A Multi-Agent Feedback System for Detecting and Describing News Events in Satellite Imagery

TL;DR

This paper introduces SkyScraper, a multi-agent system that detects news-related events in satellite imagery, creating a new dataset and improving event detection accuracy over traditional methods.

Contribution

The paper presents SkyScraper, a novel multi-agent workflow that geocodes news articles and synthesizes captions for satellite image sequences, significantly enhancing multi-temporal event detection.

Findings

SkyScraper finds 5x more events than traditional geocoding methods.

It successfully curates a dataset of 5,000 multi-temporal satellite image sequences.

The framework supports journalism by automatically identifying news-related imagery.

Abstract

Changes in satellite imagery often occur over multiple time steps. Despite the emergence of bi-temporal change captioning datasets, there is a lack of multi-temporal event captioning datasets (at least two images per sequence) in remote sensing. This gap exists because (1) searching for visible events in satellite imagery and (2) labeling multi-temporal sequences require significant time and labor. To address these challenges, we present SkyScraper, an iterative multi-agent workflow that geocodes news articles and synthesizes captions for corresponding satellite image sequences. Our experiments show that SkyScraper successfully finds 5x more events than traditional geocoding methods, demonstrating that agentic feedback is an effective strategy for surfacing new multi-temporal events in satellite imagery. We apply our framework to a large database of global news articles, curating a new multi-temporal captioning dataset with 5,000 sequences. By automatically identifying imagery related to news events, our work also supports journalism and reporting efforts.