Continental-scale habitat distribution modelling with multimodal earth observation foundation models

• URL: http://arxiv.org/abs/2507.09732v2
• Date: Mon, 27 Oct 2025 09:12:08 GMT
• Title: Continental-scale habitat distribution modelling with multimodal earth observation foundation models
• Authors: Sara Si-Moussi, Stephan Hennekens, Sander Mucher, Stan Los, Yoann Cartier, Borja Jiménez-Alfaro, Fabio Attorre, Jens-Christian Svenning, Wilfried Thuiller,
• Abstract summary: Habitats integrate the abiotic conditions, vegetation composition and structure that support biodiversity and sustain nature's contributions to people.<n>Current habitat maps often fall short in thematic or spatial resolution.<n>We evaluated how high-resolution remote sensing (RS) data and Artificial Intelligence (AI) tools can improve habitat mapping.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Habitats integrate the abiotic conditions, vegetation composition and structure that support biodiversity and sustain nature's contributions to people. Most habitats face mounting pressures from human activities, which requires accurate, high-resolution habitat mapping for effective conservation and restoration. Yet, current habitat maps often fall short in thematic or spatial resolution because they must (1) model several mutually exclusive habitat types that co-occur across landscapes and (2) cope with severe class imbalance that complicates exhaustive multi-class training. Here, we evaluated how high-resolution remote sensing (RS) data and Artificial Intelligence (AI) tools can improve habitat mapping across large geographical extents at fine spatial and thematic resolution. Using vegetation plots from the European Vegetation Archive, we modelled the distribution of Level 3 EUNIS habitat types across Europe and assessed multiple modelling strategies against independent validation datasets. Strategies that exploited the hierarchical nature of habitat classifications resolved classification ambiguities, especially in fragmented habitats. Integrating satellite-borne multispectral and radar imagery, particularly through Earth Observation (EO) Foundation models (EO-FMs), enhanced within-formation discrimination and overall performance. Finally, ensemble machine learning that corrects class imbalance boosted predictive accuracy even further. Our methodological framework is transferable beyond Europe and adaptable to other classification systems. Future research should advance temporal modelling of habitat dynamics, extend to habitat segmentation and quality assessment, and exploit next-generation EO data paired with higher-quality in situ observations.

Related papers

• A Method for Identifying Farmland System Habitat Types Based on the Dynamic-Weighted Feature Fusion Network Model [0.0]
  This study developed an annotated ultra-high-resolution remote sensing image dataset encompassing 15 categories of cultivated land system habitats.<n>We propose a Dynamic-Weighted Feature Fusion Network (DWFF-Net) to extract foundational features.<n>The proposed model achieves a mean Intersection over Union (mIoU) of 0.6979 and an F1-score of 0.8049, outperforming the baseline network by 0.021 and 0.0161, respectively.
  arXiv  Detail & Related papers  (2025-11-11T02:44:38Z)
• Automated classification of natural habitats using ground-level imagery [1.9646275424931439]
  We present a methodology for classification of habitats based solely on ground-level imagery (photographs)<n>This study develops a classification system that applies deep learning to ground-level habitat photographs, categorising each image into one of 18 classes defined by the 'Living England' framework.<n>Using five-fold cross-validation, the model demonstrated strong overall performance across 18 habitat classes, with accuracy and F1-scores varying between classes.
  arXiv  Detail & Related papers  (2025-08-26T10:57:53Z)
• BioAnalyst: A Foundation Model for Biodiversity [0.565395466029518]
  We introduce BioAnalyst, the first Foundation Model tailored for biodiversity analysis and conservation planning.<n>BioAnalyst employs a transformer-based architecture, pretrained on extensive multi-modal datasets.<n>We evaluate the model's performance on two downstream use cases, demonstrating its generalisability compared to existing methods.
  arXiv  Detail & Related papers  (2025-07-11T23:56:08Z)
• Deep learning-based species-area models reveal multi-scale patterns of species richness and turnover [0.0]
  As the sampled area expands, species richness increases, a phenomenon described by the species-area relationship (SAR)<n>Here, we develop a deep learning approach that leverages sampling theory and small-scale ecological surveys to spatially resolve the scale-dependency of species richness.<n>Our model improves species richness estimates by 32% and delivers spatially explicit patterns of species richness and turnover for sampling areas ranging from square meters to hundreds of square kilometers.
  arXiv  Detail & Related papers  (2025-07-08T19:42:33Z)
• Habitat Classification from Ground-Level Imagery Using Deep Neural Networks [1.3408365072149797]
  This study applies state-of-the-art deep neural network architectures to ground-level habitat imagery.<n>We evaluate two families of models -- convolutional neural networks (CNNs) and vision transformers (ViTs)<n>Our results demonstrate that ViTs consistently outperform state-of-the-art CNN baselines on key classification metrics.
  arXiv  Detail & Related papers  (2025-07-05T12:07:13Z)
• EUNIS Habitat Maps: Enhancing Thematic and Spatial Resolution for Europe through Machine Learning [0.0]
  The EUNIS habitat classification is crucial for categorising European habitats.<n>We provide predictions for 260 EUNIS habitat types at hierarchical level 3.<n>We produce a European habitat map indicating the most probable EUNIS habitat at 100-m resolution across Europe.
  arXiv  Detail & Related papers  (2025-06-16T16:10:08Z)
• TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation [65.74990259650984]
  We introduce TerraFM, a scalable self-supervised learning model that leverages globally distributed Sentinel-1 and Sentinel-2 imagery.<n>Our training strategy integrates local-global contrastive learning and introduces a dual-centering mechanism.<n>TerraFM achieves strong generalization on both classification and segmentation tasks, outperforming prior models on GEO-Bench and Copernicus-Bench.
  arXiv  Detail & Related papers  (2025-06-06T17:59:50Z)
• BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning [51.341003735575335]
  We find emergent behaviors in biological vision models via large-scale contrastive vision-language training.<n>We train BioCLIP 2 on TreeOfLife-200M to distinguish different species.<n>We identify emergent properties in the learned embedding space of BioCLIP 2.
  arXiv  Detail & Related papers  (2025-05-29T17:48:20Z)
• Mapping biodiversity at very-high resolution in Europe [2.4081658738294283]
  This paper describes a cascading multimodal pipeline for high-resolution biodiversity mapping across Europe.<n>The proposed pipeline first predicts species compositions using a deep-SDM, a multimodal model trained on remote sensing, climate time series, and species occurrence data at 50x50m resolution.<n>These predictions are then used to generate biodiversity indicator maps and classify habitats with Pl@ntBERT.
  arXiv  Detail & Related papers  (2025-04-07T16:15:52Z)
• Image-Based Relocalization and Alignment for Long-Term Monitoring of Dynamic Underwater Environments [57.59857784298534]
  We propose an integrated pipeline that combines Visual Place Recognition (VPR), feature matching, and image segmentation on video-derived images.<n>This method enables robust identification of revisited areas, estimation of rigid transformations, and downstream analysis of ecosystem changes.
  arXiv  Detail & Related papers  (2025-03-06T05:13:19Z)
• SPARTAN: A Sparse Transformer Learning Local Causation [63.29645501232935]
  Causal structures play a central role in world models that flexibly adapt to changes in the environment. We present the SPARse TrANsformer World model (SPARTAN), a Transformer-based world model that learns local causal structures between entities in a scene. By applying sparsity regularisation on the attention pattern between object-factored tokens, SPARTAN identifies sparse local causal models that accurately predict future object states.
  arXiv  Detail & Related papers  (2024-11-11T11:42:48Z)
• Combining Observational Data and Language for Species Range Estimation [63.65684199946094]
  We propose a novel approach combining millions of citizen science species observations with textual descriptions from Wikipedia.<n>Our framework maps locations, species, and text descriptions into a common space, enabling zero-shot range estimation from textual descriptions.<n>Our approach also acts as a strong prior when combined with observational data, resulting in more accurate range estimation with less data.
  arXiv  Detail & Related papers  (2024-10-14T17:22:55Z)
• SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Data [68.2366021016172]
  We present SatBird, a satellite dataset of locations in the USA with labels derived from presence-absence observation data from the citizen science database eBird. We also provide a dataset in Kenya representing low-data regimes. We benchmark a set of baselines on our dataset, including SOTA models for remote sensing tasks.
  arXiv  Detail & Related papers  (2023-11-02T02:00:27Z)
• Activation Regression for Continuous Domain Generalization with Applications to Crop Classification [48.795866501365694]
  Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions. We model geographic generalisation in medium resolution Landsat-8 satellite imagery as a continuous domain adaptation problem. We develop a dataset spatially distributed across the entire continental United States.
  arXiv  Detail & Related papers  (2022-04-14T15:41:39Z)
• Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology [0.0]
  We show that ensembles of Data-efficient image Transformers (DeiTs) significantly outperform the previous state of the art (SOTA) On all the data sets we test, we achieve a new SOTA, with a reduction of the error with respect to the previous SOTA ranging from 18.48% to 87.50%.
  arXiv  Detail & Related papers  (2022-03-03T14:16:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.