Premium
Detecting outliers in species distribution data
Author(s) -
Liu Canran,
White Matt,
Newell Graeme
Publication year - 2018
Publication title -
journal of biogeography
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.7
H-Index - 158
eISSN - 1365-2699
pISSN - 0305-0270
DOI - 10.1111/jbi.13122
Subject(s) - outlier , computer science , species distribution , environmental niche modelling , data quality , support vector machine , data mining , anomaly detection , range (aeronautics) , spatial analysis , random forest , ecology , geography , machine learning , remote sensing , artificial intelligence , biology , ecological niche , metric (unit) , operations management , materials science , habitat , economics , composite material
Abstract Aim Species distribution data play a pivotal role in the study of ecology, evolution, biogeography and biodiversity conservation. Although large amounts of location data are available and accessible from public databases, data quality remains problematic. Of the potential sources of error, positional errors are critical for spatial applications, particularly where these errors place observations beyond the environmental or geographical range of species. These outliers need to be identified, checked and removed to improve data quality and minimize the impact on subsequent analyses. Manually checking all species records within large multispecies datasets is prohibitively costly. This work investigates algorithms that may assist in the efficient vetting of outliers in such large datasets. Location We used real, spatially explicit environmental data derived from the western part of Victoria, Australia, and simulated species distributions within this same region. Methods By adapting species distribution modelling ( SDM ), we developed a pseudo‐ SDM approach for detecting outliers in species distribution data, which was implemented with random forest ( RF ) and support vector machine ( SVM ) resulting in two new methods: RF _pd SDM and SVM _pd SDM . Using virtual species, we compared eight existing multivariate outlier detection methods with these two new methods under various conditions. Results The two new methods based on the pseudo‐ SDM approach had higher true skill statistic ( TSS ) values than other approaches, with TSS values always exceeding 0. More than 70% of the true outliers in datasets for species with a low and intermediate prevalence can be identified by checking 10% of the data points with the highest outlier scores. Main conclusions Pseudo‐ SDM ‐based methods were more effective than other outlier detection methods. However, this outlier detection procedure can only be considered as a screening tool, and putative outliers must be examined by experts to determine whether they are actual errors or important records within an inherently biased set of data.