• Home
  • Search
  • Generalist Geospatial Foundation Model PhilEO on Satellite Sentinel-2 MajorTOM Multi-Spectral Data
  • https://doi.org/10.5194/egusphere-egu25-16635Copy DOI Icon

Generalist Geospatial Foundation Model PhilEO on Satellite Sentinel-2 MajorTOM Multi-Spectral Data

  • Mar 15, 2025
  • Nikolaos Dionelis +9 more
Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Recent advancements in AI and Self-Supervised Learning (SSL) have revolutionized large-scale computer vision models, enabling exceptional performance on downstream tasks in remote sensing with minimal labelled data. These models are pre-trained on large amounts of unlabelled data and, then, fine-tuned on specific downstream Earth Observation (EO) applications [1-3]. The scarcity of large-scale labelled datasets and the technical challenges of annotating the vast volumes of data collected by satellites pose significant barriers to achieving high accuracy in many important downstream tasks, which require extensive labeling at a large scale to be effective. Furthermore, the dynamic nature of Earth adds complexity, as labels at a particular moment in time are not enough. Consequently, SSL and Foundation Models offer a powerful solution to these challenges. By pre-training a Foundation Model on extensive unlabelled data, only a small amount of labelled data is required for supervised fine-tuning on downstream tasks. This approach reduces the need for labelled EO data. This enables the development of general-purpose EO Foundation Models capable of solving a diverse range of problems. In this work, we train the EO Foundation Model PhilEO Version 1.0 [2] on the dataset MajorTOM [6]. The model is trained on Sentinel-2 data, i.e. 23TB, Core-S2L2A. We scale up the pre-training data from less than 1TB in the dataset PhilEO-Globe [7] to 23TB. The model is trained using a combination of reconstruction and auxiliary task losses, including the Mean Squared Error (MSE) for geo-location longitude and latitude prediction. The architecture is a modified U-Net. The training is conducted on the Leonardo Davinci-1 supercomputer. In this work, we also extend the capabilities of the evaluation framework for EO Foundation Models we recently introduced in [2]. We develop PhilEO-Bench++. To take advantage of multi-level features and of a U-Net-like architecture, for fine-tuning on downstream tasks, we use the decoder UPerNet [4]. Furthermore, to strengthen the evaluation of EO Foundation Models, we also perform confidence quantification and assessment [5] on both classification and regression tasks, including on land cover semantic segmentation and building density pixel-wise regression. Experiments on the PhilEO-Bench downstream tasks of building density estimation, road segmentation and land cover mapping demonstrate the effectiveness of our model. For building density regression, for n-shots n=50 and n=100, the PhilEO model trained on MajorTOM achieves the MSEs 0.0191 and 0.0058, respectively. 

Similar Papers
  • PDF
  • Research Article
  • Citations1

CDEST: Class Distinguishability-Enhanced Self-Training Method for Adopting Pre-Trained Models to Downstream Remote Sensing Image Semantic Segmentation

  • Apr 06, 2024
  • Remote Sensing
  • Ming Zhang +7
  • Preprint Article

Towards Foundation Models for Earth Observation; Benchmarking Datasets and Performance on Diverse Downstream Tasks

  • Nov 27, 2024
  • Anna Jungbluth +6
  • PDF
  • Research Article
  • Citations16

A Generic Self-Supervised Learning (SSL) Framework for Representation Learning from Spectral–Spatial Features of Unlabeled Remote Sensing Imagery

  • Nov 03, 2023
  • Remote Sensing
  • Xin Zhang +1
  • Preprint Article

GeoDINO: A Vision Foundation Model for Earth Observation Leveraging DINO Architecture and Sentinel-2 Multi-Spectral Data

  • Mar 15, 2025
  • Riccardo Musto +9
  • Conference Article
  • Citations13

Multi-Modal Self-Supervised Representation Learning for Earth Observation

  • Jul 11, 2021
  • Pallavi Jain +2
  • PDF
  • Research Article
  • Citations4

Deep learning based on self-supervised pre-training: Application on sandstone content prediction

  • Jan 10, 2023
  • Frontiers in Earth Science
  • Chong Ming Wang +5
  • Research Article
  • Citations286

RingMo: A Remote Sensing Foundation Model With Masked Image Modeling

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Xian Sun +14
  • Conference Article
  • Citations12

Conformer-Based Self-Supervised Learning For Non-Speech Audio Tasks

  • May 23, 2022
  • Sangeeta Srivastava +6
  • Supplementary Content
  • Citations259

Self-supervised Learning: A Succinct Review

  • Jan 01, 2023
  • Archives of Computational Methods in Engineering
  • Veenu Rani +4
  • Conference Article
  • Citations2

A Novel Multi-Task Self-Supervised Representation Learning Paradigm

  • May 28, 2021
  • Control theory & applications
  • Yinggang Li +5
  • Research Article
  • Citations20

Self-supervised visual learning in the low-data regime: A comparative evaluation

  • Mar 01, 2025
  • Neurocomputing
  • Sotirios Konstantakos +6
  • Research Article

A Self-Supervised Learning of a Foundation Model for Analog Layout Design Automation

  • Feb 01, 2026
  • IEEE Transactions on Circuits and Systems I: Regular Papers
  • Sungyu Jeong +4
  • Conference Article
  • Citations1

Self-Supervised Contrastive Learning on Cross-Augmented Samples for SAR Target Recognition

  • May 01, 2023
  • Xiaoyu Liu +6
  • Research Article
  • Citations43

Steel surface defect detection based on self-supervised contrastive representation learning with matching metric

  • Jun 30, 2023
  • Applied Soft Computing
  • Xuejin Hu +5
  • Conference Article
  • Citations51

Divide and Contrast: Self-supervised Learning from Uncurated Data

  • Oct 01, 2021
  • Yonglong Tian +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.