Large Multi-modal Model Cartographic Map Comprehension for Textual Locality Georeferencing

TL;DR

This paper introduces a novel multi-modal approach using Large Multi-Modal Models to improve georeferencing of biological sample locations by visually contextualizing spatial relations, achieving around 1 km accuracy.

Contribution

It presents a new zero-shot multi-modal method leveraging maps within LMMs for georeferencing, outperforming existing uni-modal and traditional tools.

Findings

Achieved approximately 1 km average distance error

Demonstrated the effectiveness of visual contextualization in georeferencing

Proposed a practical framework for integrating the method into workflows

Abstract

Millions of biological sample records collected in the last few centuries archived in natural history collections are un-georeferenced. Georeferencing complex locality descriptions associated with these collection samples is a highly labour-intensive task collection agencies struggle with. None of the existing automated methods exploit maps that are an essential tool for georeferencing complex relations. We present preliminary experiments and results of a novel method that exploits multi-modal capabilities of recent Large Multi-Modal Models (LMM). This method enables the model to visually contextualize spatial relations it reads in the locality description. We use a grid-based approach to adapt these auto-regressive models for this task in a zero-shot setting. Our experiments conducted on a small manually annotated dataset show impressive results for our approach ($\sim$1 km Average distance error) compared to uni-modal georeferencing with Large Language Models and existing georeferencing tools. The paper also discusses the findings of the experiments in light of an LMM's ability to comprehend fine-grained maps. Motivated by these results, a practical framework is proposed to integrate this method into a georeferencing workflow.