Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
AimsThe 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.LocationThe framework was designed for use in Europe and adjacent areas (e.g., Anatolia, Caucasus).MethodsWe 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.ResultsExploration 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.ConclusionsOur 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.
AimsThe 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.LocationThe framework was designed for use in Europe and adjacent areas (e.g., Anatolia, Caucasus).MethodsWe 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.ResultsExploration 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.ConclusionsOur 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.
New Italian data on the distribution of some of the Annex I Habitats are reported in this contribution. Specifically, 16 records are presented including 9 new occurrences in Natura 2000 sites, and 27 new cells are added in the EEA 10 km × 10 km reference grid. The new data refer to the Italian administrative regions of Abruzzo, Apulia, Latium, Marche, Lombardy, Piedmont, Sardinia, Sicily, Tuscany, and Veneto.
Aim: To revise Pinus pinaster-dominated communities of the Italian peninsula with special regard to central-southern Tuscany, and assess their floristic and ecological differences. Study area: Tuscany and Liguria regions, Italy. Methods: We classified 251 vegetation plots using the Two-way indicator species analysis method and we explored vegetation patterns through Principal Coordinate Analysis. We then investigated the ecology using Ecological Indicator Values. Results: We identified four major groups, primarily distinguished by the substrate of their stands and along a latitudinal gradient. We classified the forests in central-southern Tuscany in the association Erico scopariae-Pinetum pinastri. This community includes thermophilous and mesophilous species primarily distributed in the Atlantic and Western Mediterranean regions. Comparison of community means of Ecological Indicator Values revealed significant differences in soil reaction, nitrogen, moisture, and light conditions, but not in temperature, between the central-southern Tuscany forests and the other clusters. We classified the other studied forest communities on acidic substrates within the association Erico arboreae-Pinetum pinastri, whereas those found on ultramafic substrates were placed in the Euphorbio ligusticae-Pinetum pinastri typus cons. propos., and in an informal group of secondary vegetation stands. Conclusions: Our analyses showed that the Pinus pinaster-dominated forests of central-southern Tuscany belong to the association Erico scopariae-Pinetum pinastri of the alliance Genisto pilosae-Pinion pinastri (class Pinetea halepensis). The presence of species of phytogeographical importance in the forest understory, underscores the high biogeographic and conservation value of these pine forests. Taxonomic reference: Euro+Med (2024-). Syntaxonomic reference: Mucina et al. (2016), except for the changes proposed by Bonari et al. (2021). Abbreviations: EVC = EuroVegChecklist; ICPN = International Code of Phytosociological Nomenclature; PCoA = Principal Coordinate Analysis; TWINSPAN = Two-way indicator species analysis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2025 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.