mlsanityData to 14 Oct 2026

Earth Embeddings as Products: Taxonomy, Ecosystem, and Standardized Access

arXiv 2601.13134 ↗First posted 19 Jan 2026cs.SE cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Geospatial Foundation Models (GFMs) provide powerful representations, but high compute costs hinder their widespread use. Pre-computed embedding data products offer a practical "frozen" alternative, yet they currently exist in a fragmented ecosystem of incompatible formats and resolutions. This lack of standardization creates an engineering bottleneck that prevents meaningful model comparison and reproducibility. We formalize this landscape through a three-layer taxonomy: Data, Tools, and Value. We survey existing products to identify interoperability barriers. To bridge this gap, we extend TorchGeo with a unified API that standardizes the loading and querying of diverse embedding products. By treating embeddings as first-class geospatial datasets, we decouple downstream analysis from model-specific engineering, providing a roadmap for more transparent and accessible Earth observation workflows.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 19 Jan 2026.

Builds on

25 of 33 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  3. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  4. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  5. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  6. 2023SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagerycited by 151
  7. 2025AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label datacited by 137
  8. 2024Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observationcited by 104
  9. 2025TerraMind: Large-Scale Generative Multimodality for Earth Observationcited by 104
  10. 2023Lightweight, Pre-trained Transformers for Remote Sensing Timeseriescited by 103
  11. 2022SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observationcited by 84
  12. 2024MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learningcited by 77
13 more
  1. 2021TorchGeo: Deep Learning With Geospatial Datacited by 73
  2. 2023Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networkscited by 61
  3. 2025Towards a Unified Copernicus Foundation Model for Earth Visioncited by 53
  4. 2025TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysiscited by 39
  5. 2023Decoupling Common and Unique Representations for Multimodal Self-supervised Learningcited by 36
  6. 2024Major TOM: Expandable Datasets for Earth Observationcited by 32
  7. 2024Multi-Label Guided Soft Contrastive Learning for Efficient Earth Observation Pretrainingcited by 28
  8. 2025OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observationcited by 24
  9. 2025Lossy Neural Compression for Geospatial Analytics: A Reviewcited by 10
  10. 2025Measuring the Intrinsic Dimension of Earth Representationscited by 10
  11. 2025NeuCo-Bench: A Novel Benchmark Framework for Neural Embeddings in Earth Observationcited by 7
  12. 2025Cropland Mapping using Geospatial Embeddingscited by 5
  13. 2025Leveraging Compact Satellite Embeddings and Graph Neural Networks for Large-Scale Poverty Mappingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026TESSERA v2: Scaling Pixel-wise Earth Foundation Modelscited by 5
  2. 2026Characterizing AlphaEarth Embedding Geometry for Agentic Environmental Reasoningcited by 4
  3. 2026EarthEmbeddingExplorer: A Web Application for Cross-Modal Retrieval of Global Satellite Imagescited by 1
  4. 2026Better Together: Evaluating the Complementarity of Earth Embedding Modelscited by 1
  5. 2026Earth Embeddingscited by 0