mlsanityData to 14 Oct 2026

SSL4EO-L: Datasets and Foundation Models for Landsat Imagery

arXiv 2306.09424 ↗First posted 15 Jun 2023cs.LG cs.CV eess.IVcited by 49

Not on the map. Why?

Abstract (arXiv)

The Landsat program is the longest-running Earth observation program in history, with 50+ years of data acquisition by 8 satellites. The multispectral imagery captured by sensors onboard these satellites is critical for a wide range of scientific fields. Despite the increasing popularity of deep learning and remote sensing, the majority of researchers still use decision trees and random forests for Landsat image analysis due to the prevalence of small labeled datasets and lack of foundation models. In this paper, we introduce SSL4EO-L, the first ever dataset designed for Self-Supervised Learning for Earth Observation for the Landsat family of satellites (including 3 sensors and 2 product levels) and the largest Landsat dataset in history (5M image patches). Additionally, we modernize and re-release the L7 Irish and L8 Biome cloud detection datasets, and introduce the first ML benchmark datasets for Landsats 4-5 TM and Landsat 7 ETM+ SR. Finally, we pre-train the first foundation models for Landsat imagery using SSL4EO-L and evaluate their performance on multiple semantic segmentation tasks. All datasets and model weights are available via the TorchGeo (https://github.com/microsoft/torchgeo) library, making reproducibility and experimentation easy, and enabling scientific advancements in the burgeoning field of remote sensing for a multitude of downstream applications.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 22 of its 69 references that are in the map. First posted on arXiv 15 Jun 2023.

Builds on

22 of 69 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  8. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  9. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  10. 2022SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagerycited by 408
  11. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 308
  12. 2021Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Datacited by 215
10 more
  1. 2020Geography-Aware Self-Supervised Learningcited by 190
  2. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  3. 2018Tile2Vec: Unsupervised representation learning for spatially distributed datacited by 110
  4. 2022An Empirical Study of Remote Sensing Pretrainingcited by 105
  5. 2022SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observationcited by 84
  6. 2021TorchGeo: Deep Learning With Geospatial Datacited by 73
  7. 2023Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidarcited by 60
  8. 2021Self-supervised pre-training enhances change detection in Sentinel-2 imagerycited by 21
  9. 2022K-textures, a self-supervised hard clustering deep learning algorithm for satellite image segmentationcited by 4
  10. 2022Self-Supervised Pretraining on Satellite Imagery: a Case Study on Label-Efficient Vehicle Detectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 14; 2025: 21; 2026: 13.

49 papers.

Sort:

By area:

  1. 2024Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observationcited by 104
  2. 2024Mission Critical -- Satellite Data is a Distinct Modality in Machine Learningcited by 77
  3. 2024AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalitiescited by 74
  4. 2024PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Modelscited by 68
  5. 2025Towards a Unified Copernicus Foundation Model for Earth Visioncited by 53
  6. 2024SpectralEarth: Training Hyperspectral Foundation Models at Scalecited by 42
  7. 2025Panopticon: Advancing Any-Sensor Foundation Models for Earth Observationcited by 34
  8. 2024On the Foundations of Earth and Climate Foundation Modelscited by 33
  9. 2024Multi-Label Guided Soft Contrastive Learning for Efficient Earth Observation Pretrainingcited by 28
  10. 2024CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentationcited by 27
  11. 2024Harnessing Massive Satellite Imagery with Efficient Masked Image Modelingcited by 12
  12. 2026Foundation Models in Remote Sensing: Evolving from Unimodality to Multimodalitycited by 12
37 more
  1. 2025EarthView: A Large Scale Remote Sensing Dataset for Self-Supervisioncited by 11
  2. 2025Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?cited by 10
  3. 2025GAIR: Location-Aware Self-Supervised Contrastive Pre-Training with Geo-Aligned Implicit Representationscited by 10
  4. 2025From Physics to Foundation Models: A Review of AI-Driven Quantitative Remote Sensing Inversioncited by 8
  5. 2025DOFA-CLIP: Multimodal Vision-Language Foundation Models for Earth Observationcited by 7
  6. 2023Fewshot learning on global multimodal embeddings for earth observation taskscited by 6
  7. 2024M3LEO: A Multi-Modal, Multi-Label Earth Observation Dataset Integrating Interferometric SAR and Multispectral Datacited by 6
  8. 2025FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mappingcited by 6
  9. 2024On the Generalizability of Foundation Models for Crop Type Mappingcited by 5
  10. 2025MultiMAE Meets Earth Observation: Pre-training Multi-modal Multi-task Masked Autoencoders for Earth Observation Taskscited by 5
  11. 2025Foundation Models for Environmental Science: A Survey of Emerging Frontierscited by 4
  12. 2025Landsat30-AU: A Vision-Language Dataset for Australian Landsat Imagerycited by 4
  13. 2026CrossEarth-SAR: A SAR-Centric and Billion-Scale Geospatial Foundation Model for Domain Generalizable Semantic Segmentationcited by 4
  14. 2024Rapid Adaptation of Earth Observation Foundation Models for Segmentationcited by 3
  15. 2024Generalized Few-Shot Semantic Segmentation in Remote Sensing: Challenge and Benchmarkcited by 3
  16. 2025Landsat-Bench: Datasets and Benchmarks for Landsat Foundation Modelscited by 3
  17. 2025Towards Scalable Foundation Model for Multi-modal and Hyperspectral Geospatial Datacited by 2
  18. 2025MSSDF: Modality-Shared Self-supervised Distillation for High-Resolution Multi-modal Remote Sensing Image Learningcited by 2
  19. 2025Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysiscited by 2
  20. 2026RSEdit: Text-Guided Image Editing for Remote Sensingcited by 2
  21. 2026A satellite foundation model for improved wealth monitoringcited by 2
  22. 2025Leveraging AI multimodal geospatial foundation models for improved near-real-time flood mapping at a global scalecited by 1
  23. 2026CBEN -- A Multimodal Machine Learning Dataset for Cloud Robust Remote Sensing Image Understandingcited by 1
  24. 2026NeighborMAE: Exploiting Spatial Dependencies between Neighboring Earth Observation Images in Masked Autoencoders Pretrainingcited by 1
  25. 2024Uncertainty and Generalizability in Foundation Models for Earth Observationcited by 0
  26. 2025Deep Self-Supervised Disturbance Mapping with the OPERA Sentinel-1 Radiometric Terrain Corrected SAR Backscatter Productcited by 0
  27. 2025Geospatial Machine Learning Librariescited by 0
  28. 2025Needles in the Landscape: Semi-Supervised Pseudolabeling for Archaeological Site Discovery under Label Scarcitycited by 0
  29. 2025LandSegmenter: Towards a Flexible Foundation Model for Land Use and Land Cover Mappingcited by 0
  30. 2025EoS-FM: Can an Ensemble of Specialist Models act as a Generalist Feature Extractor?cited by 0
  31. 2026Composable multi-satellite precipitation estimation for evolving observing systemscited by 0
  32. 2026Self-supervised training for high-resolution close-range multispectral remote sensing imagerycited by 0
  33. 2026Earth Embeddingscited by 0
  34. 2026HeatCast: A Benchmark for Neighborhood-Scale LST Forecasting across 124 U.S. Citiescited by 0
  35. 2026Earth Observation Foundation Models for Terrestrial Ecohydrology: From Representation Learning to Process Inferencecited by 0
  36. 2026Far from the Crowd: Scalable Self-Supervised Learning via Geographic Isolationcited by 0
  37. 2026SomBench: Benchmark Dataset for Advancing Machine Learning in Lunar Sciencecited by 0