EUNIS Habitat Maps: Enhancing Thematic and Spatial Resolution for Europe through Machine Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916796036022272 |
|---|---|
| author | Si-Moussi, Sara Hennekens, Stephan Mücher, Sander De Keersmaecker, Wanda Chytrý, Milan Agrillo, Emiliano Attorre, Fabio Biurrun, Idoia Bonari, Gianmaria Čarni, Andraž Ćušterevska, Renata Dziuba, Tetiana Ecker, Klaus Güler, Behlül Jandt, Ute Jiménez-Alfaro, Borja Lenoir, Jonathan Svenning, Jens-Christian Swacha, Grzegorz Thuiller, Wilfried |
| author_facet | Si-Moussi, Sara Hennekens, Stephan Mücher, Sander De Keersmaecker, Wanda Chytrý, Milan Agrillo, Emiliano Attorre, Fabio Biurrun, Idoia Bonari, Gianmaria Čarni, Andraž Ćušterevska, Renata Dziuba, Tetiana Ecker, Klaus Güler, Behlül Jandt, Ute Jiménez-Alfaro, Borja Lenoir, Jonathan Svenning, Jens-Christian Swacha, Grzegorz Thuiller, Wilfried |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13649 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EUNIS Habitat Maps: Enhancing Thematic and Spatial Resolution for Europe through Machine Learning Si-Moussi, Sara Hennekens, Stephan Mücher, Sander De Keersmaecker, Wanda Chytrý, Milan Agrillo, Emiliano Attorre, Fabio Biurrun, Idoia Bonari, Gianmaria Čarni, Andraž Ćušterevska, Renata Dziuba, Tetiana Ecker, Klaus Güler, Behlül Jandt, Ute Jiménez-Alfaro, Borja Lenoir, Jonathan Svenning, Jens-Christian Swacha, Grzegorz Thuiller, Wilfried Applications Machine Learning Geophysics Quantitative Methods 62P12, 62M30, 92D40 I.2.6; J.3; I.6.5 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. |
| title | EUNIS Habitat Maps: Enhancing Thematic and Spatial Resolution for Europe through Machine Learning |
| topic | Applications Machine Learning Geophysics Quantitative Methods 62P12, 62M30, 92D40 I.2.6; J.3; I.6.5 |
| url | https://arxiv.org/abs/2506.13649 |