Szczegóły publikacji
Opis bibliograficzny
Identification of differences in habitat use patterns by individuals from separate animal populations through machine learning techniques / Małgorzata Charytanowicz, Kajetan Perzanowski, Maciej Januszczak, Aleksandra Wołoszyn-Gałęza, Maria Sobczuk, Piotr KULCZYCKI // Acta Oecologica ; ISSN 1146-609X . — 2026 — vol. 130 art. no. 104151, s. 1–9. — Bibliogr. s. 8–9, Abstr. — Publikacja dostępna online od: 2025-12-19. — P. Kulczycki - dod. afiliacja: Systems Research Institute, Polish Academy of Sciences, Warsaw, Poland
Autorzy (6)
- Charytanowicz Małgorzata
- Perzanowski Kajetan
- Januszczak Maciej
- Wołoszyn-Gałęza Aleksandra
- Sobczuk Maria
- AGHKulczycki Piotr
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 165612 |
|---|---|
| Data dodania do BaDAP | 2026-02-16 |
| Tekst źródłowy | URL |
| DOI | 10.1016/j.actao.2025.104151 |
| Rok publikacji | 2026 |
| Typ publikacji | artykuł w czasopiśmie |
| Otwarty dostęp |  |
| Czasopismo/seria | Acta Oecologica |
Abstract
A frequent problem in introduction programs is the assessment of introduction success measured as an acceptance of animals towards habitat patches selected for this purpose. Despite efforts to select optimal habitat patches for reintroduction programs, animals released to the wild rarely stay within such designated spots. Therefore, it is important to be able to evaluate their true landscape affiliation. Wisents upon having been reintroduced to the Bieszczady Mountains, have remained in two separate subpopulations of slightly different habitats. In this study, we compared the affiliation to their home ranges. Using movement data obtained through radio-tracking and employing machine learning techniques (notably, eXtreme Gradient Boosting) for classification purposes, we were able to obtain a precise determination of the most intensively used habitats within their home ranges. We analysed 31,480 location records of wisent presence in the Bieszczady Mountains during the years 2002–2021, and correlated this with data on land use and land cover obtained from the Corine Land Cover inventory. The machine-learning algorithm XGBoost was then applied to identify the affiliation of individual wisents to habitats within the home range of the given subpopulation. The results showed very high classification performance, with a recognition accuracy of 92 % in the vegetative and 96 % in the winter seasons. We thus propose a new approach to recognizing the affiliation of particular individuals to their home ranges. This may considerably improve the decision-making process in conservation and management of wildlife populations.
