Shrubby cinquefoil Dasiphora fruticosa L. Rydb. mapping in Northwestern Estonia based upon site similaritiesReportar como inadecuado




Shrubby cinquefoil Dasiphora fruticosa L. Rydb. mapping in Northwestern Estonia based upon site similarities - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

BMC Ecology

, 17:7

Theoretical ecology and models

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 km 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.

KeywordsDasiphora fruticosa Similarity-based reasoning Species distribution mapping Gower’s distance metric AbbreviationsConstuda software system for similarity-based reasoning developed at the University of Tartu

GPSGlobal Positioning System

MLmachine learning; in Constud software used in this project—iterative optimization of feature and case weights

RMSEroot mean squared error, the standard deviation of differences between observed and predicted values

SQL Servera relational database management system developed by Microsoft

Download fulltext PDF



Autor: Kalle Remm - Liina Remm

Fuente: https://link.springer.com/







Documentos relacionados