Forests are vital to ecosystems, supporting biodiversity and essential services, but are rapidly changing due to land use and climate change. Understanding and mitigating negative effects requires parsing data on forests at global scale from a broad array of sensory modalities, and using them in diverse forest monitoring applications. Such diversity in data and applications can be effectively addressed through the development of a large, pre-trained foundation model that serves as a versatile base for various downstream tasks. However, remote sensing modalities, which are an excellent fit for several forest management tasks, are particularly challenging considering the variation in environmental conditions, object scales, image acquisition modes and spatio-temporal resolutions, etc. With that in mind, we present the first unified Forest Monitoring Benchmark (FoMo-Bench), carefully constructed to evaluate foundation models with such flexibility. 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 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 enhance task and geographic diversity in FoMo-Bench, we introduce TalloS, a global dataset combining satellite imagery with ground-based annotations for tree species classification across 1,000+ categories and hierarchical taxonomic levels. Finally, we propose FoMo-Net, a pre-training framework to develop foundation models with the capacity to process any combination of commonly used modalities and spectral bands 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 and beyond. All code, data and appendices are published in the repository and on ArXiv.

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.

Global flash floods, exacerbated by climate change, pose severe threats to humanlife, infrastructure, and the environment. Recent catastrophic events in Pakistan andNew Zealand underscore the urgent need for precise flood mapping to guide restoration efforts, understand vulnerabilities, and prepare for future occurrences. While Synthetic Aperture Radar (SAR) remote sensing offers day-and-night, all-weatherimaging capabilities, its application in deep learning for flood segmentation is limited by the lack of large annotated datasets. To address this, we introduce KuroSiwo, a manually annotated multi-temporal dataset, spanning 43 flood events globally. Our dataset maps more than 338 billion $m^2$ of land, with 33 billion designatedas either flooded areas or permanent water bodies. Kuro Siwo includes a highlyprocessed product optimized for flash flood mapping based on SAR Ground RangeDetected, and a primal SAR Single Look Complex product with minimal preprocessing, designed to promote research on the exploitation of both the phase and amplitude information and to offer maximum flexibility for downstream task preprocessing. To leverage advances in large scale self-supervised pretraining methodsfor remote sensing data, we augment Kuro Siwo with a large unlabeled set of SARsamples. Finally, we provide an extensive benchmark, namely BlackBench, offering strong baselines for a diverse set of flood events globally. All data and code arepublished in our Github repository: https://github.com/Orion-AI-Lab/KuroSiwo.

We present a fire risk management system which takes input data from various sources (e.g., meteorological data, satellite indicators for vegetation, historical burned areas), produces a harmonized spatio-temporal data cube to compute fire risk and enables semantic querying to assist fire risk management. The distinguishing implementation features of the system is the use of data cubes, machine learning algorithms and, most importantly, geospatial ontology-based data access technologies. The system has been implemented in the European project DeepCube for the geographic area of Greece and can be used operationally to assist authorities to determine fire risk during the summer fire season.

We introduce Mesogeos, a large-scale multi-purpose dataset for wildfire modeling in the Mediterranean. Mesogeos integrates variables representing wildfire drivers (meteorology, vegetation, human activity) and historical records of wildfire ignitions and burned areas for 17 years (2006-2022). It is designed as a cloud-friendly spatio-temporal dataset, namely a datacube, harmonizing all variables in a grid of 1km x 1km x 1-day resolution. The datacube structure offers opportunities to assess machine learning (ML) usage in various wildfire modeling tasks. We extract two ML-ready datasets that establish distinct tracks to demonstrate this potential: (1) short-term wildfire danger forecasting and (2) final burned area estimation given the point of ignition. We define appropriate metrics and baselines to evaluate the performance of models in each track. By publishing the datacube, along with the code to create the ML datasets and models, we encourage the community to foster the implementation of additional tracks for mitigating the increasing threat of wildfires in the Mediterranean.

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, toward global volcanic hazard mitigation. However, detection accuracy is compromised from the lack of labeled data and class imbalance. To overcome this, synthetic data are typically used for fine-tuning DL models pretrained on the ImageNet dataset. This approach suffers from poor generalization 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 labeled 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 generalization 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.

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 amounts to the highest reported accuracy on a large test set for 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.

This work introduces a one of its kind labeled Earth Observation based benchmark dataset, Sen4AgriNet, for agricultural applications in Europe. The dataset is labeled using farmer declarations for the period 2016–2020, available as open data only very recently. The Sen4AgriNet contains 42.5 million parcels hence is significantly larger than the existing archives and is tailored to be used as a training source in the context of deep learning. It consists of two sub-datasets: Object Aggregated Dataset (OAD) and Patches Assembled Dataset (PAD). OAD dataset capitalizes zonal statistics of each parcel, thus creating a powerful label-to-features instance for classification algorithms. On the other hand, PAD structure generalizes the classification problem to parcel extraction and semantic segmentation and labeling. Key advantages from other similar datasets are the inclusion of all bands, multicountry and multi-year time span, and standardization of the crop type taxonomy across Europe. Finally, we showcase the potential of Sen4AgriNet through machine learning experiments. All data and code are accessible here: https://sen4agrinet.space.noa.gr/

TELEIOS is a recent European project that addresses the need for scalable access to petabytes of Earth Observation data and the discovery and exploitation of knowledge that is hidden in them. TELEIOS builds on scientific database technologies (array databases, SciQL, data vaults) and Semantic Web technologies (stRDF and stSPARQL) implemented on top of a state of the art column store database system (MonetDB). We demonstrate a first prototype of the TELEIOS Virtual Earth Observatory (VEO) architecture, using a forest fire monitoring application as example.

The Permanent Scatterers (PS) technique, invented by Politechnico di Milano research team, is an approach that minimises the undesirable noise components in the classic InSAR technique, such as spatial and temporal decorrelations, signal delay due to tropospheric and ionospheric disturbances, orbital errors as well as topographical errors. This approach is suitable for the measurement of near vertical displacements of the order of ∼1 mm per year. It exploits almost all of the available SAR interferometric data over an area and requires availability of natural and/or artificial permanent scatterers. In this study we describe the implementation of the PS technique, called PerSePHONE (Permanent Scatterers Project Held by the Observatory, National, of Hellas). Its development has been based on a number of algorithmic adaptations, as well as new approaches in PS candidate selection. An example of this implementation is shown for the case of the Corinth Rift area (Hellas).