LAUSR.org creates dashboard-style pages of related content for over 1.5 million academic articles. Sign Up to like articles & get recommendations!

Spatial Distribution Patterns of Eurasian Otter (Lutra Lutra) in Association with Environmental Factors Unravelled by Machine Learning and Diffusion Kernel Method

Photo from wikipedia

In South Korea, the endangered Eurasian otter (Lutra lutra) populations have been recovered throughout the country. To examine the status of otter populations, we monitored spraint densities at 250 ~… Click to show full abstract

In South Korea, the endangered Eurasian otter (Lutra lutra) populations have been recovered throughout the country. To examine the status of otter populations, we monitored spraint densities at 250 ~ 355 sites annually from 2014 to 2017 in the Nakdong River basin. The diffusion kernel method was applied to both binary and continuous spraint data. Two geographical popula - tions were identified: northern and southern populations. The northern population continuously increased over a broad area from north to south during the study period. In contrast, the southern population narrowly dispersed, limited by its location in an industrial area. The spatial self-organizing map (Geo-SOM) revealed associations between spraint densities and environmental factors by correlating the geographic locations of the sampling sites. Both populations were negatively affected by anthropogenic factors, including proximi - ty to factories and human population density. However, cumulative association of all environmental factors, including landscape, food sources, and anthropogenic factors, were noted in 2016 after which otter populations fully recovered. Population development stabilized while exhibiting an overall high association with environmental factors. The results of the diffusion kernel method and data variation according to the Geo-SOM consistently presented substantial change in population dispersal (i.e. the merge of two subpopulations, and complete associations between spraint and environmental factors). The combination of the diffusion kernel method and Geo-SOM was effective in portraying temporal changes in population states in association with environmental factors based on spra int data in the last phase of full recovery.

Keywords: association environmental; environmental factors; otter; kernel method; diffusion kernel

Journal Title: Journal of Environmental Informatics
Year Published: 2020

Link to full text (if available)


Share on Social Media:                               Sign Up to like & get
recommendations!

Related content

More Information              News              Social Media              Video              Recommended



                Click one of the above tabs to view related content.