Kajetan Perzanowski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kajetan Perzanowski has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Maciej Januszczak
Museum and Institute of Zoology, Poland
3 shared publications - Aleksandra Wołoszyn-Gałęza
Museum and Institute of Zoology, Polish Academy of Sciences, Ogrodowa 10, 38-700 Ustrzyki Dolne, Poland, Poland
1 shared publication - Aleksandra Wołoszyn-Gałęza
Carpathian Wildlife Research Station, Museum and Institute of Zoology Polish Academy of Sciences, 38-700 Ustrzyki Dolne, Poland
1 shared publication - Aleksandra Wołoszyn-Gałęza
Museum and Institute of Zoology, Poland
1 shared publication - Jozef Štofík
National Park Poloniny, Slovakia
1 shared publication - Maria Sobczuk
Department of Animal Genetics and Conservation, Warsaw University of Life Sciences, Ciszewskiego 8, 02-786 Warsaw, Poland
1 shared publication
Latest Publications
- Open Access
- 4 July 2025
- Published by MDPI AG in Preprints.org
Recognition of Animals’ Affiliation with Habitat Patches Using Machine Learning Techniques
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 isolated subpopulations of slightly different habitats. Using movement data obtained through radio-tracking and employing machine learning (ML) techniques (notably, eXtreme Gradient Boosting (XGBoost)) for classification purposes, we were able to obtain a precise determination of preferred habitats within their home rangeswe analyzed 31,480 location records of wisent presence in the Bieszczady Mountains during the years 2002-2021 and correlated this data on land use and land cover obtained from the CORINE Land Cover (CLC) 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 amay considerably improve the decision-making process in conservation and management of wildlife populations.
- 4 July 2025
- Published by MDPI AG in Preprints.org
Open AccessRecognition of Animals’ Affiliation with Habitat Patches Using Machine Learning Techniques
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 isolated subpopulations of slightly different habitats. Using movement data obtained through radio-tracking and employing machine learning (ML) techniques (notably, eXtreme Gradient Boosting (XGBoost)) for classification purposes, we were able to obtain a precise determination of preferred habitats within their home rangeswe analyzed 31,480 location records of wisent presence in the Bieszczady Mountains during the years 2002-2021 and correlated this data on land use and land cover obtained from the CORINE Land Cover (CLC) 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 amay considerably improve the decision-making process in conservation and management of wildlife populations.
- Open Access
- 19 November 2024
- Published by MDPI AG in Preprints.org
Forest Corridors Crucial for a Metapopulation of Wisents in the Carpathians—a Potential Rescue for Ukrainian Population of the Species
A majority of free ranging wisent (Bison bonasus L.) populations in Ukraine is critically threatened by the acts of warfare. The only, relatively safe populations, dwell in the Carpathians. One of them - the herd inhabiting Skolyvsky Beskyd National Park, lives in a close proximity to larger herds from Bieszczady Mountains in Poland and National Park Poloniny in Slovakia. Creating conditions for a mutual exchange of individuals within those populations, could secure genetic diversity of the Ukrainian herd in a long term. Such migrations are however limited by permeability of forest corridors, linking herds dwelling across Polish and Slovak borders. Additionally, a border fence along the Ukrainian border effectively prevents any transboundary movements of large mammals. In this paper ecological conditions along national borders of those three countries are analysed, and existing obstacles for animal movements are identified. A concept for the creation a functional metapopulation of wisents, within this transboundary region of the Carpathians is proposed.
- 19 November 2024
- Published by MDPI AG in Preprints.org
Open AccessForest Corridors Crucial for a Metapopulation of Wisents in the Carpathians—a Potential Rescue for Ukrainian Population of the Species
A majority of free ranging wisent (Bison bonasus L.) populations in Ukraine is critically threatened by the acts of warfare. The only, relatively safe populations, dwell in the Carpathians. One of them - the herd inhabiting Skolyvsky Beskyd National Park, lives in a close proximity to larger herds from Bieszczady Mountains in Poland and National Park Poloniny in Slovakia. Creating conditions for a mutual exchange of individuals within those populations, could secure genetic diversity of the Ukrainian herd in a long term. Such migrations are however limited by permeability of forest corridors, linking herds dwelling across Polish and Slovak borders. Additionally, a border fence along the Ukrainian border effectively prevents any transboundary movements of large mammals. In this paper ecological conditions along national borders of those three countries are analysed, and existing obstacles for animal movements are identified. A concept for the creation a functional metapopulation of wisents, within this transboundary region of the Carpathians is proposed.
- Open Access
European Beech Masting Cycles and the Spatial Distribution of Wisents in the Bieszczady Mountains, Poland
The variability of food resources considerably affects the habitat preferences of animals. In mast years, the availability of highly nutritive food increases significantly. We tested whether changes in the distribution of the areas of wisents, Bison bonasus L. concentration, in the Bieszczady Mountains, Poland, were connected with the availability of beechnuts. In the two beech masting years of 2013 and 2022, we considered the months with the highest availability of beechnuts, namely September and October. The beechnut crop varied significantly between as little as 2.4 g dry matter/m2, recorded within the Baligród herd’s home range in 2013, and up to 238.8 g dry matter/m2 within the Tworylne herd’s range, also in 2013. The analysis of the spatial distribution of beech stands within various parts of the wisents’ home range showed that within the 95% kernel area, their share was mostly high, varying between 25.7% and 42.8%. Meanwhile, within the 50% kernel area, it was generally much lower, except for the year 2022 in the case of the Baligród herd. The densities of wisents varied significantly between the kernel areas of 95% and 50%, ranging between 0.04 and 0.08 animals/ha and 0.17 and 0.48 animals/ha, respectively. However, there was no statistical difference between the figures for all plots tested within the home range of the wisent population and plots dominated by beech. Based on the data obtained in this study, habitat selection patterns of wisents in the Bieszczady Mountains cannot be explained by the availability of beech stands and the phenomenon of mast years.
Open AccessEuropean Beech Masting Cycles and the Spatial Distribution of Wisents in the Bieszczady Mountains, Poland
The variability of food resources considerably affects the habitat preferences of animals. In mast years, the availability of highly nutritive food increases significantly. We tested whether changes in the distribution of the areas of wisents, Bison bonasus L. concentration, in the Bieszczady Mountains, Poland, were connected with the availability of beechnuts. In the two beech masting years of 2013 and 2022, we considered the months with the highest availability of beechnuts, namely September and October. The beechnut crop varied significantly between as little as 2.4 g dry matter/m2, recorded within the Baligród herd’s home range in 2013, and up to 238.8 g dry matter/m2 within the Tworylne herd’s range, also in 2013. The analysis of the spatial distribution of beech stands within various parts of the wisents’ home range showed that within the 95% kernel area, their share was mostly high, varying between 25.7% and 42.8%. Meanwhile, within the 50% kernel area, it was generally much lower, except for the year 2022 in the case of the Baligród herd. The densities of wisents varied significantly between the kernel areas of 95% and 50%, ranging between 0.04 and 0.08 animals/ha and 0.17 and 0.48 animals/ha, respectively. However, there was no statistical difference between the figures for all plots tested within the home range of the wisent population and plots dominated by beech. Based on the data obtained in this study, habitat selection patterns of wisents in the Bieszczady Mountains cannot be explained by the availability of beech stands and the phenomenon of mast years.