cs.AINov 10, 2026

Earth Embeddings in Environmental Remote Sensing

Authors: Yuchi Ma, Jiaqi Yang, Mengyu Liang, Ivan Higuera-Mendieta, Caleb Robinson, Anthony Ortiz, Min Chen, David B. Lobell, 

Organizations: Microsoft AI for Good Lab, Redmond, WA, USA · Department of Forest and Wildlife Ecology, University of Wisconsin-Madison, Madison, WI, USA · Department of Earth System Science, Stanford University, Stanford, CA, USA · Department of Geographical Sciences, University of Maryland, College Park, MD, USA · 

Abstract

Earth observations from satellite platforms have profoundly transformed research and applications across numerous domains. However, uneven observation coverage and frequent data gaps continue to limit their ability to capture Earth's surface dynamics. Moreover, processing multi-modal Earth observations requires substantial computational resources and sophisticated data harmonization frameworks, which may not be readily accessible to many remote sensing practitioners. Earth embeddings have emerged as promising solutions to these challenges. As general-purpose representations converted from multi-source Earth observations, Earth embeddings can support a wide range of downstream tasks with no requirement of task-specific feature design and preprocessing. In this study, we first introduce the theoretical foundations of Earth embeddings. Then, we review several representative Earth embedding products. We next examine the applications of Earth embeddings across six major domains of environmental remote sensing. Finally, we systematically assess the performance of Earth embeddings in four downstream tasks, including hyperspectral image classification, individual tree crown segmentation, crop yield prediction, and aboveground biomass mapping. Our review and case studies suggest that, despite several advantages over conventional Earth observation data, current Earth embeddings do not always outperform remote sensing imagery or hand-crafted features. Earth embeddings should not be viewed as a direct replacement for conventional EO data, but rather as representations that provide stable information across space and time. Remote sensing practitioners may consider evaluating Earth embeddings' suitability for specific tasks and using them strategically, rather than assuming superior performance by default.

Explore similar work

CardsList
  1. Earth Embeddings

    Aug 4, 2026Adam J. Stewart, Heng Fang, Isaac A. Corley +1Geospatial Representation LearningLand Cover Classification

  2. Better Together: Evaluating the Complementarity of Earth Embedding Models

    May 18, 2026Thijs L van der Plas, Jacob JW Bakermans, Vishal Nedungadi +3Geospatial Foundation ModelsGeospatial Representation Learning

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

    Mar 31, 2026Yijie Zheng, Weijie Wu, Zhuoyao He +5Remote Sensing