A Composition-Aware Pretraining Framework for Geospatial Foundation Models

Geospatial foundation models have emerged as state-of-the-art methods for downstream Earth observation tasks. However, existing pretraining methodologies process imagery through a single-concept lens, failing to capture the highly compositional nature of complex satellite scenes. We propose a composition-aware pretraining framework that explicitly encodes fractional land-cover mixtures. Each satellite image cell is mapped to a histogram representing its fractional land-cover distribution, which we term the "composition target". These targets serve as the primary prediction objective and are distilled into the backbone using Earth Mover's Distance. Experimental evaluation shows that composition-aware pretraining yields substantial gains on region-level understanding tasks requiring semantic similarity judgment, including zero-shot image retrieval and scene classification, while remaining competitive on tasks requiring fine-grained spatial precision, such as segmentation and object detection. With a 36.8M-parameter backbone, our framework outperforms SatMAE and Prithvi-EO-2.0, which contain 303M and 600M parameters, respectively, in most retrieval and scene classification settings. On the fine-grained ForestNet-12 dataset, a rigorous testbed for compositional discrimination, our method boosts baseline mAP@10 from 0.279 to 0.434, a 55.6% relative improvement, providing direct evidence for the effectiveness of explicit composition modeling. The code implementation can be found at https://github.com/05kashyap/GFM_Composition_Pretraining

A comprehensive and trustworthy benchmark of AI methods for change detection in Earth observation

Change detection in Earth observation (EO) is critical for monitoring land surface transformations, yet recent research in the field is constrained by inconsistent evaluation protocols and a narrow focus on predictive accuracy without regard for computational efficiency. To address this, we present a standardized, open-source benchmark for evaluating state-of-the-art (SOTA) deep learning methods for Earth observation change detection. We conduct a comprehensive analysis of ten representative model architectures, ranging from convolutional networks (CNNs) to vision transformers (ViTs), across ten heterogeneous change detection datasets. We rigorously evaluate these models with identical experimental protocols, comparing models trained from scratch against those utilizing pre-trained weights. Furthermore, we evaluate predictive performance alongside computational efficiency, including parameter counts and inference latency. Our findings reveal that well-optimized classical architectures, such as Siamese U-Nets, frequently outperform more complex contemporary models when computational efficiency is factored in, and that pre-training consistently provides a significant performance boost with no additional inference cost. To ensure complete transparency and reproducibility, all experimental resources, including standardized data splits, training scripts, training logs, and model checkpoints are publicly available and adhere to FAIR principles (Findable, Accessible, Interoperable, and Reusable).

Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddings

Addressing critical global challenges, from food security and disaster risk to disease outbreaks and socio-economic vulnerability, demands high-fidelity geospatial modeling. However, building predictive planetary models remains bottlenecked by a fragmented data ecosystem, requiring manual data retrieval, multimodal data curation and fusion along with iterative model selection. We present the Planetary Prediction Engine (PPE), an autonomous AI system that executes this end-to-end workflow directly from natural-language queries. PPE synthesizes multimodal datasets on the fly, retrieving spatiotemporally relevant covariates across open-web and Earth observation platforms (Data Commons, Google Earth Engine) and fusing them with geospatial foundation model embeddings (PDFM, AlphaEarth). Simultaneously, it searches over task-tailored model architecture families with automated overfitting guards. Across diverse tasks, geographies, and scientific domains, PPE consistently outperforms state-of-the-art or manually tuned expert baselines. For US spatial regression, PPE improves mean $R^2$ across 21 CDC health indicators (76.8% vs. 60.0%), FEMA national risk indices (64.9% vs. 60.0%), and the Social Vulnerability Index (66.2% vs. 58.6%). For spatial downscaling in data-scarce settings, PPE integrates localized proxies to double baseline accuracy in Nigerian food security indicators ($R^2$ of 66.1% vs. 31.5%). For epidemiological nowcasting of the 2026 DRC Bundibugyo Ebola outbreak, PPE achieves a Recall@10 of 83.3% (identifying 15 of 18 newly invaded health zones across five weekly forecasts), a +10.3 percentage-point improvement over the public state-of-the-art modeling (~73%). By combining autonomous multimodal planetary data discovery with targeted model optimization, PPE lowers the technical barrier to planetary-scale analytics, enabling rapid, customized, expert-level deployment.

Earth Observation Foundation Models for Terrestrial Ecohydrology: From Representation Learning to Process Inference

Earth observation foundation models (EOFMs) are emerging as reusable representation frameworks for data-driven retrieval, prediction and process modelling within ecohydrology, which integrate EO, meteorological forcing and process models to characterise coupled water, energy and carbon dynamics in vegetation and soil across scales. However, there is yet to be an ecohydrology-specific synthesis assessing the EOFM relevance, application evidence or evaluation requirements under uncertain reference data, scale mismatch and temporal dependence. Here, we develop a framework for determining when EOFMs support interpretable inference and identify a mismatch between EOFMs and ecohydrological requirements. Firstly, an observation-to-inference hierarchy shows that relevance depends on target-specific sensing pathways, spatial-temporal support and traceable uncertainty. Secondly, a meta-analysis shows that pretraining is dominated by reflected optical and active-microwave data, with sparse thermal coverage and no passive-microwave-emission sources. Thirdly, our synthesis of ecohydrological applications finds strongest support for spatial context, label-efficient adaptation and hybrid workflows. Evidence declines with inference depth; independent validation of fluxes, coupled dynamics, event trajectories, calibrated uncertainty and decision benefits remains sparse. Fourthly, our benchmark audit finds stronger coverage of fair adaptation and reproducibility in general EOFM suites, and of process targets, direct reference evidence and distribution shifts in ecohydrological evaluations; physical consistency and uncertainty remain weakly assessed. These findings motivate a process-aware framework aligning EOFM design and evaluation with the target variable, observation pathway and process timescale, supporting trustworthy monitoring and interpretation of coupled water, energy and carbon dynamics.

Learning to Forecast Crop Growth from Earth Observation Data

Forecasting crop growth across agricultural landscapes is important for improving the productivity, resilience, and operational management of farming systems. In this work, we investigate whether Earth observation time series and meteorological drivers can be used to predict future canopy development at country scale. We focus on winter wheat and formulate crop growth prediction as forecasting future leaf area index (LAI) trajectories beyond the last available Sentinel-2 observation. We evaluate this task on a multi-year dataset which spans the entire country of Switzerland, containing over 20 million pixel-level Sentinel-2-derived LAI time series paired with meteorological variables. Because cloud cover and revisit gaps leave LAI supervision sparse, models fit the few valid (cloud-free) LAI observations yet oscillate implausibly between them, producing trajectories no real canopy could follow. We introduce a lightweight unimodal shape regulariser which improves trajectory plausibility with negligible loss in accuracy. We compare deep learning sequence-to-sequence (Seq2Seq) models with classic machine learning baselines and show that Seq2Seq models generalise well across years, achieving $\mathrm{R}^2$ above 0.8 and consistently outperforming conventional approaches. Together, these results demonstrate that remote sensing and weather-driven sequence modelling can learn crop growth dynamics at landscape scale. S

Earth observation embeddings are effective sub-grid descriptors for probabilistic weather downscaling

Global weather reanalyses and forecasts resolve the evolving atmospheric state on coarse grids, but site-specific applications require predictions at arbitrary locations where near-surface conditions also depend on unresolved terrain and land-surface properties. Existing probabilistic downscalers address this gap using hand-crafted topographic descriptors. We ask instead whether Earth observation foundation models can provide transferable sub-grid surface representations for probabilistic weather downscaling. We augment a convolutional conditional neural process that downscales coarse ERA5 reanalysis fields at ~25 km resolution with a learned local surface descriptor, obtained by compressing a patch of TESSERA embeddings at 10 m resolution. Although these embeddings summarise surface conditions over annual timescales, they improve downscaling of instantaneous 2 m temperature and 10 m wind speed by encoding persistent surface properties that capture a location's departure from the coarse-grid atmospheric state. Across five climatically diverse regions, the embedding improves point and probabilistic skill at stations held out in both space and time, overall improving CRPS skill by 11.5% for 2 m temperature and 6.2% for 10 m wind speed. We further analyse how its contribution differs by variable, finding that topography explains more of temperature's sub-grid structure, while TESSERA provides additional surface information for wind speed. These improvements persist when the coarse input is changed from ERA5 to forecasts from the Aurora AI forecasting model, and when predicting at newly deployed stations with no regional history. To our knowledge, this is the first evidence that long-timescale Earth-observation embeddings can support short-timescale weather downscaling where sub-grid departures are systematically structured by persistent surface properties.

Warping Earth Observations for better ice labeling in the Marginal Marginal Ice Zone

Multimodal satellite imagery provides complementary information for Earth Observation, but accurately combining heterogeneous sensors remains challenging in dynamic environments. Fast-changing regions, such as the Antarctic marginal ice zone, cannot fully exploit multimodal information from different satellite sensors because surface features move between image acquisitions. This spatial and temporal mismatch challenges effective perceptual grounding, violating the assumption of pixel-level correspondence that underpins most multimodal reasoning and downstream classification pipelines. Antarctic sea ice provides a challenging benchmark due to the rapid, heterogeneous drift of individual ice floes and the differing responses of sea ice to radar, visible and thermal sensing modalities. Accurate, dense supervision of sea ice remains scarce because generating pixel-wise labels requires time-consuming expert interpretation of noisy data, leading to historical reliance on coarse-resolution maritime ice charts for model training. This paper presents a novel architecture based on mutual information warping to align multi-satellite (Sentinel-1 and MODIS platforms) multimodal (visible, thermal, radar) satellite scenes. To demonstrate the approach, we introduce a sparse expert-labeled dataset of 2,088 pixel-wise annotations (7,046 expert point classifications) located at the ice-water margin interface across 43 scenes. Our results demonstrate that spatially grounding and aligning modalities prior to segmentation improves classification accuracy, and enables accurate, dense sea ice segmentation from sparse point-wise supervision.

Summarize First, Download Later: Onboard VLMs for Bandwidth-Efficient Earth Observation

Modern Earth observation (EO) satellites carry increasingly advanced sensors that produce vast volumes of high-resolution, multispectral data, yet downlink capacity remains a critical bottleneck -- often causing significant latency or the loss of valuable observations within limited contact windows. We propose a "Summarize First, Download Later" paradigm that exploits recent advances in onboard edge computing and Vision-Language Models (VLMs). Rather than indiscriminately downlinking raw imagery, the system follows a three-phase interaction protocol: the satellite first transmits concise natural language summaries generated by a quantized onboard VLM; ground operators then issue targeted Visual Question Answering (VQA) queries to verify scene relevance (e.g., wildfires or maritime anomalies); and full-resolution images are downloaded only when critical information is confirmed. This transforms the downlink from passive bulk transfer into an active, semantics-aware dialogue. We implement and evaluate the system on a resource-constrained NVIDIA Jetson platform, and experiments on diverse remote sensing scenes show that the proposed strategy substantially reduces bandwidth consumption while accelerating time-to-insight for time-sensitive missions.

Multi-Year Geospatial Reasoning using Interannually-Consistent Historical Predictions as a Free Input Modality

Machine learning, and deep networks in particular, are increasingly used to derive higher-level Earth observation (EO) products such as annual land-cover and crop-type maps. Many are generated operationally: each year a new acquisition is processed, typically with the same model, extending a multi-year archive. In the process these systems accumulate two kinds of useful signal that are almost never fed back into the model: the system's own archive of past predictions, and ancillary layers produced by other partners in a processing consortium. Both are normally used outside the network, as rule-based post-processing or a fixed input mask. Using the Copernicus Land Monitoring Service High Resolution Layer (HRL) Croplands crop-type product as a testbed, we show that bringing both signals inside the model turns a single-year, single-task pixel classifier into one that reasons across years. We introduce a Crop Type (CTY) embedding encoder that represents each past prediction as a confidence-scaled, time-ordered categorical token and attends over the year axis, and we study how the externally provided Base Vegetation Layer (BVL) mask should be represented in the model's inputs and outputs. To compare designs fairly when they relabel non-crop pixels, we evaluate on the 18 crop classes only and report precision and recall separately. On a pan-European dataset of about 5.4M labelled pixels, adding the prediction history raises crop-only F1 by 1.6 percentage points (pp) and, more importantly, corrects a recall-skewed error profile, with the largest gains on perennial and tree crops (olives +4.6, fruits +3.7, nuts +3.2 pp). Representing the BVL mask consistently in both the history and the target year adds about 2.5 pp on the crop classes. The approach is a low-cost recipe for any recurring geospatial or foundation model that emits class maps.

Volcanic Clouds Detection through QCNN and Geostationary Satellite Multispectral Imagery

Recent advances in quantum computing are opening new possibilities for Earth Observation (EO) data analysis. Quantum machine learning (QML) approaches offer novel ways to process information by exploiting quantum phenomena such as superposition and entanglement. These capabilities have motivated the exploration of whether quantum-enhanced models can address long-standing challenges in satellite remote sensing, where complex spectral and spatial signals often require sophisticated feature extraction. Among various fields of application, EO data allow the global monitoring of volcanic clouds and are crucial for aviation safety, hazard assessment, real-time eruption response, and evaluation of volcanic impacts on climate. Yet accurate detection of volcanic clouds remains difficult due to their similarity with meteorological clouds, the variability of eruption signatures, and the coarse spectral sampling of geostationary sensors. In this work, the potential of hybrid quantum convolutional neural networks (QCNNs) for the classification of satellite images containing volcanic clouds was investigated. These architectures integrate quantum computational layers into a classical convolutional framework. Two QCNN variants (with 2 and 4 qubits) have been considered to evaluate their ability to classify a dataset of SEVIRI images, including scenes with volcanic clouds (composed of ash, $SO_2$, or mixed components) as well as non-volcanic backgrounds. Finally, the performance of the hybrid QCNN models was compared with that of purely classical architectures.

Hybrid Quantum CNN for Cross-Sensor Spaceborne Volcanic Thermal Activity Recognition Worldwide

As Earth Observation (EO) enters the Big Data era, the exponential volume of daily satellite imagery poses significant computational and storage challenges for classical Deep Learning (DL) models. Moreover, current approaches often struggle to generalize across heterogeneous sensors and volcanic environments while requiring large labeled datasets and substantial computational resources. These limitations are particularly critical for emerging On-Board Processing (OBP) applications, where memory, computational power, and annotated data are inherently limited. This work proposes a Hybrid Quantum AlexNet architecture for cross-sensor recognition of volcanic thermal activity at the global scale. The proposed model combines a classical convolutional backbone for high-level spatial features extraction with a parameterized quantum circuit (PQC) acting as a variational layer. By embedding high-level image representations into a high-dimensional Hilbert space, the quantum layer learns task-specific representations that enhance feature discrimination. Experimental results demonstrate that the proposed hybrid quantum model learns more discriminative feature representations, leading to improved cross-sensor transferability and robustness across heterogeneous volcanic environments using fewer trainable parameters and reduced training data than its classical counterpart.

From Machine Learning to Large-Scale EO Products: Best Practices for Making Maps

Recent years have seen a rapid expansion in the production of large-scale geospatial maps derived from Earth observation (EO) data, driven largely by advances in machine learning (ML) and large computing infrastructure. Although the barrier to generating such maps has dropped substantially, established best practices have yet to emerge, and design decisions made early in the pipeline can quietly propagate errors into the final product. Producing a technically sound and scientifically credible product remains challenging. Choices made at every stage are tightly coupled: preprocessing decisions shape the training signal, dataset design governs what the model can learn and how reliably its performance can be assessed, and global-scale inference introduces engineering challenges in compute and data access at scale, as well as artifact mitigation. Furthermore, uncertainty quantification and independent map validation each require dedicated methodological attention that is often underestimated. This paper presents a concise, end-to-end account of the recommended practices spanning the pipeline from satellite data to an operational map product. We organize the discussion around six interconnected themes: the EO data infrastructure landscape, data selection and preprocessing, ML dataset construction and model training, uncertainty quantification, map production and distribution, and validation. This paper is a condensed version of a longer guide that provides greater depth across all stages, accessible online at ghjuliasialelli.github.io/MLEO-Maps/.

Embeddings based Anomaly Detection for Cleaning Global Crop Type Reference Datasets

High quality reference data remain a critical bottleneck for crop-type mapping at any spatial and temporal scale. Operational systems such as WorldCereal aggregate labels from heterogeneous sources such as parcel registers, national databases, field surveys, and map-derived products, each with their own biases, coverage gaps and unknown label noise. Simple global rules are inadequate, since crop phenology and observation conditions vary strongly across regions and seasons. In this study, we focus on a single, operationally relevant question: whether embeddings produced through geospatial foundation models are a viable basis for cleaning the reference data. We propose a practical, locality-aware, embedding-based anomaly (EBA) detection framework that operates on the embeddings of a pretrained Earth-observation encoder. We score each labelled sample against other samples of the same crop in the same area using a pretrained embedding, flag the ones that stand out, and test whether removing or down-weighting them before training yields a better model. We establish that the flagged points are genuinely mislabelled or misplaced in two independent ways: against synthetic ground truth, the detector concentrates injected label errors 2.5-5x above chance in its flagged set (detection AUROC up to 0.84); and on real data, a model-independent test shows that removing or confidence-weighting the flagged held-out points raises measured accuracy in trained models, for both crop type and land cover. Acting on the flags then improves the WorldCereal crop-type model across five macro-regions, evaluated on a fixed held-out split under three views. We find conservative cleaning helps while over-cleaning hurts. The EBA detector approach is designed to be reproducible and extensible, and can serve as a template for cleaning large, noisy Earth observation reference datasets beyond crop mapping.

Uncertainty Quantification for EO Regression Tasks: Building Height, Tree Canopy Height and Above-ground Biomass Estimation

Earth Observation regression tasks such as building height, canopy height, and above-ground biomass estimation underpin critical applications in urban planning, forest monitoring, and climate policy, where both accuracy and reliability are critical. Yet most deep learning models yield only deterministic predictions, providing no indication of per-pixel reliability. These regression tasks are inherently challenging due to heterogeneous land surfaces, skewed target distributions, sensor noise, and signal saturation at high target values, making uncertainty (UC) estimation essential for reliable inference. We address this gap by modeling aleatoric uncertainty using year-long Sentinel-1 SAR and Sentinel-2 MSI time series, proposing two complementary approaches: (i) Gaussian UC, which jointly predicts mean and standard deviation under a Gaussian assumption, and (ii) Quantile UC, which estimates the 10th, 50th, and 90th quantiles to capture asymmetric and heteroscedastic error distributions. Both models are evaluated on three representative EO regression tasks at 10 m spatial resolution. Results show that both approaches match or surpass deterministic benchmarks and existing global products, while delivering well-calibrated, interpretable, and operationally useful confidence estimates. Notably, both models outperform the current 10 m state-of-the-art uncertainty-aware model for canopy height estimation. Our implementation will be available at: https://github.com/RituYadav92/EO-Regression-Uncertainty-Estimation

Prior-matched evaluation of operational Earth-observation classifiers: a three-number reporting method demonstrated on Sentinel-1 internal-wave detection

The Internal Waves Service screens the Sentinel-1 Wave-mode archive for internal solitary waves, routing detections to experts whose adjudication time is the resource the effort exists to conserve. Because attention is the cost of error, precision leads. Its classifier was trained and reported at a one-to-one class balance, fixed before the operational rate could be known. That rate has since emerged at roughly one scene in twenty, and a balanced-test score badly overstates the precision a validator meets. A model that scores 0.794 balanced-test precision scores 0.192 in real operation: the gap is a systematic artefact of reporting at the wrong prior, invisible to the metric most work quotes. We show the mismatch to be an evaluation problem in the costume of a training one at a fixed recall, prior correction and calibration cannot move precision, and answer it with a prior-matched reporting method based on three figures: balanced-test, operational-prior, and real post-deployment, whose contrast is the honest measure. A precision-first, leakage-controlled development cycle then improves the classifier lever by lever, each promoted only against a pre-registered margin; added capacity not clearing it, calibration inert, feature aggregation the one real lift, so the honest negatives are as much a result as the gain. Holding recall at a floor of 0.80 and certifying against a sealed, single-read lockbox, the promoted model reports 0.927 precision at the operational prior; an out-of-time check confirms discrimination transfers to unseen periods while a fixed operating point does not. Prior-matched reporting, begin balanced, then move to the prior as the stream reveals it, transfers to any operational Earth-observation service bootstrapping a rare-event detector under a prior it has yet to discover.

EO-Agents: A Three-Agent LLM Pipeline for Earth Observation Hypothesis Generation

Large language models have recently been explored for scientific hypothesis generation, but most prior work relies on unstructured literature and free-form textual claims. We present a pipeline for Earth observation that grounds hypothesis generation directly in the NASA Earth Observation Knowledge Graph. A heterogeneous graph neural network trained on historical co-usage relations ranks candidate dataset pairings, and a three-agent LLM pipeline filters, generates, and evaluates structured research hypotheses. Applied to 1,475 NASA datasets, the system produces 160 hypotheses spanning multiple Earth-science domains, including ecohydrology, glaciology, aerosol--cloud interactions, vegetation phenology, and stratospheric chemistry. Model-predicted novel dataset pairings are rated nearly as plausible as held-out real co-usages from the literature, indicating that the pipeline surfaces scientifically coherent yet unexplored combinations. A 2*2*2 factorial experiment across GPT-5.2 and Claude Sonnet 4.6 shows that hypothesis rankings remain stable, while absolute scores depend strongly on judge identity, highlighting limitations of single-judge LLM evaluation.

Foundation-Model Earth Representations Enable Regional-Scale Forest Aboveground Biomass Monitoring Across the Northeastern United States

Forest aboveground biomass (AGB) is a critical indicator of ecosystem productivity and terrestrial carbon storage, yet regional carbon monitoring remains constrained by the sparse spatial and temporal availability of field inventories and airborne structural measurements. Recent Earth observation foundation models provide globally consistent geospatial representations derived from diverse multimodal datasets, offering a potential pathway toward scalable biomass monitoring. Here, we evaluate Google Satellite Embeddings (GSE), generated by the AplphaEarth Foundation Model, for regional-scale AGB estimation across diverse temperate forest ecosystems in the northeastern United States. We integrated annual GSE observations, airborne LiDAR, and continuous forest inventory measurements from the Northeastern Forest Inventory Network (NEFIN) within a machine-learning framework. Combined LiDAR-GSE models achieved an R^2 of 0.79 for AGB estimation. Capitalizing on annual GSE observations expanded the training dataset by more than tenfold through temporal growth adjustment, increasing predictive performance to R^2 = 0.82 while reducing model bias by over 70%. Spatial autocorrelation analyses showed that integrating foundation-model representations and structural predictors substantially reduced residual spatial dependence. Monte Carlo simulations demonstrated that hyperparameter optimization reduced model-performance variability by 27.9%. Our findings demonstrate that foundation-model Earth representations capture ecologically meaningful information relevant to forest biomass and provide a scalable framework for annual carbon monitoring in regions with incomplete airborne LiDAR coverage. Our fundings establish a pathway toward next-generation forest carbon assessment based on globally available foundation-model Earth observations.

Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelligence from Raw Earth Observation Streams

Multimodal Large Language Models (MLLMs) are increasingly used to interpret Earth observation data, yet their capability to support real-world disaster emergency response remains insufficiently evaluated. Existing remote sensing benchmarks largely rely on static, post-hoc, and expert-processed products, such as gridded reanalysis data, which are difficult to align with operational disaster scenarios where hazards evolve rapidly and decisions must be made under strict time constraints. To bridge this gap, we introduce Obshazard-bench, a real-time, observation-driven benchmark for evaluating disaster intelligence in MLLMs. Unlike image-centric or post-event benchmarks, Obshazard-bench directly integrates raw, high-frequency satellite sounding streams from diverse satellite sensors with concurrent ground-station observations, historical disaster records, and socio-economic indicators, bypassing delayed expert-processing and physical-inversion pipelines. The benchmark covers 8 major disaster categories and 28 sub-categories across more than 60 countries, incorporating over 120 historically documented extreme-event cases and thousands of lifecycle-oriented VQA samples. Moreover, Obshazard-bench further defines a three-stage evaluation taxonomy aligned with the operational disaster workflow: Predictive Crisis Anticipation for pre-disaster risk detection and early forecasting, Active Evolution Reasoning for in-situ disaster tracking and termination prediction, and Multi-faceted Impact Quantification for post-disaster magnitude deduction, humanitarian burden estimation, and socio-economic impact assessment. Experiments on representative general-purpose and Earth-focused foundation models reveal substantial limitations in transforming raw multi-channel physical observations into temporally grounded and decision-relevant disaster reasoning.

Benchmarking the Alignment of Data-Quality Metrics, Human Judgment and Land-Cover Segmentation Performance for Earth Observation

Volume and quality of datasets are crucial for deep learning model training, yet they are often constrained by availability and data acquisition costs. Synthetic data augmentation can extend existing datasets with realistic images, and the quality of these images is generally assessed through fidelity metrics such as FID, KID, IS, LPIPS and SSIM that measure structural or distributional similarity. However, such metrics, including the widely used FID, focus on visual fidelity without reflecting downstream utility, and can diverge from human perception under perturbations that are imperceptible to human observers. In this work, we systematically evaluate Earth observation datasets alongside synthetic counterparts generated by deep generative models, comparing automatic metrics against human perception and downstream tasks. Our results reveal a stark misalignment: semantics-preserving perturbations such as rotation drastically alter metric scores while leaving human recognition unaffected, and synthetic samples that score poorly on automatic metrics achieve comparable or higher perceived realism, and can improve downstream performance when combined with real data. By benchmarking semantic segmentation models trained on mixed real-synthetic datasets, we demonstrate that quality metrics rooted in ImageNet-pretrained feature spaces are unreliable indicators for geospatial data. Our findings underscore that automatic quality evaluation of synthetic datasets should be grounded in downstream task performance and human evaluation.

UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation

Vision Transformers (ViT) dominate computer vision. However, their reliance on rigid patch projectors hinders transfer to Earth Observation (EO), where input modalities, scales, and resolutions vary widely. We introduce UniverSat, a ViT-style backbone built around a Universal Patch Encoder that maps patches from arbitrary spatial, spectral, and temporal resolutions, and from both optical and non-optical sensors, into a shared embedding space with a shared set of weights. This enables training a single model on heterogeneous multimodal corpora via self-supervision, yielding robust, sensor-agnostic spatial features. We validate this approach with strong results across classification and segmentation on standard EO benchmarks from GeoBench, PANGEABench, and SpectralEarth. Our code and models are available at https://github.com/gastruc/UniverSat.

Exploring the potential of AlphaEarth and TESSERA embeddings for Fine-scale Local Climate Zone Mapping: A case study across five cities in Switzerland

Understanding urban spatial morphology is critical for climate modeling, risk assessment, and sustainable urban design, and Local Climate Zone (LCZ) mapping provides the basic framework for this. However, many cities still use coarse ~100-m resolution LCZ records, which are unsuitable for fine-scale urban research. In this study, precomputed embeddings from TESSERA (Feng et al., 2025) and AlphaEarth (Brown et al., 2025) are compared to traditional Sentinel-1/2 (S1S2) composites in five Swiss cities to see if they can upscale coarse LCZ maps to 10-m resolution using an attention-based U-Net. Three experiments assess multi-city transferability, the impact of higher-resolution reference data, and temporal robustness to year-to-year phenology changes. We find that all datasets achieve strong performance with test data Intersection-over-Union (IoU) ranging from 0.59-0.69 and 0.77-0.82 in the first two experiments. TESSERA consistently outperforms both S1S2 and AlphaEarth across both settings As expected, we find that the transfer of embedding-based models from one year to another remains an open challenge. Overall, however, our results demonstrate the promising potential of embeddings derived from EO foundation models to reduce time consuming preprocessing, respectively, manual feature engineering tasks and to guide a universal deep learning-based LCZ mapping workflow. When combined with a simple location-aware attention U-Net architecture, the embeddings enhance regional transferability and scalability, supporting the development of comprehensive and reproducible fine-scale LCZ maps for global urban climate applications Improving reference data quality remains the strongest lever for further accuracy gains.

Emerging Flexible Designs for Geospatial Multimodal Foundation Models

Foundation models are rapidly transforming Earth observation by enabling scalable pretraining across diverse unlabeled geospatial modalities. However, their architectural diversity ranging from encoder-only to encoder-decoder and masked autoencoding paradigms makes it challenging to assess performance trade offs in a consistent manner. In this work, we present an apples-to-apples comparison of leading FM architectures designed for geospatial multimodal reasoning, with a particular focus on flexibility across varied spectral band configurations. We standardize pretraining using identical self supervised learning objectives and training datasets, and evaluate all models under consistent parameterization on the GEOBench benchmark across classification and segmentation tasks. Our results offer new insights into the design trade-offs between model flexibility, modality alignment, and downstream task performance. By highlighting architectural strengths and limitations under controlled conditions, this study provides practical guidance for building next generation geospatial foundation models capable of robust multimodal reasoning.

AI4Land: Scalable Deep Learning for Global High-Resolution Land Use Reconstruction

Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly driven by the uncertainties affecting the land surface representation and variability in Earth system models. To address this limitation, we present a data-driven framework AI4Land, for generating high-resolution historical reconstructions and future projections of key land surface variables. The framework follows a two-phase approach using a U-Net architecture. In the first phase, which is the focus of this work, it reconstructs annual land use and land cover by integrating coarse-resolution scenario data with static geophysical features. In a planned second phase, the resulting high-resolution maps will be used to predict dynamic biophysical variables, particularly leaf area index, at finer temporal scales. Trained on Earth observation data, the models learn to reproduce spatially explicit and physically consistent land surface patterns, extending temporal coverage to periods lacking direct observations. AI4Land was developed and trained on MareNostrum5, demonstrating how GPU-accelerated HPC infrastructure enables global-scale climate AI pipelines. The final product is a suite of open-source emulators designed for real-time coupling with digital twin platforms, such as those developed under the Destination Earth initiative. By delivering realistic and evolving land surface conditions on demand, this work aims to reduce critical uncertainties and improve the predictive power of next-generation climate simulations.

Continuous biome representations from Earth observation embeddings

Biotic communities vary continuously across space, yet biome maps impose categorical boundaries that compress this variation, particularly at ecotones where transitional communities are ecologically distinct. Could Earth observation (EO) foundation models, which encode spectral, spatial, and temporal information with dense embeddings, convert discrete biome maps into continuous representations that better capture ecological variation? Here, we fit a linear classifier on Clay v1.5 satellite image embeddings to predict biome labels from a categorical map. The softmax output yields a continuous probability vector whose dimensions correspond to named biome classes. We evaluate this approach using six Brazilian biomes, 1.3 million embeddings, and 10,015 withheld forest inventory plots spanning 4,672 plant species. The continuous biome representation outperforms discrete biome labels for predicting species occurrence (mean per-species AUC 0.618 vs. 0.570 across 10 spatial cross-validation folds). Decomposing this gain shows that continuity in the graded probability output, rather than label reassignment, accounts for the improvement; the pattern holds across all distances from biome boundaries. The raw 1024-dimensional embedding remains the strongest predictor we tested (mean AUC 0.646 vs. 0.618), but the continuous representation recovers most of the embedding's gain over discrete labels. This simple approach provides a probabilistic replacement for categorical map labels, preserving their meaning while encoding graded variation that discrete maps suppress.

NAVI-Orbital: First In-Orbit Demonstration of a Zero-Shot Vision-Language Model for Autonomous Earth Observation

As Earth Observation data generation outpaces downlink bandwidth and human-in-the-loop processing, a widening gap has emerged between onboard collection and actionable ground intelligence. This paper presents NAVI-Orbital, a software system deployed on a Low Earth Orbit (LEO) spacecraft. On April 16, 2026, NAVI-Orbital achieved what is, to the authors' knowledge, the first in-orbit demonstration of a vision-language model performing autonomous multi-modal inference entirely onboard. NAVI-Orbital uses a local vision-language model (Gemma 3) to classify each captured scene, produce a text description of its content and the relationships between its features, and respond to operator follow-up via natural-language dialogue. The system is re-tasked through plain-English prompts in place of conventional command sequences, and is orchestrated by a graph-based state machine (LangGraph) coordinating dedicated agents for detection and dialogue. Results across ground benchmarking (88.16% accuracy on the 7,960-image curated AID benchmark), Flatsat validation, and live in-orbit captures of newly acquired, previously unseen Earth imagery (including uncorrected YAM-9 imagery, processed onboard with hardware-accelerated GPU inference and no fine-tuning for the flight instrument) demonstrate the feasibility of running foundation models on satellite-class edge computers to invert the conventional acquire-then-downlink-everything bandwidth profile through semantic compression of Earth observations in-orbit.