EarthEmbeddingExplorer: A Web Application for Cross-Modal Retrieval of Global Satellite Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Yijie, Wu, Weijie, Wu, Bingyue, Zhao, Long, Li, Guoqing, Czerkawski, Mikolaj, Klemmer, Konstantin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911574208282624
author Zheng, Yijie
Wu, Weijie
Wu, Bingyue
Zhao, Long
Li, Guoqing
Czerkawski, Mikolaj
Klemmer, Konstantin
author_facet Zheng, Yijie
Wu, Weijie
Wu, Bingyue
Zhao, Long
Li, Guoqing
Czerkawski, Mikolaj
Klemmer, Konstantin
contents While the Earth observation community has witnessed a surge in high-impact foundation models and global Earth embedding datasets, a significant barrier remains in translating these academic assets into freely accessible tools. This tutorial introduces EarthEmbeddingExplorer, an interactive web application designed to bridge this gap, transforming static research artifacts into dynamic, practical workflows for discovery. We will provide a comprehensive hands-on guide to the system, detailing its cloud-native software architecture, demonstrating cross-modal queries (natural language, visual, and geolocation), and showcasing how to derive scientific insights from retrieval results. By democratizing access to precomputed Earth embeddings, this tutorial empowers researchers to seamlessly transition from state-of-the-art models and data archives to real-world application and analysis. The web application is available at https://modelscope.ai/studios/Major-TOM/EarthEmbeddingExplorer.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29441
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EarthEmbeddingExplorer: A Web Application for Cross-Modal Retrieval of Global Satellite Images
Zheng, Yijie
Wu, Weijie
Wu, Bingyue
Zhao, Long
Li, Guoqing
Czerkawski, Mikolaj
Klemmer, Konstantin
Computer Vision and Pattern Recognition
While the Earth observation community has witnessed a surge in high-impact foundation models and global Earth embedding datasets, a significant barrier remains in translating these academic assets into freely accessible tools. This tutorial introduces EarthEmbeddingExplorer, an interactive web application designed to bridge this gap, transforming static research artifacts into dynamic, practical workflows for discovery. We will provide a comprehensive hands-on guide to the system, detailing its cloud-native software architecture, demonstrating cross-modal queries (natural language, visual, and geolocation), and showcasing how to derive scientific insights from retrieval results. By democratizing access to precomputed Earth embeddings, this tutorial empowers researchers to seamlessly transition from state-of-the-art models and data archives to real-world application and analysis. The web application is available at https://modelscope.ai/studios/Major-TOM/EarthEmbeddingExplorer.
title EarthEmbeddingExplorer: A Web Application for Cross-Modal Retrieval of Global Satellite Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.29441