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

arXiv cs.CV / 4/1/2026

💬 OpinionDeveloper Stack & InfrastructureTools & Practical UsageModels & Research

共有:

Key Points

The article presents EarthEmbeddingExplorer, an interactive, cloud-native web application that turns precomputed global Earth embeddings into a practical workflow for retrieval and discovery.
It provides a hands-on guide to the system’s architecture and demonstrates cross-modal queries using natural language, visual inputs, and geolocation.
The tutorial emphasizes how retrieval results can be used to derive scientific insights, not just to fetch similar items.
It aims to reduce the gap between academic foundation models/datasets and freely accessible tools for researchers to apply state-of-the-art resources in real-world analysis.
The application is made available via ModelScope Studios at https://modelscope.ai/studios/Major-TOM/EarthEmbeddingExplorer.

Abstract

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.