arXiv subjects

Borja Jiménez-Alfaro

Publications and source records attributed to Borja Jiménez-Alfaro.

3 recordsLinked to original sources

arXiv2025

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

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.

cs.LG↗

arXiv2025

EUNIS Habitat Maps: Enhancing Thematic and Spatial Resolution for Europe through Machine Learning

The EUNIS habitat classification is crucial for categorising European habitats, supporting European policy on nature conservation and implementing the Nature Restoration Law. To meet the growing demand for detailed and accurate habitat information, we provide spatial predictions for 260 EUNIS habitat types at hierarchical level 3, together with independent validation and uncertainty analyses. Using ensemble machine learning models, together with high-resolution satellite imagery and ecologically meaningful climatic, topographic and edaphic variables, we produced a European habitat map indicating the most probable EUNIS habitat at 100-m resolution across Europe. Additionally, we provide information on prediction uncertainty and the most probable habitats at level 3 within each EUNIS level 1 formation. This product is particularly useful for both conservation and restoration purposes. Predictions were cross-validated at European scale using a spatial block cross-validation and evaluated against independent data from France (forests only), the Netherlands and Austria. The habitat maps obtained strong predictive performances on the validation datasets with distinct trade-offs in terms of recall and precision across habitat formations.

stat.AP↗

arXiv2018

Beta-diversity of Central European forests decreases along an elevational gradient due to the variation in local community assembly processes

Beta-diversity has been repeatedly shown to decline with increasing elevation, but the causes of this pattern remain unclear, partly because they are confounded by coincident variation in alpha- and gamma-diversity. We used 8,795 forest vegetation-plot records from the Czech National Phytosociological Database to compare the observed patterns of beta diversity to null-model expectations (beta-deviation) controlling for the effects of alpha- and gamma-diversity. We tested whether \b{eta}-diversity patterns along a 1,200 m elevation gradient exclusively depend on the effect of varying species pool size, or also on the variation of the magnitude of community assembly mechanisms determining the distribution of species across communities (e.g., environmental filtering, dispersal limitation). The null model we used is a novel extension of an existing null-model designed for presence/absence data and was specifically designed to disrupt the effect of community assembly mechanisms, while retaining some key features of observed communities such as average species richness and species abundance distribution. Analyses were replicated in ten subregions with comparable elevation ranges. Beta-diversity declined along the elevation gradient due to a decrease in gamma-diversity, which was steeper than the decrease in alpha-diversity. This pattern persisted after controlling for alpha- and gamma-diversity variation, and the results were robust when different resampling schemes and diversity metrics were used. We conclude that in temperate forests the pattern of decreasing beta-diversity with elevation does not exclusively depend on variation in species pool size, as has been hypothesized, but also on variation in community assembly mechanisms. The results were consistent across resampling schemes and diversity measures, thus supporting the use of vegetation plot databases for understanding...

q-bio.PE↗