FN Archimer Export Format PT J TI dsmextra: Extrapolation assessment tools for density surface models BT AF Bouchet, PJ Miller, DL Roberts, JJ Mannocci, Laura Harris, CM Thomas, L AS 1:1,2;2:1,2;3:3;4:4;5:1,5;6:1,2; FF 1:;2:;3:;4:;5:;6:; C1 Centre for Research into Ecological and Environmental Modelling (CREEM) University of St Andrews St Andrews Fife ,Scotland School of Mathematics and Statistics University of St Andrews St Andrews Fife ,Scotland Marine Geospatial Ecology Lab, Duke University Durham North Carolina ,USA MARBEC (Marine BiodiversityExploitation and Conservation), University of Montpellier, CNRS, Ifremer, IRD Sète ,France School of Biology, University of St Andrews St Andrews Fife , Scotland C2 UNIV ST ANDREWS, UK UNIV ST ANDREWS, UK UNIV DUKE, USA IRD, FRANCE UNIV ST ANDREWS, UK UM MARBEC IN WOS Cotutelle UMR copubli-europe copubli-int-hors-europe IF 5.093 TC 32 UR https://archimer.ifremer.fr/doc/00643/75485/76332.pdf https://archimer.ifremer.fr/doc/00643/75485/76333.pdf https://archimer.ifremer.fr/doc/00643/75485/76334.r LA English DT Article DE ;cetaceans;distance sampling;ecological predictions;extrapolation;model transferability;R package;spatial modelling;wildlife surveys AB Forecasting the responses of biodiversity to global change has never been more important. However, many ecologists faced with limited sample sizes and shoestring budgets often resort to extrapolating predictive models beyond the range of their data to support management actions in data‐deficient contexts. This can lead to error‐prone inference that has the potential to misdirect conservation interventions and undermine decision‐making. Despite the perils associated with extrapolation, little guidance exists on the best way to identify it when it occurs, leaving users questioning how much credence they should place in model outputs. To address this, we present dsmextra, a new R package for measuring, summarising, and visualising extrapolation in multivariate environmental space. dsmextra automates the process of conducting quantitative, spatially‐explicit assessments of extrapolation on the basis of two established metrics: the Extrapolation Detection (ExDet) tool, and the percentage of data nearby (%N). The package provides user‐friendly functions to (a) calculate these metrics, (b) create tabular and graphical summaries, (c) explore combinations of covariate sets as a means of informing covariate selection, and (d) produce visual displays in the form of interactive html maps. dsmextra implements a model‐agnostic approach to extrapolation detection that is applicable across taxonomic groups, modelling techniques, and datasets. We present a case study fitting a density surface model to visual detections of pantropical spotted dolphins (Stenella attenuata) in the Gulf of Mexico. Predictive modelling seeks to deliver actionable information about the states and trajectories of ecological systems, yet model performance can be strongly impaired out‐of‐sample. By assessing conditions under which models are likely to fail or succeed in extrapolating, ecologists are likely to gain a better understanding of biological patterns and their underlying drivers. Critical to this is a concerted effort to standardise best practice in model evaluation, with an emphasis on extrapolative capacity. PY 2020 PD NOV SO Methods In Ecology And Evolution SN 2041-210X PU Wiley VL 11 IS 11 UT 000571593200001 BP 1464 EP 1469 DI 10.1111/2041-210X.13469 ID 75485 ER EF