Nicolas Longépé

Vít Růžička, Gonzalo Mateo-García, Chris Bridges et al.

Artificial intelligence onboard satellites has the potential to reduce data transmission requirements, enable real-time decision-making and collaboration within constellations. This study deploys a lightweight foundational model called RaVAEn on D-Orbit's ION SCV004 satellite. RaVAEn is a variational auto-encoder (VAE) that generates compressed latent vectors from small image tiles, enabling several downstream tasks. In this work we demonstrate the reliable use of RaVAEn onboard a satellite, achieving an encoding time of 0.110s for tiles of a 4.8x4.8 km$^2$ area. In addition, we showcase fast few-shot training onboard a satellite using the latent representation of data. We compare the deployment of the model on the on-board CPU and on the available Myriad vision processing unit (VPU) accelerator. To our knowledge, this work shows for the first time the deployment of a multi-task model on-board a CubeSat and the on-board training of a machine learning model.

Lukasz Tulczyjew, Michal Kawulok, Nicolas Longépé et al.

Hyperspectral unmixing remains one of the most challenging tasks in the analysis of such data. Deep learning has been blooming in the field and proved to outperform other classic unmixing techniques, and can be effectively deployed onboard Earth observation satellites equipped with hyperspectral imagers. In this letter, we follow this research pathway and propose a multi-branch convolutional neural network that benefits from fusing spectral, spatial, and spectral-spatial features in the unmixing process. The results of our experiments, backed up with the ablation study, revealed that our techniques outperform others from the literature and lead to higher-quality fractional abundance estimation. Also, we investigated the influence of reducing the training sets on the capabilities of all algorithms and their robustness against noise, as capturing large and representative ground-truth sets is time-consuming and costly in practice, especially in emerging Earth observation scenarios.

Lukasz Tulczyjew, Michal Kawulok, Nicolas Longépé et al.

Maintaining farm sustainability through optimizing the agricultural management practices helps build more planet-friendly environment. The emerging satellite missions can acquire multi- and hyperspectral imagery which captures more detailed spectral information concerning the scanned area, hence allows us to benefit from subtle spectral features during the analysis process in agricultural applications. We introduce an approach for extracting 2.5 m cultivated land maps from 10 m Sentinel-2 multispectral image series which benefits from a compact graph convolutional neural network. The experiments indicate that our models not only outperform classical and deep machine learning techniques through delivering higher-quality segmentation maps, but also dramatically reduce the memory footprint when compared to U-Nets (almost 8k trainable parameters of our models, with up to 31M parameters of U-Nets). Such memory frugality is pivotal in the missions which allow us to uplink a model to the AI-powered satellite once it is in orbit, as sending large nets is impossible due to the time constraints.

Bartosz Grabowski, Maciej Ziaja, Michal Kawulok et al.

Cloud detection is a pivotal satellite image pre-processing step that can be performed both on the ground and on board a satellite to tag useful images. In the latter case, it can reduce the amount of data to downlink by pruning the cloudy areas, or to make a satellite more autonomous through data-driven acquisition re-scheduling. We approach this task with nnU-Nets, a self-reconfigurable framework able to perform meta-learning of a segmentation network over various datasets. Unfortunately, such models are commonly memory-inefficient due to their (very) large architectures. To benefit from them in on-board processing, we compress nnU-Nets with knowledge distillation into much smaller and compact U-Nets. Our experiments, performed over Sentinel-2 and Landsat-8 images revealed that nnU-Nets deliver state-of-the-art performance without any manual design. Our approach was ranked within the top 7% best solutions (across 847 teams) in the On Cloud N: Cloud Cover Detection Challenge, where we reached the Jaccard index of 0.882 over more than 10k unseen Sentinel-2 images (the winners obtained 0.897, the baseline U-Net with the ResNet-34 backbone: 0.817, and the classic Sentinel-2 image thresholding: 0.652). Finally, we showed that knowledge distillation enables to elaborate dramatically smaller (almost 280x) U-Nets when compared to nnU-Nets while still maintaining their segmentation capabilities.

Bartosz Grabowski, Maciej Ziaja, Michal Kawulok et al.

Cloud detection is a pivotal satellite image pre-processing step that can be performed both on the ground and on board a satellite to tag useful images. In the latter case, it can help to reduce the amount of data to downlink by pruning the cloudy areas, or to make a satellite more autonomous through data-driven acquisition re-scheduling of the cloudy areas. We approach this important task with nnU-Nets, a self-reconfigurable framework able to perform meta-learning of a segmentation network over various datasets. Our experiments, performed over Sentinel-2 and Landsat-8 multispectral images revealed that nnU-Nets deliver state-of-the-art cloud segmentation performance without any manual design. Our approach was ranked within the top 7% best solutions (across 847 participating teams) in the On Cloud N: Cloud Cover Detection Challenge, where we reached the Jaccard index of 0.882 over more than 10k unseen Sentinel-2 image patches (the winners obtained 0.897, whereas the baseline U-Net with the ResNet-34 backbone used as an encoder: 0.817, and the classic Sentinel-2 image thresholding: 0.652).

Brandon Victor, Mathilde Letard, Peter Naylor et al.

Floods are among the most common and devastating natural hazards, imposing immense costs on our society and economy due to their disastrous consequences. Recent progress in weather prediction and spaceborne flood mapping demonstrated the feasibility of anticipating extreme events and reliably detecting their catastrophic effects afterwards. However, these efforts are rarely linked to one another and there is a critical lack of datasets and benchmarks to enable the direct forecasting of flood extent. To resolve this issue, we curate a novel dataset enabling a timely prediction of flood extent. Furthermore, we provide a representative evaluation of state-of-the-art methods, structured into two benchmark tracks for forecasting flood inundation maps i) in general and ii) focused on coastal regions. Altogether, our dataset and benchmark provide a comprehensive platform for evaluating flood forecasts, enabling future solutions for this critical challenge. Data, code & models are shared at https://github.com/Multihuntr/GFF under a CC0 license.

Aurélien Colin, Pierre Tandeo, Charles Peureux et al.

Remote sensing of rainfall events is critical for both operational and scientific needs, including for example weather forecasting, extreme flood mitigation, water cycle monitoring, etc. Ground-based weather radars, such as NOAA's Next-Generation Radar (NEXRAD), provide reflectivity and precipitation estimates of rainfall events. However, their observation range is limited to a few hundred kilometers, prompting the exploration of other remote sensing methods, particularly over the open ocean, that represents large areas not covered by land-based radars. Here we propose a deep learning approach to deliver a three-class segmentation of SAR observations in terms of rainfall regimes. SAR satellites deliver very high resolution observations with a global coverage. This seems particularly appealing to inform fine-scale rain-related patterns, such as those associated with convective cells with characteristic scales of a few kilometers. We demonstrate that a convolutional neural network trained on a collocated Sentinel-1/NEXRAD dataset clearly outperforms state-of-the-art filtering schemes such as the Koch's filters. Our results indicate high performance in segmenting precipitation regimes, delineated by thresholds at 24.7, 31.5, and 38.8 dBZ. Compared to current methods that rely on Koch's filters to draw binary rainfall maps, these multi-threshold learning-based models can provide rainfall estimation. They may be of interest in improving high-resolution SAR-derived wind fields, which are degraded by rainfall, and provide an additional tool for the study of rain cells.

Àlex R. Atrio, Antonio Lopez, Jino Rohit et al.

We introduce Earth Virtual Expert (EVE), the first open-source, end-to-end initiative for developing and deploying domain-specialized LLMs for Earth Intelligence. At its core is EVE-Instruct, a domain-adapted 24B model built on Mistral Small 3.2 and optimized for reasoning and question answering. On newly constructed Earth Observation and Earth Sciences benchmarks, it outperforms comparable models while preserving general capabilities. We release curated training corpora and the first systematic domain-specific evaluation benchmarks, covering MCQA, open-ended QA, and factuality. EVE further integrates RAG and a hallucination-detection pipeline into a production system deployed via API and GUI, supporting 350 pilot users so far. All models, datasets, and code are ready to be released under open licenses as contributions to our field at huggingface.co/eve-esa and github.com/eve-esa.

Theodor Forgaard, Jarle H. Reksten, Anders U. Waldeland et al.

Current Earth observation foundation models are architecturally rigid, struggle with heterogeneous sensors and are constrained to fixed patch sizes. This limits their deployment in real-world scenarios requiring flexible computeaccuracy trade-offs. We propose THOR, a "computeadaptive" foundation model that solves both input heterogeneity and deployment rigidity. THOR is the first architecture to unify data from Copernicus Sentinel-1, -2, and -3 (OLCI & SLSTR) satellites, processing their native 10 m to 1000 m resolutions in a single model. We pre-train THOR with a novel randomized patch and input image size strategy. This allows a single set of pre-trained weights to be deployed at inference with any patch size, enabling a dynamic trade-off between computational cost and feature resolution without retraining. We pre-train THOR on THOR Pretrain, a new, large-scale multi-sensor dataset and demonstrate state-of-the-art performance on downstream benchmarks, particularly in data-limited regimes like the PANGAEA 10% split, validating that THOR's flexible feature generation excels for diverse climate and society applications.

Johannes Jakubik, Felix Yang, Benedikt Blumenstiel et al.

We present TerraMind, the first any-to-any generative, multimodal foundation model for Earth observation (EO). Unlike other multimodal models, TerraMind is pretrained on dual-scale representations combining both token-level and pixel-level data across modalities. On a token level, TerraMind encodes high-level contextual information to learn cross-modal relationships, while on a pixel level, TerraMind leverages fine-grained representations to capture critical spatial nuances. We pretrained TerraMind on nine geospatial modalities of a global, large-scale dataset. In this paper, we demonstrate that (i) TerraMind's dual-scale early fusion approach unlocks a range of zero-shot and few-shot applications for Earth observation, (ii) TerraMind introduces "Thinking-in-Modalities" (TiM) -- the capability of generating additional artificial data during finetuning and inference to improve the model output -- and (iii) TerraMind achieves beyond state-of-the-art performance in community-standard benchmarks for EO like PANGAEA. The pretraining dataset, the model weights, and our code are open-sourced under a permissive license.

Jonas Weiss, Patricia Sagmeister, Gabriel Maiolini Capez et al.

Dramatic cost reductions driven by private sector innovations have led to a rapid increase in the number of satellites in orbit and a corresponding surge in space-generated data. As this trend continues, transmitting large volumes of data to Earth for processing may become increasingly costly and challenging due to potential space-to-Earth link congestion and increased latency. Moreover, traditional ground station networks may face difficulties accommodating growing data flows and workloads because of capacity constraints, complex scheduling logistics, and restricted visibility windows, which can limit scalability. Space Data Centers (SDCs) -- software-driven, multi-tenant artificial intelligence-based service platforms capable of processing data in orbit to generate actionable insights for client satellites and ground users -- represent a promising approach to address these challenges. This article presents the architecture of a Low Earth Orbit SDC satellite constellation, considering orbital design, inter-satellite links and network topology, computational resource organization, and software service orchestration. We analyze the potential technical feasibility and economic viability of SDCs using forecasting models informed by technology roadmaps and illustrate the concept through Earth observation and lunar exploration use cases.

Benedikt Blumenstiel, Paolo Fraccaro, Valerio Marsocci et al.

Large-scale foundation models in Earth Observation can learn versatile, label-efficient representations by leveraging massive amounts of unlabeled data. However, existing public datasets are often limited in scale, geographic coverage, or sensor variety. We introduce TerraMesh, a new globally diverse, multimodal dataset combining optical, synthetic aperture radar, elevation, and land-cover modalities in an Analysis-Ready Data format. TerraMesh includes over 9~million samples with eight spatiotemporal aligned modalities, enabling large-scale pre-training. We provide detailed data processing steps, comprehensive statistics, and empirical evidence demonstrating improved model performance when pre-trained on TerraMesh. The dataset is hosted at https://huggingface.co/datasets/ibm-esa-geospatial/TerraMesh.

Vladimir Zaigrajew, Hubert Baniecki, Lukasz Tulczyjew et al.

Remote sensing (RS) applications in the space domain demand machine learning (ML) models that are reliable, robust, and quality-assured, making red teaming a vital approach for identifying and exposing potential flaws and biases. Since both fields advance independently, there is a notable gap in integrating red teaming strategies into RS. This paper introduces a methodology for examining ML models operating on hyperspectral images within the HYPERVIEW challenge, focusing on soil parameters' estimation. We use post-hoc explanation methods from the Explainable AI (XAI) domain to critically assess the best performing model that won the HYPERVIEW challenge and served as an inspiration for the model deployed on board the INTUITION-1 hyperspectral mission. Our approach effectively red teams the model by pinpointing and validating key shortcomings, constructing a model that achieves comparable performance using just 1% of the input features and a mere up to 5% performance loss. Additionally, we propose a novel way of visualizing explanations that integrate domain-specific information about hyperspectral bands (wavelengths) and data transformations to better suit interpreting models for hyperspectral image analysis.

Roberto Del Prete, Manuel Salvoldi, Domenico Barretta et al.

Satellite-based onboard data processing is crucial for time-sensitive applications requiring timely and efficient rapid response. Advances in edge artificial intelligence are shifting computational power from ground-based centers to on-orbit platforms, transforming the "sensing-communication-decision-feedback" cycle and reducing latency from acquisition to delivery. The current research presents a framework addressing the strict bandwidth, energy, and latency constraints of small satellites, focusing on maritime monitoring. The study contributes three main innovations. Firstly, it investigates the application of deep learning techniques for direct ship detection and classification from raw satellite imagery. By simplifying the onboard processing chain, our approach facilitates direct analyses without requiring computationally intensive steps such as calibration and ortho-rectification. Secondly, to address the scarcity of raw satellite data, we introduce two novel datasets, VDS2Raw and VDV2Raw, which are derived from raw data from Sentinel-2 and Vegetation and Environment Monitoring New Micro Satellite (VENuS) missions, respectively, and enriched with Automatic Identification System (AIS) records. Thirdly, we characterize the tasks' optimal single and multiple spectral band combinations through statistical and feature-based analyses validated on both datasets. In sum, we demonstrate the feasibility of the proposed method through a proof-of-concept on CubeSat-like hardware, confirming the models' potential for operational satellite-based maritime monitoring.

Maciej Ziaja, Pawel Kowaleczko, Daniel Kostrzewa et al.

Super-resolution is aimed at reconstructing high-resolution images from low-resolution observations. State-of-the-art approaches underpinned with deep learning allow for obtaining outstanding results, generating images of high perceptual quality. However, it often remains unclear whether the reconstructed details are close to the actual ground-truth information and whether they constitute a more valuable source for image analysis algorithms. In the reported work, we address the latter problem, and we present our efforts toward learning super-resolution algorithms in a task-driven way to make them suitable for generating high-resolution images that can be exploited for automated image analysis. In the reported initial research, we propose a methodological approach for assessing the existing models that perform computer vision tasks in terms of whether they can be used for evaluating super-resolution reconstruction algorithms, as well as training them in a task-driven way. We support our analysis with experimental study and we expect it to establish a solid foundation for selecting appropriate computer vision tasks that will advance the capabilities of real-world super-resolution.

Nikolaos Dionelis, Alessandra Feliciotti, Mattia Marconcini et al.

Estimating the construction year of buildings is critical for advancing sustainability, as older structures often lack energy-efficient features. Sustainable urban planning relies on accurate building age data to reduce energy consumption and mitigate climate change. In this work, we introduce MapYourCity, a novel multi-modal benchmark dataset comprising top-view Very High Resolution (VHR) imagery, multi-spectral Earth Observation (EO) data from the Copernicus Sentinel-2 satellite constellation, and co-localized street-view images across various European cities. Each building is labeled with its construction epoch, and the task is formulated as a seven-class classification problem covering periods from 1900 to the present. To advance research in EO generalization and multi-modal learning, we organized a community-driven data challenge in 2024, hosted by ESA $Φ$-lab, which ran for four months and attracted wide participation. This paper presents the Top-4 performing models from the challenge and their evaluation results. We assess model generalization on cities excluded from training to prevent data leakage, and evaluate performance under missing modality scenarios, particularly when street-view data is unavailable. Results demonstrate that building age estimation is both feasible and effective, even in previously unseen cities and when relying solely on top-view satellite imagery (i.e. with VHR and Sentinel-2 images). The MapYourCity dataset thus provides a valuable resource for developing scalable, real-world solutions in sustainable urban analytics.

Ziyang Zhang, Plamen Angelov, Dmitry Kangin et al.

In this paper, we address two critical challenges in the domain of flood detection: the computational expense of large-scale time series change detection and the lack of interpretable decision-making processes on explainable AI (XAI). To overcome these challenges, we proposed an interpretable multi-stage approach to flood detection, IMAFD has been proposed. It provides an automatic, efficient and interpretable solution suitable for large-scale remote sensing tasks and offers insight into the decision-making process. The proposed IMAFD approach combines the analysis of the dynamic time series image sequences to identify images with possible flooding with the static, within-image semantic segmentation. It combines anomaly detection (at both image and pixel level) with semantic segmentation. The flood detection problem is addressed through four stages: (1) at a sequence level: identifying the suspected images (2) at a multi-image level: detecting change within suspected images (3) at an image level: semantic segmentation of images into Land, Water or Cloud class (4) decision making. Our contributions are two folder. First, we efficiently reduced the number of frames to be processed for dense change detection by providing a multi-stage holistic approach to flood detection. Second, the proposed semantic change detection method (stage 3) provides human users with an interpretable decision-making process, while most of the explainable AI (XAI) methods provide post hoc explanations. The evaluation of the proposed IMAFD framework was performed on three datasets, WorldFloods, RavAEn and MediaEval. For all the above datasets, the proposed framework demonstrates a competitive performance compared to other methods offering also interpretability and insight.

Nikolaos Dionelis, Riccardo Musto, Jente Bosmans et al.

Today, Earth Observation (EO) satellites generate massive volumes of data. To fully exploit this, it is essential to pretrain EO Foundation Models (FMs) on large unlabeled datasets, enabling efficient fine-tuning for downstream tasks with minimal labeled data. In this paper, we study scaling-up FMs: we train our models on the pretraining dataset MajorTOM 23TB which includes all regions, and the performance on average is competitive versus models pretrained on more specialized datasets which are substantially smaller and include only land. The additional data of oceans and ice do not decrease the performance on land-focused downstream tasks. These results indicate that large FMs trained on global datasets for a wider variety of downstream tasks can be useful for downstream applications that only require a subset of the information included in their training. The second contribution is the exploration of U-Net Convolutional Neural Network (CNN), Vision Transformers (ViT), and Mamba State-Space Models (SSM) as FMs. U-Net captures local correlations amongst pixels, while ViT and Mamba capture local and distant correlations. We develop various models using different architectures, including U-Net, ViT, and Mamba, and different number of parameters. We evaluate the FLoating-point OPerations (FLOPs) needed by the models. We fine-tune on the PhilEO Bench for different downstream tasks: roads, buildings, and land cover. For most n-shots for roads and buildings, U-Net 200M-2T outperforms the other models. Using Mamba, we achieve comparable results on the downstream tasks, with less computational expenses. We also compare with the recent FM TerraMind which we evaluate on PhilEO Bench.

Nikolaos Dionelis, Jente Bosmans, Nicolas Longépé

Performing accurate confidence quantification and assessment in pixel-wise regression tasks, which are downstream applications of AI Foundation Models for Earth Observation (EO), is important for deep neural networks to predict their failures, improve their performance and enhance their capabilities in real-world applications, for their practical deployment. For pixel-wise regression tasks, specifically utilizing remote sensing data from satellite imagery in EO Foundation Models, confidence quantification is a critical challenge. The focus of this research work is on developing a Foundation Model using EO satellite data that computes and assigns a confidence metric alongside regression outputs to improve the reliability and interpretability of predictions generated by deep neural networks. To this end, we develop, train and evaluate the proposed Confidence-Aware Regression Estimation (CARE) Foundation Model. Our model CARE computes and assigns confidence to regression results as downstream tasks of a Foundation Model for EO data, and performs a confidence-aware self-corrective learning method for the low-confidence regions. We evaluate the model CARE, and experimental results on multi-spectral data from the Copernicus Sentinel-2 satellite constellation to estimate the building density (i.e. monitoring urban growth), show that the proposed method can be successfully applied to important regression problems in EO and remote sensing. We also show that our model CARE outperforms other baseline methods.

Gabriele Meoni, Roberto Del Prete, Federico Serva et al.

Nowadays, there is growing interest in applying Artificial Intelligence (AI) on board Earth Observation (EO) satellites for time-critical applications, such as natural disaster response. However, the unavailability of raw satellite data currently hinders research on lightweight pre-processing techniques and limits the exploration of end-to-end pipelines, which could offer more efficient and accurate extraction of insights directly from the source data. To fill this gap, this work presents a novel methodology to automate the creation of datasets for the detection of target events (e.g., warm thermal hotspots) or objects (e.g., vessels) from Sentinel-2 raw data and other multispectral EO pushbroom raw imagery. The presented approach first processes the raw data by applying a pipeline consisting of spatial band registration and georeferencing of the raw data pixels. Then, it detects the target events by leveraging event-specific state-of-the-art algorithms on the Level-1C products, which are mosaicked and cropped on the georeferenced correspondent raw granule area. The detected events are finally re-projected back onto the corresponding raw images. We apply the proposed methodology to realize THRawS (Thermal Hotspots in Raw Sentinel-2 data), the first dataset of Sentinel-2 raw data containing warm thermal hotspots. THRawS includes 1090 samples containing wildfires, volcanic eruptions, and 33,335 event-free acquisitions to enable thermal hotspot detection and general classification applications. This dataset and associated toolkits provide the community with both an immediately useful resource as well as a framework and methodology acting as a template for future additions. With this work, we hope to pave the way for research on energy-efficient pre-processing algorithms and AI-based end-to-end processing systems on board EO satellites.