Leveraging ChatGPT's Multimodal Vision Capabilities to Rank Satellite Images by Poverty Level: Advancing Tools for Social Science Research

TL;DR

This study explores how ChatGPT's multimodal vision capabilities can be used to rank satellite images by poverty level, offering a scalable tool for social science research and poverty monitoring.

Contribution

It demonstrates the novel application of vision-enabled LLMs like ChatGPT for geospatial poverty assessment, showing their potential to match expert accuracy.

Findings

ChatGPT can rank satellite images by poverty level with expert-level accuracy.

Vision-enabled LLMs offer interpretable and scalable insights into socioeconomic conditions.

The approach provides a foundation for large-scale, cost-effective poverty monitoring.

Abstract

This paper investigates the novel application of Large Language Models (LLMs) with vision capabilities to analyze satellite imagery for village-level poverty prediction. Although LLMs were originally designed for natural language understanding, their adaptability to multimodal tasks, including geospatial analysis, has opened new frontiers in data-driven research. By leveraging advancements in vision-enabled LLMs, we assess their ability to provide interpretable, scalable, and reliable insights into human poverty from satellite images. Using a pairwise comparison approach, we demonstrate that ChatGPT can rank satellite images based on poverty levels with accuracy comparable to domain experts. These findings highlight both the promise and the limitations of LLMs in socioeconomic research, providing a foundation for their integration into poverty assessment workflows. This study contributes to the ongoing exploration of unconventional data sources for welfare analysis and opens pathways for cost-effective, large-scale poverty monitoring.