EarthEmbeddingExplorer: A Web Application for Cross-Modal Retrieval of Global Satellite Images
This work addresses the gap for Earth observation researchers in accessing and applying state-of-the-art models and data, though it is incremental as it focuses on tool development rather than new scientific or methodological advances.
The authors tackled the problem of translating academic Earth observation foundation models and datasets into accessible tools by introducing EarthEmbeddingExplorer, a web application that enables cross-modal retrieval of global satellite images through natural language, visual, and geolocation queries, making these resources freely available for practical use.
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.