the geospatial vector data are passed to large language models (LLMs) including GPT-3.5-turbo, GPT-4, and DeepSeek-R1-14B. Our workflow employs three distinct approaches to complete the spatial reasoning tasks for comparison, i.e., geometry embedding-based, prompt engineering-based, and everyday language-based evaluation. Our experiment results demonstrate that both the embedding-based and prompt engineering-based approaches to geospatial question-answering tasks with GPT models can achieve an accuracy of over 0.6 on average for the identification of topological spatial relations between two geometries. Among the evaluated models, GPT-4 with few-shot prompting achieved the highest performance with over 0.66 accuracy on topological spatial relation inference. Additionally, GPT-based reasoner is capable of properly comprehending inverse topological spatial relations and including an LLM-generated geometry can enhance the effectiveness for geographic entity retrieval. GPT-4 also exhibits the ability to translate certain vernacular descriptions about places into formal topological relations, and adding the geometry-type or place-type context in prompts may improve inference accuracy, but it varies by instance. The performance of these spatial reasoning tasks offers valuable insights for the refinement of LLMs with geographical knowledge towards the development of geo-foundation models capable of geospatial reasoning.