Abstract
BackgroundDifferent methods have been used to map species and habitat distributions. In this paper, similarity-based reasoning—a methodological approach that has received less attention—was applied to estimate the distribution and coverage of Dasiphora fruticosa for the region in the Baltic states where grows the most abundant population of this species.MethodsField observations, after thinning to at least 50 m interval, included 1480 coverage estimations in the species presence locations and 8317 absence locations. Species coverage for the 750 km2 of directly unobserved area was calculated using machine learning in the similarity-based prediction system Constud. Separate predictive sets of site features (e.g. land cover, soil type) and exemplar weights were calibrated for spatial partitions of the study area (probable presence region, unclear region, proved absence region). A modified version of the Gower’s distance metric, as used in Constud, is described.ResultsThe resulting maps depicted the predicted coverage, the certainty of decision when predicting presence or absence, and the mean similarity to the exemplar locations used while predicting. Coverage prediction errors were smaller in the unclear partition—where the species was mostly absent—than in the probable presence partition, where coverage ranged from 0 to 90%.ConclusionsWe call for methodological comparisons using the same data set.
Highlights
Different methods have been used to map species and habitat distributions
The main result was the mapping of estimated D. fruticosa coverage in the study area (Fig. 8)
The predictive set selected by the machine learning included only features that described autocovariation regarding the distribution of D. fruticosa (Table 1); i.e. soil and land cover did not support considerably the recognition of species presence sites, when the features describing autocovariation had values
Summary
Different methods have been used to map species and habitat distributions. In this paper, similaritybased reasoning—a methodological approach that has received less attention—was applied to estimate the distribution and coverage of Dasiphora fruticosa for the region in the Baltic states where grows the most abundant population of this species. Detailed distribution data are needed in order to monitor changes in species’ distributions, for conservation, territorial planning, and species and habitat management, but it is impractical and expensive to conduct detailed field observations over large areas. The likelihood of a species being present or absent at unobserved locations can be predicted using a statistical model [1,2,3,4], or alternatively, according to similarity of exemplar sites [5]. Maps of a species estimated distribution are important for further monitoring efforts, since predictions help to identify areas in need of urgent future sampling [6, 7]. Similarity-based— known as case-based—reasoning is an alternative to statistical regression models and classification methods [8]. Casebased systems reuse previous experiences at a low level of generalisation, do not produce models based on generalized statistical relationships and can be continuously
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
