---
title: "Embed the world: Multimodal AI for searchable aerial imagery at scale"
slug: "aws-macht-luftbilder-per-ki-durchsuchbar-nova-liegt-bei-semantischer-suche-vorn"
date: 2026-06-22
category: tech-pub
tags: [amazon]
language: en
sources_count: 1
featured: false
publisher: AInauten News
url: https://news.ainauten.com/en/story/aws-macht-luftbilder-per-ki-durchsuchbar-nova-liegt-bei-semantischer-suche-vorn
---

# Embed the world: Multimodal AI for searchable aerial imagery at scale

**Published**: 2026-06-22 | **Category**: tech-pub | **Sources**: 1

---

## TL;DR

- AWS outlines a search architecture for Vexcels aerial imagery: tiles are embedded via Amazon Bedrock, indexed in Amazon OpenSearch Serverless, and queried with natural language.

---

## Summary

- AWS outlines a search architecture for Vexcels aerial imagery: tiles are embedded via Amazon Bedrock, indexed in Amazon OpenSearch Serverless, and queried with natural language.
- The benchmark used OpenStreetMap as ground truth for Grant Park in Chicago and compared about 100 configurations across two query types: swimming pools as discrete objects and roads as distributed infrastructure.
- Amazon Nova Multimodal Embeddings led the test, with average F1 scores of 0.621 for pools and 0.555 for roads. Cohere Embed v4 was close on pools but weaker on roads.
- Captioning was the biggest lever: structured descriptions of the image views improved F1 by 11 percent for pools and 13 percent for roads. Text-only search still performed clearly worse.

---

## Why it matters

AWS outlines a search architecture for Vexcels aerial imagery: tiles are embedded via Amazon Bedrock, indexed in Amazon OpenSearch Serverless, and queried with natural language.

---

## Key Points

- AWS outlines a search architecture for Vexcels aerial imagery: tiles are embedded via Amazon Bedrock, indexed in Amazon OpenSearch Serverless, and queried with natural language.
- The benchmark used OpenStreetMap as ground truth for Grant Park in Chicago and compared about 100 configurations across two query types: swimming pools as discrete objects and roads as distributed infrastructure.
- Amazon Nova Multimodal Embeddings led the test, with average F1 scores of 0.621 for pools and 0.555 for roads. Cohere Embed v4 was close on pools but weaker on roads.
- Captioning was the biggest lever: structured descriptions of the image views improved F1 by 11 percent for pools and 13 percent for roads. Text-only search still performed clearly worse.

---

## Nauti's Take

The post is clearly AWS- and Vexcel-friendly, but the useful part sits in the uncomfortable details. Multimodal search does not work here because a big model magically understands geography. It works because the team defined what counts as a hit, tested K values, checked which image views were worth paying for, and measured captions against visual embeddings. That is where demo AI starts becoming production AI.

---


## FAQ

**Q:** What is Embed the world about?

**A:** - AWS outlines a search architecture for Vexcels aerial imagery: tiles are embedded via Amazon Bedrock, indexed in Amazon OpenSearch Serverless, and queried with natural language.

**Q:** Why does it matter?

**A:** AWS outlines a search architecture for Vexcels aerial imagery: tiles are embedded via Amazon Bedrock, indexed in Amazon OpenSearch Serverless, and queried with natural language.

**Q:** What are the key takeaways?

**A:** AWS outlines a search architecture for Vexcels aerial imagery: tiles are embedded via Amazon Bedrock, indexed in Amazon OpenSearch Serverless, and queried with natural language.. The benchmark used OpenStreetMap as ground truth for Grant Park in Chicago and compared about 100 configurations across two query types: swimming pools as discrete objects and roads as distributed infrastructure.. Amazon Nova Multimodal Embeddings led the test, with average F1 scores of 0.621 for pools and 0.555 for roads. Cohere Embed v4 was close on pools but weaker on roads.

---

## Related Topics

- [amazon](https://news.ainauten.com/en/tag/amazon)

---

## Sources

- [Embed the world: Multimodal AI for searchable aerial imagery at scale](https://aws.amazon.com/blogs/machine-learning/embed-the-world-multimodal-ai-for-searchable-aerial-imagery-at-scale/) - AWS Machine Learning Blog

---

## About This Article

This article is a synthesis of 1 sources, curated and summarized by AInauten News. We aggregate AI news from trusted sources and provide bilingual (German/English) coverage.

**Publisher**: [AInauten](https://www.ainauten.com) | **Site**: [news.ainauten.com](https://news.ainauten.com)

---

*Last Updated: 2026-06-24*