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

DevFeed: [Leveraging ChatGPT's Multimodal Vision Capabilities to Rank Satellite Images by Poverty Level: Advancing Tools for Social Science Research](<https://devfeed.tech/articles/leveraging-chatgpt-s-multimodal-vision-capabilities-to-rank-satellite-images-by-poverty-level-advancing-tools-for-social-science-research-119973.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2501.14546>)

Author: Hamid Sarmadi, Ola Hall, Thorsteinn R\\"ognvaldsson, Mattias Ohlsson

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Computer vision](<https://devfeed.tech/topics/computer-vision.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>)

Tags: [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [data](<https://devfeed.tech/tags/data.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [dhs](<https://devfeed.tech/tags/dhs.md>), [features](<https://devfeed.tech/tags/features.md>), [geospatial](<https://devfeed.tech/tags/geospatial.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [noise](<https://devfeed.tech/tags/noise.md>), [novel](<https://devfeed.tech/tags/novel.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [rank](<https://devfeed.tech/tags/rank.md>), [research](<https://devfeed.tech/tags/research.md>), [satellite](<https://devfeed.tech/tags/satellite.md>), [social](<https://devfeed.tech/tags/social.md>), [vision](<https://devfeed.tech/tags/vision.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

## AI overview

Using pairwise comparisons, the study finds that vision-enabled ChatGPT can rank satellite images by village poverty with accuracy comparable to a model trained on features identified by human experts, and higher than direct expert wealth classifications reported previously. The authors present this as a potential tool for scalable poverty assessment while noting limitations and questioning whether DHS wealth indices remain reliable when location coordinates are anonymized with added noise. The evidence provided is an abstract, so it does not give further methodological detail or quantify the reported accuracy.

## Source excerpt

arXiv:2501.14546v4 Announce Type: replace-cross 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 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 an accuracy comparable to a model trained on human-expert-identified image features and better than direct expert wealth classifications reported previously. 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 public datasets, such as DHS, are for retrieving wealth indices that are anonymized by adding noise to the location coordinates. The code and data used for the analyses in this paper are publicly available.