---
format: "aidr-story-markdown/v1"
id: "70b6e0e37bdecc39c45b084b82b4f1d8b668649a0825bb396264ebfe352198b1"
canonical_url: "https://aidr.today/70b6e0e3?lang=en"
title: "EarthRecord: From Pixels to Land Change with Multimodal Agents over Four Decades of Satellite Imagery"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-11T05:00:00.000Z"
category: "Data"
topics: ["agent","data-engineering"]
source_urls: ["https://arxiv.org/abs/2611.12934"]
summary: "EarthRecord is a benchmark built on the raw record of 56 sites featuring four decades of Landsat, MODIS, VIIRS, and Sentinel-2 data. It poses 238 land-change questions across ten analysis tasks. Evaluations of twelve multimodal agents reveal that leading agents complete most analyses end to end but falter when an answer requires mapping from imagery."
---

# EarthRecord: From Pixels to Land Change with Multimodal Agents over Four Decades of Satellite Imagery

> [Open the canonical story](<https://aidr.today/70b6e0e3?lang=en>)

**Published:** 2026-11-11T05:00:00.000Z
**Category:** Data
**Topics:** agent, data\-engineering

## Summary

EarthRecord is a benchmark built on the raw record of 56 sites featuring four decades of Landsat, MODIS, VIIRS, and Sentinel\-2 data\. It poses 238 land\-change questions across ten analysis tasks\. Evaluations of twelve multimodal agents reveal that leading agents complete most analyses end to end but falter when an answer requires mapping from imagery\.

## Sources

- [Story source](<https://arxiv.org/abs/2611.12934>)