Identifying appropriate spatial scales of predictors in species distribution models with the random forest algorithm

Bradter, Ute; Kunin, William E.; Altringham, John D.; Thom, Tim; Benton, Tim G.

doi:10.1111/j.2041-210x.2012.00253.x

Cited by 102 publications

(80 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Selection of scales for the variables included in the multi-scale models Selection of variables for the multi-scale models was applied as proposed by Bradter et al (2013). This preceding reduction of variables was selected to prevent inclusion of several variables at neighbouring scales that are often highly correlated with each other (Figure 1).…”

Section: Statistical Analysesmentioning

confidence: 99%

“…If significant, these eigenvectors were added to the model and included in the model averaging procedure. Furthermore, as recommended by Bradter et al (2013), we applied Moran eigenvector filtering for all multi-scale models selected with random forest variable selection (Dray et al, 2006;Griffith and Peres-Neto, 2006). Spatial eigenvectors were added until residual spatial autocorrelation was no longer significant at the P=0.05 level.…”

Section: Spatial Autocorrelationmentioning

confidence: 99%

“…Therefore, but for multi-scale models only, we used a second modelling approach based on random forests for the variable selection, which was found to be robust even if the number of response data is generally small in comparison to the number of predictors (Strobl et al, 2007). This variable selection method was applied as described in detail by Bradter et al (2013). In the random forest approach, several classification or regression trees are built from random subsets of the dataset (Breiman, 2001;Liaw and Wiener, 2002).…”

Section: Multi-scale Models With Random Forest Variable Selectionmentioning

confidence: 99%

“…However, as previously shown (Hamer and Hill, 2000), the selection of the spatial scales affects the outcome of the modelling, e.g. decrease the variance explained or bias regression coefficients, which might result in wrong conclusions and interpretations (reviewed by Bradter et al, 2013). Therefore, a selection of the appropriate scale is important to allow accurate species distribution modelling.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, a selection of the appropriate scale is important to allow accurate species distribution modelling. Furthermore, as generally described by Bradter et al (2013), species distribution can also be affected by land cover variables at multiple scales, e.g. if breeding sites, resting sites, and hosts of Culicoides biting midges are distributed over several scales.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Comparison of single- and multi-scale models for the prediction of the Culicoides biting midge distribution in Germany

et al. 2016

View full text Add to dashboard Cite

This study analysed Culicoides presence-absence data from 46 sampling sites in Germany, where monitoring was carried out from April 2007 until May 2008. Culicoides presence-absence data were analysed in relation to land cover data, in order to study whether the prevalence of biting midges is correlated to land cover data with respect to the trapping sites. We differentiated eight scales, i.e. buffer zones with radii of 0.5, 1, 2, 3, 4, 5, 7.5 and 10 km, around each site, and chose several land cover variables. For each species, we built eight single-scale models (i.e. predictor variables from one of the eight scales for each model) based on averaged, generalised linear models and two multiscale models (i.e. predictor variables from all of the eight scales) based on averaged, generalised linear models and generalised linear models with random forest variable selection. There were no significant differences between performance indicators of models built with land cover data from different buffer zones around the trapping sites. However, the overall performance of multi-scale models was higher than the alternatives. Furthermore, these models mostly achieved the best performance for the different species using the index area under the receiver operating characteristic curve. However, as also presented in this study, the relevance of the different variables could significantly differ between various scales, including the number of species affected and the positive or negative direction. This is an even more severe problem if multi-scale models are concerned, in which one model can have the same variable at different scales but with different directions, i.e. negative and positive direction of the same variable at different scales. However, multi-scale modelling is a promising approach to model the distribution of Culicoides species, accounting much more for the ecology of biting midges, which uses different resources (breeding sites, hosts, etc.) at different scales.

show abstract

Section: Statistical Analysesmentioning

confidence: 99%

Section: Spatial Autocorrelationmentioning

confidence: 99%

Section: Multi-scale Models With Random Forest Variable Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Comparison of single- and multi-scale models for the prediction of the Culicoides biting midge distribution in Germany

et al. 2016

View full text Add to dashboard Cite

show abstract

Application of Artificial Intelligence and Machine Learning Techniques in Island Detection in a Smart Grid

Dutta¹,

Sadhu²,

Cherikuri³

et al. 2021

Intelligent Renewable Energy Systems

View full text Add to dashboard Cite

Occurrence of lemurs in landscapes and their species‐specific scale responses to habitat loss

Steffens

Malabet

Lehman

2020

American J Primatol

View full text Add to dashboard Cite

Studies on the impact of habitat loss on species occurrence consistently find that the amount of habitat (measured as patch area) is a major determinant of species occurrence at a patch-level. However, patch-level research may fail to detect important patterns and processes only observable at a landscape-level. A landscapelevel approach that incorporates species-specific scale responses is needed to better understand what drives species occurrence. Our aim was to determine the landscape-level scale of effect of habitat amount on the occurrence of three species of nocturnal lemurs (Cheirogaleus medius, Microcebus murinus, and M. ravelobensis).We surveyed line transects to determine the occurrence of three lemur species within a fragmented landscape of deciduous dry forest and anthropogenic grassland in northwestern Madagascar. To determine the scale of effect of habitat loss on lemur occurrence, we compared logistic regression models of occurrence against habitat amount among eight different landscape scales using Akaike's Information Criterion values. We found differing scale responses among the lemurs in our study.Occurrence of C. medius responded to habitat amount at scales between 0.5-4 ha, M. murinus at scales between 1 and 4 ha and M. ravelobensis at scales between 0.125 and 4 ha. We suggest that the scale of effect for C. medius is mediated by their ability to hibernate. A relatively lower scale-response for Microcebus spp. likely reflect their omnivorous diet, small habitat requirements, and limited dispersal ability. Differences in scale responses between M. murinus and M. ravelobensis are likely a result of differing dispersal ability and responses to edge effects between these species. Our study is among the first on lemurs to show the value of a landscape-level approach when assessing the effects of habitat loss on species occurrence. K E Y W O R D S arboreal, biogeography, fragments, Madagascar, primate

show abstract

Identifying appropriate spatial scales of predictors in species distribution models with the random forest algorithm

Cited by 102 publications

References 44 publications

Comparison of single- and multi-scale models for the prediction of the Culicoides biting midge distribution in Germany

Comparison of single- and multi-scale models for the prediction of the Culicoides biting midge distribution in Germany

Application of Artificial Intelligence and Machine Learning Techniques in Island Detection in a Smart Grid

Occurrence of lemurs in landscapes and their species‐specific scale responses to habitat loss

Contact Info

Product

Resources

About