Comparing species distribution models constructed with different subsets of environmental predictors

2014 ◽  
Vol 21 (1) ◽  
pp. 23-35 ◽  
Author(s):  
David N. Bucklin ◽  
Mathieu Basille ◽  
Allison M. Benscoter ◽  
Laura A. Brandt ◽  
Frank J. Mazzotti ◽  
...  
Keyword(s):  
Species Distribution ◽  
Species Distribution Models ◽  
Environmental Predictors ◽  
Distribution Models

scholarly journals Bounding species distribution models

2011 ◽  
Vol 57 (5) ◽  
pp. 642-647 ◽  
Author(s):  
Thomas J. Stohlgren ◽  
Catherine S. Jarnevich ◽  
Wayne E. Esaias ◽  
Jeffrey T. Morisette
Keyword(s):  
Species Distribution ◽  
Honey Bees ◽  
Best Practice ◽  
Species Distribution Models ◽  
Regression Tree ◽  
Classification And Regression Tree ◽  
Suitable Habitat ◽  
Environmental Predictors ◽  
Distribution Models ◽  
Africanized Honey Bees

Abstract Species distribution models are increasing in popularity for mapping suitable habitat for species of management concern. Many investigators now recognize that extrapolations of these models with geographic information systems (GIS) might be sensitive to the environmental bounds of the data used in their development, yet there is no recommended best practice for “clamping” model extrapolations. We relied on two commonly used modeling approaches: classification and regression tree (CART) and maximum entropy (Maxent) models, and we tested a simple alteration of the model extrapolations, bounding extrapolations to the maximum and minimum values of primary environmental predictors, to provide a more realistic map of suitable habitat of hybridized Africanized honey bees in the southwestern United States. Findings suggest that multiple models of bounding, and the most conservative bounding of species distribution models, like those presented here, should probably replace the unbounded or loosely bounded techniques currently used.

scholarly journals Evaluating species distribution models with discrimination accuracy is uninformative for many applications

2019 ◽  
Author(s):  
Dan L. Warren ◽  
Nicholas J. Matzke ◽  
Teresa L. Iglesias
Keyword(s):  
Species Distribution ◽  
Species Distribution Models ◽  
Current Approach ◽  
Data Partitioning ◽  
Empirical Modeling ◽  
Environmental Predictors ◽  
Discrimination Accuracy ◽  
Distribution Models ◽  
Ecological Processes ◽  
Occurrence Data

AbstractAimSpecies distribution models are used across evolution, ecology, conservation, and epidemiology to make critical decisions and study biological phenomena, often in cases where experimental approaches are intractable. Choices regarding optimal models, methods, and data are typically made based on discrimination accuracy: a model’s ability to predict subsets of species occurrence data that were withheld during model construction. However, empirical applications of these models often involve making biological inferences based on continuous estimates of relative habitat suitability as a function of environmental predictor variables. We term the reliability of these biological inferences “functional accuracy.” We explore the link between discrimination accuracy and functional accuracy.MethodsUsing a simulation approach we investigate whether models that make good predictions of species distributions correctly infer the underlying relationship between environmental predictors and the suitability of habitat.ResultsWe demonstrate that discrimination accuracy is only informative when models are simple and similar in structure to the true niche, or when data partitioning is geographically structured. However, the utility of discrimination accuracy for selecting models with high functional accuracy was low in all cases.Main conclusionsThese results suggest that many empirical studies and decisions are based on criteria that are unrelated to models’ usefulness for their intended purpose. We argue that empirical modeling studies need to place significantly more emphasis on biological insight into the plausibility of models, and that the current approach of maximizing discrimination accuracy at the expense of other considerations is detrimental to both the empirical and methodological literature in this active field. Finally, we argue that future development of the field must include an increased emphasis on simulation; methodological studies based on ability to predict withheld occurrence data may be largely uninformative about best practices for applications where interpretation of models relies on estimating ecological processes, and will unduly penalize more biologically informative modeling approaches.

scholarly journals Simple is sometimes better: a test of the transferability of species distribution models

2020 ◽  
Vol 77 (5) ◽  
pp. 1752-1761
Author(s):  
Danielle E Haulsee ◽  
Matthew W Breece ◽  
Dewayne A Fox ◽  
Matthew J Oliver
Keyword(s):  
Species Distribution ◽  
Mixed Model ◽  
Species Distribution Models ◽  
Autonomous Underwater Vehicle ◽  
Spatial Scales ◽  
Test Model ◽  
Atlantic Sturgeon ◽  
Environmental Predictors ◽  
Distribution Models ◽  
New Locations

Abstract Species distribution models (SDMs) are often empirically developed on spatially and temporally biased samples and then applied over much larger spatial scales to test ecological hypotheses or to inform management. Underlying this approach is the assumption that the statistical relationships between species observations and environmental predictors are applicable to other locations and times. However, testing and quantifying the transferability of these models to new locations and times can be a challenge for resource managers because of the technical difficulty in obtaining species observations in new locations in a dynamic environment. Here, we apply two SDMs developed in the Mid-Atlantic Bight for Atlantic sturgeon (Acipenser oxyrhynchus oxyrhynchus) to the South Atlantic Bight and use an autonomous underwater vehicle to test model predictions. We compare Atlantic sturgeon occurrence to two SDMs: one associating sturgeon occurrence with simple seascapes and one developed through coupling occurrences with environmental predictors in a generalized additive mixed model (GAMM). Our analysis showed that the seascape model was transferable across these disparate regions; however, the complex GAMM was not. The association of the imperilled Atlantic sturgeon with simple seascapes allows managers to easily integrate this remotely sensed dynamic oceanographic product into future ecosystem-based management strategies.

scholarly journals Continent-Wide Tree Species Distribution Models May Mislead Regional Management Decisions: A Case Study in the Transboundary Biosphere Reserve Mura-Drava-Danube

Forests ◽  
2021 ◽  
Vol 12 (3) ◽  
pp. 330
Author(s):  
Markus Sallmannshofer ◽  
Debojyoti Chakraborty ◽  
Harald Vacik ◽  
Gábor Illés ◽  
Markus Löw ◽  
...  
Keyword(s):  
Species Distribution ◽  
Tree Species ◽  
Large Scale ◽  
Species Distribution Models ◽  
Riparian Forest ◽  
Forest Composition ◽  
Occurrence Probability ◽  
Environmental Predictors ◽  
Distribution Models ◽  
Bioclimatic Variables

The understanding of spatial distribution patterns of native riparian tree species in Europe lacks accurate species distribution models (SDMs), since riparian forest habitats have a limited spatial extent and are strongly related to the associated watercourses, which needs to be represented in the environmental predictors. However, SDMs are urgently needed for adapting forest management to climate change, as well as for conservation and restoration of riparian forest ecosystems. For such an operative use, standard large-scale bioclimatic models alone are too coarse and frequently exclude relevant predictors. In this study, we compare a bioclimatic continent-wide model and a regional model based on climate, soil, and river data for central to south-eastern Europe, targeting seven riparian foundation species—Alnus glutinosa, Fraxinus angustifolia, F. excelsior, Populus nigra, Quercus robur, Ulmus laevis, and U. minor. The results emphasize the high importance of precise occurrence data and environmental predictors. Soil predictors were more important than bioclimatic variables, and river variables were partly of the same importance. In both models, five of the seven species were found to decrease in terms of future occurrence probability within the study area, whereas the results for two species were ambiguous. Nevertheless, both models predicted a dangerous loss of occurrence probability for economically and ecologically important tree species, likely leading to significant effects on forest composition and structure, as well as on provided ecosystem services.

scholarly journals A Robust Prediction Model for Species Distribution Using Bagging Ensembles with Deep Neural Networks

2021 ◽  
Vol 13 (8) ◽  
pp. 1495
Author(s):  
Jehyeok Rew ◽  
Yongjang Cho ◽  
Eenjun Hwang
Keyword(s):  
Neural Networks ◽  
Species Distribution ◽  
Best Practice ◽  
Deep Neural Networks ◽  
Species Distribution Models ◽  
Species Distribution Model ◽  
Environmental Data ◽  
Distribution Model ◽  
Distribution Models ◽  
Robust Prediction

Species distribution models have been used for various purposes, such as conserving species, discovering potential habitats, and obtaining evolutionary insights by predicting species occurrence. Many statistical and machine-learning-based approaches have been proposed to construct effective species distribution models, but with limited success due to spatial biases in presences and imbalanced presence-absences. We propose a novel species distribution model to address these problems based on bootstrap aggregating (bagging) ensembles of deep neural networks (DNNs). We first generate bootstraps considering presence-absence data on spatial balance to alleviate the bias problem. Then we construct DNNs using environmental data from presence and absence locations, and finally combine these into an ensemble model using three voting methods to improve prediction accuracy. Extensive experiments verified the proposed model’s effectiveness for species in South Korea using crowdsourced observations that have spatial biases. The proposed model achieved more accurate and robust prediction results than the current best practice models.

Sign in / Sign up

Export Citation Format

Share Document