A multi-view contrastive learning framework for spatial embeddings in risk modelling

Earth Embeddings

Earth observation is moving from foundation models that users must run themselves toward embedding products that package model feature outputs as reusable data without needing to download and process the imagery used to generate them. Earth embeddings are vectors that summarize locations, image patches, or pixels, letting users analyze compact features instead of repeatedly training or running large models on raw satellite imagery. This chapter explains the main types of Earth embeddings, from implicit location encoders to explicit patch and pixel products, and compares their coverage, resolution, dimensionality, storage cost, licenses, and reproducibility. We review their use in land cover and crop mapping, ecological and hazard modeling, socioeconomic prediction, and semantic search, with evidence on when embeddings improve on conventional features and when pooling, fusion, or spatial transfer limit performance. Two case studies show practical workflows for similarity search and land cover mapping. We close with guidance for choosing, evaluating, storing, compressing, and publishing embeddings, and with open problems in oceanic and atmospheric coverage, uncertainty, and benchmarking.

SAGE-XGBoost: Spatially Augmented Graph Embeddings--Machine Learning Framework for Natural Hazards Susceptibility Mapping under Data Scarcity

Natural hazard susceptibility mapping is often constrained by limited labeled data, reducing the generalizability of conventional machine learning and limiting the applicability of complex deep learning models. This study proposes SAGE (Spatially Augmented Graph Embeddings), a structurally informed feature-engineering framework that combines controlled noise-based data augmentation with neighborhood-based graph embeddings to improve prediction under data-scarce conditions. A K-nearest neighbor graph is constructed to derive local spatial statistics, which are reduced using principal component analysis and integrated with environmental covariates and spatial coordinates. The resulting features are used with XGBoost to develop the SAGE-XGBoost model. The framework was evaluated for landslide and wildfire susceptibility mapping. SAGE-XGBoost consistently outperformed conventional and spatially explicit machine learning models. Compared with Spatial XGBoost, it achieved an absolute improvement of above 33 percentage points across the two case studies. The model reached AUC values of approximately 0.97 for landslide susceptibility and 0.95 for wildfire susceptibility. Feature importance analysis confirmed the contribution of graph embeddings to prediction, while their integration improved spatial coherence and reduced local noise amplification. Overall, SAGE-XGBoost provides an efficient and transferable alternative to deep representation learning for environmental hazard assessment and other geospatial prediction tasks under limited supervision.

Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding

Geospatial and urban applications increasingly require models to compare heterogeneous evidence across street-view imagery, remote-sensing observations, text descriptions, region proposals, and temporal change cues. However, existing multimodal embedding models and benchmarks are still largely designed and evaluated around general-purpose image-text matching, leaving unclear whether unified embedding space can support heterogeneous geospatial tasks involving spatial relationships, fine-grained semantics, and temporal changes. To address this gap, we make three key contributions. First, we introduce GeoMEB, a large-scale multimodal embedding benchmark that standardizes 45 urban evaluation tasks across retrieval, visual question answering, change detection, classification, and visual grounding, together with training collections comprising 1.32M examples and 286K evaluation queries. Second, we present Geo-Embed, a unified embedding model that adapts a shared vision-language backbone to instruction-conditioned query-target matching over heterogeneous geospatial inputs, including single images, multiple images, text, regions, and masks. On GeoMEB, Geo-Embed achieves the strongest overall performance among representative multimodal embedders, with a 15.3% relative improvement over the strongest baseline. These results motivate future geospatial embedders that organize training and evaluation around explicit query-target relations, including semantic, cross-view, region-level, and temporal correspondence.

Earth Embedding Products for Geospatial Analysis: Foundations, Applications, and Open Challenges

Is a (satellite) image worth a thousand data points? Comparing machine learning approaches to predict environmental and social inequalities in England

Accurately mapping environmental and social inequalities at fine spatial scales is critical for urban policy, yet the data required are often costly and infrequently updated. Vision foundation models can extract information directly from satellite imagery, offering a rapid and scalable alternative. We compare three modelling pipelines for predicting two contrasting indicators of urban inequality – air pollution and house prices – across England on a fine hexagonal grid: regression models trained on structured features of form and function (census, land cover and urban morphology), models trained on 128-dimensional image embeddings from a geospatial foundation model and a hybrid of the two, each evaluated with and without coarse regional context. Structured features achieve the best overall accuracy, but image embeddings become competitive once regional context is added – most clearly for air pollution, where image-only models reach a median R2 of 0.78 (0.85 with regional context), indicating that the embeddings capture genuine image signal. For house prices the picture is more cautious: image-only models achieve a median R2 of around 0.58; however, much of the embeddings’ apparent gain reflects coarse spatial location rather than image content. Off-the-shelf satellite embeddings, while not yet surpassing data-intensive approaches, are a promising low-cost complement, particularly for rapid, large-scale, or repeated analyses and in settings where traditional data are limited.

GBFlow: Grouping Belief-Guided Dual Normalizing Flows for Accurate Spatial Domain Delineation