mlsanityData to 7 Oct 2026

Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications

arXiv 2412.02732 ↗First posted 3 Dec 2024cs.CVcited by 139

Not on the map. Why?

Abstract (arXiv)

This paper presents Prithvi-EO-2.0, a new geospatial foundation model that offers significant improvements over its predecessor, Prithvi-EO-1.0. Trained on 4.2 million global time series samples from NASA's Harmonized Landsat and Sentinel-2 data archive at 30-m resolution, the new model incorporates temporal and location embeddings for enhanced performance across various geospatial tasks. Through extensive benchmarking with GEO-Bench, the model outperforms the previous Prithvi-EO model by 8% across a range of tasks. It also outperforms six other geospatial foundation models when benchmarked on remote sensing tasks from different domains and resolutions (i.e. from 0.1 m to 15 m). The results demonstrate the versatility of the model in both classical Earth observation and high-resolution applications. Early involvement of end-users and subject matter experts (SMEs) allowed constant feedback on model and dataset design, enabling customization across diverse SME-led applications in disaster response, land cover and crop mapping, and ecosystem dynamics monitoring. Prithvi-EO-2.0 is available as an open-source model on Hugging Face and IBM TerraTorch, with additional resources on GitHub. The project exemplifies the Trusted Open Science approach embraced by all involved organizations.

Key facts. Cited by 139 papers in the map (data through 7 Oct 2026). Builds on 25 of its 60 references that are in the map. First posted on arXiv 3 Dec 2024.

Builds on

25 of 60 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  8. 2021ViViT: A Video Vision Transformercited by 1,610
  9. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  10. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,305
  11. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  12. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 428
13 more
  1. 2022SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagerycited by 402
  2. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 302
  3. 2022SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understandingcited by 164
  4. 2023Foundation Models for Generalist Geospatial Artificial Intelligencecited by 143
  5. 2021Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networkscited by 141
  6. 2023GEO-Bench: Toward Foundation Models for Earth Monitoringcited by 122
  7. 2023Lightweight, Pre-trained Transformers for Remote Sensing Timeseriescited by 102
  8. 2024Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observationcited by 97
  9. 2020Lightweight Temporal Self-Attention for Classifying Satellite Image Time Seriescited by 55
  10. 2023Decoupling Common and Unique Representations for Multimodal Self-supervised Learningcited by 36
  11. 2023Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forwardcited by 28
  12. 2022The Outcome of the 2022 Landslide4Sense Competition: Advanced Landslide Detection from Multi-Source Satellite Imagerycited by 15
  13. 2023Assessment of a new GeoAI foundation model for flood inundation mappingcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 51; 2026: 87.

139 papers.

Sort:

By area:

  1. 2024AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalitiescited by 73
  2. 2025Galileo: Learning Global & Local Features of Many Remote Sensing Modalitiescited by 41
  3. 2025TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysiscited by 35
  4. 2025TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observationcited by 25
  5. 2025TerraTorch: The Geospatial Foundation Models Toolkitcited by 24
  6. 2025OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observationcited by 20
  7. 2025GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AIcited by 19
  8. 2025TerraMesh: A Planetary Mosaic of Multimodal Earth Observation Datacited by 14
  9. 2026OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agentscited by 13
  10. 2026Foundation Models in Remote Sensing: Evolving from Unimodality to Multimodalitycited by 12
  11. 2025Geo-OLM: Enabling Sustainable Earth Observation Studies with Cost-Efficient Open Language Models & State-Driven Workflowscited by 10
  12. 2025SSL4EO-S12 v1.1: A Multimodal, Multiseasonal Dataset for Pretraining, Updatedcited by 9
38 more
  1. 2025Fine-tune Smarter, Not Harder: Parameter-Efficient Fine-Tuning for Geospatial Foundation Modelscited by 9
  2. 2025Beyond the Visible: Multispectral Vision-Language Learning for Earth Observationcited by 7
  3. 2025Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curationcited by 7
  4. 2025GeoLink: Empowering Remote Sensing Foundation Model with OpenStreetMap Datacited by 7
  5. 2026THOR: A Versatile Foundation Model for Earth Observation Climate and Society Applicationscited by 6
  6. 2025Ice-FMBench: A Foundation Model Benchmark for Sea Ice Type Segmentationcited by 5
  7. 2025ExEBench: Benchmarking Foundation Models on Extreme Earth Eventscited by 5
  8. 2025TiMo: Spatiotemporal Foundation Model for Satellite Image Time Seriescited by 5
  9. 2026PRUE: A Practical Recipe for Field Boundary Segmentation at Scalecited by 5
  10. 2025ClimateBench-M: A Multi-Modal Climate Data Benchmark with a Simple Generative Methodcited by 4
  11. 2025GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait predictioncited by 4
  12. 2025RAMEN: Resolution-Adjustable Multimodal Encoder for Earth Observationcited by 4
  13. 2026Democratizing planetary-scale analysis: An ultra-lightweight Earth embedding database for accurate and flexible global land monitoringcited by 4
  14. 2026Any Model, Any Place, Any Time: Get Remote Sensing Foundation Model Embeddings On Demandcited by 4
  15. 2026UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observationcited by 4
  16. 2025A Survey on SAR ship classification using Deep Learningcited by 3
  17. 2025AQUAH: Automatic Quantification and Unified Agent in Hydrologycited by 3
  18. 2025SPEX: A Vision-Language Model for Land Cover Extraction on Spectral Remote Sensing Imagescited by 3
  19. 2025Surya: Foundation Model for Heliophysicscited by 3
  20. 2025Lightweight Metadata-Aware Mixture-of-Experts Masked Autoencoder for Earth Observationcited by 3
  21. 2025CSMoE: An Efficient Remote Sensing Foundation Model with Soft Mixture-of-Expertscited by 3
  22. 2026Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddingscited by 3
  23. 2025FPGA-Enabled Machine Learning Applications in Earth Observation: A Systematic Reviewcited by 2
  24. 2025MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Datacited by 2
  25. 2025A Sentinel-3 foundation model for ocean colourcited by 2
  26. 2025Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewardscited by 2
  27. 2025DeDelayed: Deleting Remote Inference Delay via On-Device Correctioncited by 2
  28. 2025SHRUG-FM: Reliability-Aware Foundation Models for Earth Observationcited by 2
  29. 2026IC-EO: Interpretable Code-based assistant for Earth Observationcited by 2
  30. 2026Enabling Training-Free Text-Based Remote Sensing Segmentationcited by 2
  31. 2026TerraFlow: Multimodal, Multitemporal Representation Learning for Earth Observationcited by 2
  32. 2026Earth Embeddings Reveal Diverse Urban Signals from Spacecited by 2
  33. 2026HighFM: Towards a Foundation Model for Learning Representations from High-Frequency Earth Observation Datacited by 2
  34. 2026Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Datacited by 2
  35. 2026GeoMeld: Toward Semantically Grounded Foundation Models for Remote Sensingcited by 2
  36. 2026A satellite foundation model for improved wealth monitoringcited by 2
  37. 2026SpectralEarth-FM: Bringing Hyperspectral Imagery into Multimodal Earth Observation Pretrainingcited by 2
  38. 2026Flood Mapping from RGB imagery using a Vision Foundation Modelcited by 2

50 most cited of 139 All 139 (JSON)