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

arXiv: https://arxiv.org/abs/2501.14546 · HTML: https://mlsanity.com/paper/2501.14546/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 34 references that are in the map.
- First posted on arXiv 24 Jan 2025.

## Builds on (most cited first, 11 of 11)

- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [Using satellite imagery to understand and promote sustainable development](https://mlsanity.com/paper/2010.06988/) (2020)
- [GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks](https://mlsanity.com/paper/2411.19325/) (2024)
- [Preference Learning Algorithms Do Not Learn Preference Rankings](https://mlsanity.com/paper/2405.19534/) (2024)
- [Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data](https://mlsanity.com/paper/2401.17600/) (2024)
- [Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping](https://mlsanity.com/paper/1510.00098/) (2015)
- [From the Fair Distribution of Predictions to the Fair Distribution of Social Goods: Evaluating the Impact of Fair Machine Learning on Long-Term Unemployment](https://mlsanity.com/paper/2401.14438/) (2024)
- [High-Resolution Poverty Maps in Sub-Saharan Africa](https://mlsanity.com/paper/2009.00544/) (2020)
- [Towards Explaining Satellite Based Poverty Predictions with Convolutional Neural Networks](https://mlsanity.com/paper/2312.00416/) (2023)

## Built on by (most cited first, 1 of 1)

- [Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?](https://mlsanity.com/paper/2508.01109/) (2025)

## Abstract (arXiv)

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 perform 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. Our results also put forward the question of how reliable the anonymized public datasets, such as DHS, are for retrieving wealth indices. The code and data used for the analyses in this paper are publicly available.