Aim: The EUNIS Habitat Classification is a widely used reference framework for European habitat types (habitats), but it lacks formal definitions of individual habitats that would enable their unequivocal identification. Our goal was to develop a tool for assigning vegetation‐plot records to the habitats of the EUNIS system, use it to classify a European vegetation‐plot database, and compile statistically‐derived characteristic species combinations and distribution maps for these habitats.Location: Europe.Methods: We developed the classification expert system EUNIS‐ESy, which contains definitions of individual EUNIS habitats based on their species composition and geographic location. Each habitat was formally defined as a formula in a computer language combining algebraic and set‐theoretic concepts with formal logical operators. We applied this expert system to classify 1,261,373 vegetation plots from the European Vegetation Archive (EVA) and other databases. Then we determined diagnostic, constant and dominant species for each habitat by calculating species‐to‐habitat fidelity and constancy (occurrence frequency) in the classified data set. Finally, we mapped the plot locations for each habitat.Results: Formal definitions were developed for 199 habitats at Level 3 of the EUNIS hierarchy, including 25 coastal, 18 wetland, 55 grassland, 43 shrubland, 46 forest and 12 man‐made habitats. The expert system classified 1,125,121 vegetation plots to these habitat groups and 73,188 to other habitats, while 63,064 plots remained unclassified or were classified to more than one habitat. Data on each habitat were summarized in factsheets containing habitat description, distribution map, corresponding syntaxa and characteristic species combination.Conclusions: EUNIS habitats were characterized for the first time in terms of their species composition and distribution, based on a classification of a European database of vegetation plots using the newly developed electronic expert system EUNIS‐ESy. The data provided and the expert system have considerable potential for future use in European nature conservation planning, monitoring and assessment.

Research in global change ecology relies heavily on global climatic grids derived from estimates of air temperature in open areas at around 2 m above the ground. These climatic grids do not reflect conditions below vegetation canopies and near the ground surface, where critical ecosystem functions occur and most terrestrial species reside. Here, we provide global maps of soil temperature and bioclimatic variables at a 1‐km²resolution for 0–5 and 5–15 cm soil depth. These maps were created by calculating the difference (i.e. offset) between in situ soil temperature measurements, based on time series from over 1200 1‐km²pixels (summarized from 8519 unique temperature sensors) across all the world's major terrestrial biomes, and coarse‐grained air temperature estimates from ERA5‐Land (an atmospheric reanalysis by the European Centre for Medium‐Range Weather Forecasts). We show that mean annual soil temperature differs markedly from the corresponding gridded air temperature, by up to 10°C (mean = 3.0 ± 2.1°C), with substantial variation across biomes and seasons. Over the year, soils in cold and/or dry biomes are substantially warmer (+3.6 ± 2.3°C) than gridded air temperature, whereas soils in warm and humid environments are on average slightly cooler (−0.7 ± 2.3°C). The observed substantial and biome‐specific offsets emphasize that the projected impacts of climate and climate change on near‐surface biodiversity and ecosystem functioning are inaccurately assessed when air rather than soil temperature is used, especially in cold environments. The global soil‐related bioclimatic variables provided here are an important step forward for any application in ecology and related disciplines. Nevertheless, we highlight the need to fill remaining geographic gaps by collecting more in situ measurements of microclimate conditions to further enhance the spatiotemporal resolution of global soil temperature products for ecological applications.

Aims: The accurate classification of habitats is essential for effective biodiversity conservation. The goal of this study was to harness the potential of deep learning to advance habitat identification in Europe. We aimed to develop and evaluate models capable of assigning vegetation‐plot records to the habitats of the European Nature Information System (EUNIS), a widely used reference framework for European habitat types.Location: The framework was designed for use in Europe and adjacent areas (e.g., Anatolia, Caucasus).Methods: We leveraged deep‐learning techniques, such as transformers (i.e., models with attention components able to learn contextual relations between categorical and numerical features) that we trained using spatial k‐fold cross‐validation (CV) on vegetation plots sourced from the European Vegetation Archive (EVA), to show that they have great potential for classifying vegetation‐plot records. We tested different network architectures, feature encodings, hyperparameter tuning and noise addition strategies to identify the optimal model. We used an independent test set from the National Plant Monitoring Scheme (NPMS) to evaluate its performance and compare its results against the traditional expert systems.Results: Exploration of the use of deep learning applied to species composition and plot‐location criteria for habitat classification led to the development of a framework containing a wide range of models. Our selected algorithm, applied to European habitat types, significantly improved habitat classification accuracy, achieving a more than twofold improvement compared to the previous state‐of‐the‐art (SOTA) method on an external data set, clearly outperforming expert systems. The framework is shared and maintained through a GitHub repository.Conclusions: Our results demonstrate the potential benefits of the adoption of deep learning for improving the accuracy of vegetation classification. They highlight the importance of incorporating advanced technologies into habitat monitoring. These algorithms have shown to be better suited for habitat type prediction than expert systems. They push the accuracy score on a database containing hundreds of thousands of standardized presence/absence European surveys to 88.74%, as assessed by expert judgment. Finally, our results showcase that species dominance is a strong marker of ecosystems and that the exact cover abundance of the flora is not required to train neural networks with predictive performances. The framework we developed can be used by researchers and practitioners to accurately classify habitats.

To address the urgent biodiversity crisis, it is crucial to understand the nature of plant assemblages. The distribution of plant species is shaped not only by their broad environmental requirements but also by micro-environmental conditions, dispersal limitations, and direct and indirect species interactions. While predicting species composition and habitat type is essential for conservation and restoration purposes, it remains challenging. In this study, we propose an approach inspired by advances in large language models to learn the ‘syntax’ of abundance-ordered plant species sequences in communities. Our method, which captures latent associations between species across diverse ecosystems, can be fine-tuned for diverse tasks. In particular, we show that our methodology is able to outperform other approaches to (1) predict species that might occur in an assemblage given the other listed species, despite being originally missing in the species list (16.53% higher accuracy in retrieving a plant species removed from an assemblage than co-occurrence matrices and 6.56% higher than neural networks), and (2) classify habitat types from species assemblages (5.54% higher accuracy in assigning a habitat type to an assemblage than expert system classifiers and 1.14% higher than tabular deep learning). The proposed application has a vocabulary that covers over 10,000 plant species from Europe and adjacent countries and provides a powerful methodology for improving biodiversity mapping, restoration and conservation biology. As ecologists begin to explore the use of artificial intelligence, such approaches open opportunities for rethinking how we model, monitor and understand nature.

Soil seed banks of alien plant species are sources of propagules that play a crucial role in plant population dynamics. Studies on seed banks of woody alien species are crucial for understanding mechanisms of their encroachment on natural habitats. This study aimed to compare vertical distribution, density and composition of seed banks formed by native Cornus sanguinea subsp. sanguinea and alien C. alba, C. sericea and C. sanguinea subsp. australis in the Southern Hemiboreal zone of Europe. Five sites for each of four taxa were selected for the study, and seeds were sampled using the soil core method (400 samples in two soil layers: the upper, 0–5 cm, and the lower, 5–10 cm). Extracted seeds were tested with tetrazolium chloride stain to assess their viability. Differences in the seed banks among taxa were compared using generalised linear mixed models (GLMM). The GLMM analysis revealed significant differences in soil seed bank densities in the upper soil between the studied taxa (p < 0.001). We found that two of the alien taxa (C. alba and C. sanguinea subsp. australis) formed a much denser seed bank containing more viable seeds than the native Cornus sanguinea subsp. sanguinea. All three alien species contained more viable seeds (from 40.7% to 45.2% in the upper soil layer) than the native C. sanguinea subsp. sanguinea (19.4% in the upper and 18.2% in the lower soil layer). The cover of Cornus and habitat type had no significant effect on the density of the seed bank, according to GLMM. This study supports the hypothesis that seed banks of alien C. alba and C. sanguinea subsp. australis are denser than those of native C. sanguinea subsp. sanguinea. Furthermore, the seed bank of alien taxa contained more viable seeds than the seed bank of C. sanguinea subsp. sanguinea. Results of this study contribute to the understanding of the invasiveness of alien Cornus taxa.