Towards a Unified Copernicus Foundation Model for Earth Vision

Advances in Earth observation (EO) foundation models have unlocked the potential of big satellite data to learn generic representations from space, benefiting a wide range of downstream applications crucial to our planet. However, most existing efforts remain limited to fixed spectral sensors, focus solely on the Earth's surface, and overlook valuable metadata beyond imagery. In this work, we take a step towards next-generation EO foundation models with three key components: 1) Copernicus-Pretrain, a massive-scale pretraining dataset that integrates 18.7M aligned images from all major Copernicus Sentinel missions, spanning from the Earth's surface to its atmosphere; 2) Copernicus-FM, a unified foundation model capable of processing any spectral or non-spectral sensor modality using extended dynamic hypernetworks and flexible metadata encoding; and 3) Copernicus-Bench, a systematic evaluation benchmark with 15 hierarchical downstream tasks ranging from preprocessing to specialized applications for each Sentinel mission. Our dataset, model, and benchmark greatly improve the scalability, versatility, and multimodal adaptability of EO foundation models, while also creating new opportunities to connect EO, weather, and climate research. Codes, datasets and models are available at https://github.com/zhu-xlab/Copernicus-FM.

On the Generalization of Representation Uncertainty in Earth Observation

Recent advances in Computer Vision have introduced the concept of pretrained representation uncertainty, enabling zero-shot uncertainty estimation. This holds significant potential for Earth Observation (EO), where trustworthiness is critical, yet the complexity of EO data poses challenges to uncertainty-aware methods. In this work, we investigate the generalization of representation uncertainty in EO, considering the domain's unique semantic characteristics. We pretrain uncertainties on large EO datasets and propose an evaluation framework to assess their zero-shot performance in multi-label classification and segmentation EO tasks. Our findings reveal that, unlike uncertainties pretrained on natural images, EO-pretraining exhibits strong generalization across unseen EO domains, geographic locations, and target granularities, while maintaining sensitivity to variations in ground sampling distance. We demonstrate the practical utility of pretrained uncertainties showcasing their alignment with task-specific uncertainties in downstream tasks, their sensitivity to real-world EO image noise, and their ability to generate spatial uncertainty estimates out-of-the-box. Initiating the discussion on representation uncertainty in EO, our study provides insights into its strengths and limitations, paving the way for future research in the field. Code and weights are available at: https://github.com/Orion-AI-Lab/EOUncertaintyGeneralization.

FireCastNet: Earth-as-a-Graph for Seasonal Fire Prediction

With climate change expected to exacerbate fire weather conditions, the accurate and timely anticipation of wildfires becomes increasingly crucial for disaster mitigation. In this study, we utilize SeasFire, a comprehensive global wildfire dataset with climate, vegetation, oceanic indices, and human-related variables, to enable seasonal wildfire forecasting with machine learning. For the predictive analysis, we present FireCastNet, a novel architecture which combines a 3D convolutional encoder with GraphCast, originally developed for global short-term weather forecasting using graph neural networks. FireCastNet is trained to capture the context leading to wildfires, at different spatial and temporal scales. Our investigation focuses on assessing the effectiveness of our model in predicting the presence of burned areas at varying forecasting time horizons globally, extending up to six months into the future, and on how different spatial or/and temporal context affects the performance. Our findings demonstrate the potential of deep learning models in seasonal fire forecasting; longer input time-series leads to more robust predictions, while integrating spatial information to capture wildfire spatio-temporal dynamics boosts performance. Finally, our results hint that in order to enhance performance at longer forecasting horizons, a larger receptive field spatially needs to be considered.

Seasonal Fire Prediction using Spatio-Temporal Deep Neural Networks

With climate change expected to exacerbate fire weather conditions, the accurate anticipation of wildfires on a global scale becomes increasingly crucial for disaster mitigation. In this study, we utilize SeasFire, a comprehensive global wildfire dataset with climate, vegetation, oceanic indices, and human-related variables, to enable seasonal wildfire forecasting with machine learning. For the predictive analysis, we train deep learning models with different architectures that capture the spatio-temporal context leading to wildfires. Our investigation focuses on assessing the effectiveness of these models in predicting the presence of burned areas at varying forecasting time horizons globally, extending up to six months into the future, and on how different spatial or/and temporal context affects the performance of the models. Our findings demonstrate the great potential of deep learning models in seasonal fire forecasting; longer input time-series leads to more robust predictions across varying forecasting horizons, while integrating spatial information to capture wildfire spatio-temporal dynamics boosts performance. Finally, our results hint that in order to enhance performance at longer forecasting horizons, a larger receptive field spatially needs to be considered.

FoMo-Bench: a multi-modal, multi-scale and multi-task Forest Monitoring Benchmark for remote sensing foundation models

Forests are an essential part of Earth's ecosystems and natural systems, as well as providing services on which humanity depends, yet they are rapidly changing as a result of land use decisions and climate change. Understanding and mitigating negative effects requires parsing data on forests at global scale from a broad array of sensory modalities, and recently many such problems have been approached using machine learning algorithms for remote sensing. To date, forest-monitoring problems have largely been approached in isolation. Inspired by the rise of foundation models for computer vision and remote sensing, we here present the first unified Forest Monitoring Benchmark (FoMo-Bench). FoMo-Bench consists of 15 diverse datasets encompassing satellite, aerial, and inventory data, covering a variety of geographical regions, and including multispectral, red-green-blue, synthetic aperture radar (SAR) and LiDAR data with various temporal, spatial and spectral resolutions. FoMo-Bench includes multiple types of forest-monitoring tasks, spanning classification, segmentation, and object detection. To further enhance the diversity of tasks and geographies represented in FoMo-Bench, we introduce a novel global dataset, TalloS, combining satellite imagery with ground-based annotations for tree species classification, spanning 1,000+ hierarchical taxonomic levels (species, genus, family). Finally, we propose FoMo-Net, a foundation model baseline designed for forest monitoring with the flexibility to process any combination of commonly used sensors in remote sensing. This work aims to inspire research collaborations between machine learning and forest biology researchers in exploring scalable multi-modal and multi-task models for forest monitoring. All code and data will be made publicly available.

Kuro Siwo: 12.1 billion $m^2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping

Global floods, exacerbated by climate change, pose severe threats to human life, infrastructure, and the environment. This urgency is highlighted by recent catastrophic events in Pakistan and New Zealand, underlining the critical need for precise flood mapping for guiding restoration efforts, understanding vulnerabilities, and preparing for future events. While Synthetic Aperture Radar (SAR) offers day-and-night, all-weather imaging capabilities, harnessing it for deep learning is hindered by the absence of a large annotated dataset. To bridge this gap, we introduce Kuro Siwo, a meticulously curated multi-temporal dataset, spanning 32 flood events globally. Our dataset maps more than 63 billion m2 of land, with 12.1 billion of them being either a flooded area or a permanent water body. Kuro Siwo stands out for its unparalleled annotation quality to facilitate rapid flood mapping in a supervised setting. We also augment learning by including a large unlabeled set of SAR samples, aimed at self-supervised pretraining. We provide an extensive benchmark and strong baselines for a diverse set of flood events from Europe, America, Africa and Australia. Our benchmark demonstrates the quality of Kuro Siwo annotations, training models that can achieve $\approx$ 85% and $\approx$ 87% in F1-score for flooded areas and general water detection respectively. This work calls on the deep learning community to develop solution-driven algorithms for rapid flood mapping, with the potential to aid civil protection and humanitarian agencies amid climate change challenges. Our code and data will be made available at https://github.com/Orion-AI-Lab/KuroSiwo

TeleViT: Teleconnection-driven Transformers Improve Subseasonal to Seasonal Wildfire Forecasting

Wildfires are increasingly exacerbated as a result of climate change, necessitating advanced proactive measures for effective mitigation. It is important to forecast wildfires weeks and months in advance to plan forest fuel management, resource procurement and allocation. To achieve such accurate long-term forecasts at a global scale, it is crucial to employ models that account for the Earth system's inherent spatio-temporal interactions, such as memory effects and teleconnections. We propose a teleconnection-driven vision transformer (TeleViT), capable of treating the Earth as one interconnected system, integrating fine-grained local-scale inputs with global-scale inputs, such as climate indices and coarse-grained global variables. Through comprehensive experimentation, we demonstrate the superiority of TeleViT in accurately predicting global burned area patterns for various forecasting windows, up to four months in advance. The gain is especially pronounced in larger forecasting windows, demonstrating the improved ability of deep learning models that exploit teleconnections to capture Earth system dynamics. Code available at https://github.com/Orion-Ai-Lab/TeleViT.

Hephaestus: A large scale multitask dataset towards InSAR understanding

Synthetic Aperture Radar (SAR) data and Interferometric SAR (InSAR) products in particular, are one of the largest sources of Earth Observation data. InSAR provides unique information on diverse geophysical processes and geology, and on the geotechnical properties of man-made structures. However, there are only a limited number of applications that exploit the abundance of InSAR data and deep learning methods to extract such knowledge. The main barrier has been the lack of a large curated and annotated InSAR dataset, which would be costly to create and would require an interdisciplinary team of experts experienced on InSAR data interpretation. In this work, we put the effort to create and make available the first of its kind, manually annotated dataset that consists of 19,919 individual Sentinel-1 interferograms acquired over 44 different volcanoes globally, which are split into 216,106 InSAR patches. The annotated dataset is designed to address different computer vision problems, including volcano state classification, semantic segmentation of ground deformation, detection and classification of atmospheric signals in InSAR imagery, interferogram captioning, text to InSAR generation, and InSAR image quality assessment.

Self-supervised Contrastive Learning for Volcanic Unrest Detection

Ground deformation measured from Interferometric Synthetic Aperture Radar (InSAR) data is considered a sign of volcanic unrest, statistically linked to a volcanic eruption. Recent studies have shown the potential of using Sentinel-1 InSAR data and supervised deep learning (DL) methods for the detection of volcanic deformation signals, towards global volcanic hazard mitigation. However, detection accuracy is compromised from the lack of labelled data and class imbalance. To overcome this, synthetic data are typically used for finetuning DL models pre-trained on the ImageNet dataset. This approach suffers from poor generalisation on real InSAR data. This letter proposes the use of self-supervised contrastive learning to learn quality visual representations hidden in unlabeled InSAR data. Our approach, based on the SimCLR framework, provides a solution that does not require a specialized architecture nor a large labelled or synthetic dataset. We show that our self-supervised pipeline achieves higher accuracy with respect to the state-of-the-art methods, and shows excellent generalisation even for out-of-distribution test data. Finally, we showcase the effectiveness of our approach for detecting the unrest episodes preceding the recent Icelandic Fagradalsfjall volcanic eruption.

Learning class prototypes from Synthetic InSAR with Vision Transformers

The detection of early signs of volcanic unrest preceding an eruption, in the form of ground deformation in Interferometric Synthetic Aperture Radar (InSAR) data is critical for assessing volcanic hazard. In this work we treat this as a binary classification problem of InSAR images, and propose a novel deep learning methodology that exploits a rich source of synthetically generated interferograms to train quality classifiers that perform equally well in real interferograms. The imbalanced nature of the problem, with orders of magnitude fewer positive samples, coupled with the lack of a curated database with labeled InSAR data, sets a challenging task for conventional deep learning architectures. We propose a new framework for domain adaptation, in which we learn class prototypes from synthetic data with vision transformers. We report detection accuracy that surpasses the state of the art on volcanic unrest detection. Moreover, we built upon this knowledge by learning a new, non-linear, projection between the learnt representations and prototype space, using pseudo labels produced by our model from an unlabeled real InSAR dataset. This leads to the new state of the art with $97.1%$ accuracy on our test set. We demonstrate the robustness of our approach by training a simple ResNet-18 Convolutional Neural Network on the unlabeled real InSAR dataset with pseudo-labels generated from our top transformer-prototype model. Our methodology provides a significant improvement in performance without the need of manually labeling any sample, opening the road for further exploitation of synthetic InSAR data in various remote sensing applications.