TorchGeo embeddings

arXiv:2601.13134v1 [cs.SE] 19 Jan 2026

Earth Embeddings as Products: Taxonomy, Ecosystem, and Standardized Access is a comprehensive survey that organizes existing geospatial embedding products into a structured taxonomy through a three-layer taxonomy: Data, Tools, and Value. This research paper provides a detailed metadata atlas (resolution, license, etc.). It also proposes a unified integration by implementing standardized data loaders for these embeddings in [TorchGeo] .

An overview landscape is proposed comprising: a) Analysis Frameworks & Tools b) Embeddings data artifacts c) Charting downstream application value, specifically mapping tasks and retrieval tasks.

Embeddings are differentiated as either location-typed, patch-typed, or pixel-typed. Details of existing products are shown. "We extend TorchGeo with a unified API that standardizes the loading and querying of diverse embedding products."

1. Foundation Models for Earth Observation (EO)

These are the leading projects that aim to build general-purpose models capable of representing Earth from satellite imagery and other geospatial modalities.

Projects

• Clay Foundation Model – [HuggingFace] (2024)

  A multimodal foundation model for Earth using diverse data sources.

• Major TOM – [MajorTOM] AFrancis IGARSS 2024

  Expandable datasets and models for global EO coverage.

• Earth Index Embeddings – [EarthGenome] (2025)

  A large-scale embedding system built from Earth observation data.

• Copernicus-Embed – [LINK] Zhu et al., AI4Copernicus Project

  Foundation model leveraging Copernicus Sentinel data.

• Presto Embeddings – [NASAHarvest]

  Embedding framework for satellite time series and land use analysis.

• Tessera Embeddings – [GeoTessera] Docs / [REPO]

  Pixel-based Temporal spectral embeddings for Earth representation.

• Google Satellite Embedding (AlphaEarth) – [LINK] Google Earth Engine

  An early-stage embedding model using Google's global satellite data.

• OlmoEarth – [AllenAI] (2025)

  Latent image modeling approach for multimodal Earth observation.

Key Papers

• XXZhu 2025 [LINK] "On the Foundations of Earth Foundation Models" – Nature Computational Science
• CFBrown 2025 [LINK] "AlphaEarth Foundations"
• KKlemmer 2023 [LINK] "SatCLIP: Global Location Embeddings with Satellite Imagery"

2. Datasets

Large-scale, open-access datasets play a central role in training and evaluating Earth foundation models.

Datasets

• EuroSAT – [Zenodo]

Land use classification dataset using Sentinel-2 satellite data.

• EuroCrops – [PMC_10495462]

Crop type mapping dataset for Europe.

• National Land Cover Database (NLCD) – [LINK] Photogrammetric Engineering & Remote Sensing (2001)

USA land cover classes.

• SSL4EO-S12 – [LINK] IEEE Geoscience and Remote Sensing (2023)

Multimodal, multitemporal dataset for self-supervised learning.

• Copernicus-Pretrain [LINK] IEEE Geoscience and Remote Sensing (2023)

An extension of the SSL4EO-S12 dataset to all major Sentinel missions (S1-S5P).

3. Models & Methods

These include both classical and cutting-edge machine learning approaches used in building Earth foundation models.

Core Methods

• SatCLIP – [LINK] AAAI 2025 etc.

Vision-language model for global location representations.

• MMEarth – [LINK] EU/CV 2024

Multimodal pretext tasks for geospatial representation learning.

• ResNet – [LINK] |KHe IEEE/CV 2016

Baseline CNN architecture widely used in EO.

• ConvNeXt V2 – [LINK] Woo et al., IEEE/CVF 2023

Efficient ConvNet architecture using masked autoencoders (MAE).

• DINO, DINOv2, DINOv3 – [LINK] INRIA 2021–2023, META

Vision transformers with self-supervised learning capabilities.

• MAE (Masked Autoencoders) – [LINK] IEEE/CVF 2021

Self-supervised learning for vision transformers.

Distillation & Advanced Approaches

• Distillation methods – Transfer knowledge from large models.
• Neural plasticity-inspired models – TorchGeo_DOFA: Inspired by biological learning mechanisms.
• Multi-label guided soft contrastive learning – YWang, IEEE TGRS, 2024.
• Barlow Twins – Method for learning representations without contrastive loss.
• Continual Barlow Twins – Extends Barlow Twins to continual learning in EO segmentation.

4. Tools & Benchmarks

These are software systems and frameworks that support development, evaluation, or deployment of EO AI models.

Tools

• TorchGeo – [TorchGeo] [ACM] AJStewart et.al.

PyTorch library for geospatial deep learning.

• NeuCo-Bench – [LINK] RVinge, arXiv 2025

Benchmarking framework for neural embeddings in Earth observation.

• GeoINRID – [LINK] GitHub: arjunarao619/GeoINRID

Geospatial inference and representation learning toolkit.

Challenges

• Embed2Scale Challenge – [LINK] CVPR CAlbrecht 2025

Large-scale Earth vision challenge focused on scale-aware embeddings.

• TerraMind Blue-Sky Challenge –

Generative modeling for Earth observation.

5. Key Themes & Trends

1. Foundation Models: TorchGeo now includes data loaders designed for search/retrieval (Clay, Major TOM, Earth Index), and for dense prediction tasks like land cover mapping (Copernicus, Presto, Tessera, Google). TorchGeo allows us to enable fair, side-by-side benchmarking of different embedding models on the same downstream tasks, forming the basis for future experiments. Projects are encouraged to strengthen and improve explainability.
   • Major TOM Notes: Major TOM embeddings are not (yet) really product-oriented and are aimed with a similar purpose to the MT Core datasets - to make it easier to experiment and benchmark model outputs (hence, unlike TESSERA and AEF which came a few months after, MT embeddings do not have consistent or aggregated temporal scope). We haven't had enough time to finish off the preprint, but my current plan is to provide a simple MT Embedding benchmark at this year's EGU and integrate that into the arxiv pre-print. --Miko
   • Earth Index / Earth Genome: Use the Earth Index application (earthindex.ai) for non-technical users to use the embeddings we published on source.coop. Users of the web app (non-technical journalists, indigenous communities/allies, NGOs) have been our main focus. Users of the source.coop embeddings have generally been more technical folks interested in exploring/innovating in what's possible --BenStrong
   • Clay: Clay and Presto offer documented tutorials on generating new embeddings with their models. In CLAY, the encoder receives unmasked patches, latitude-longitude data, and timestep information. Notably, the last 2 embeddings from the encoder specifically represent the latitude-longitude and timestep embeddings.

1. Self-Supervised Learning (SSL):

1. Multimodal Integration:

1. Open Data & Tools: Open-source projects (e.g., TorchGeo, Copernicus-Embed) and public datasets (EuroSAT, EuroCrops) are crucial for reproducibility and democratization of EO AI. Projects are encouraged to increase Input Data Diversity, and to adopt cloud-native data formats for geospatial data.

1. Benchmarking: Projects are encouraged to standardize in benchmarking. Benchmarks including NeuCo-Bench and Embed2Scale.

Research Directions

• Unified Earth Foundation Models:
• Interpretability in EO AI: Exploring how these embeddings can be interpreted by domain experts.
• Ethics and Bias: Investigating fairness and bias in global EO models trained on unevenly distributed data.
• Edge Deployment: Making these large foundation models deployable on resource-constrained platforms (e.g., for field use).