SPEDInstabR: An algorithm based on a fluctuation index for selecting predictors in species distribution modeling

Guisande, Cástor; García‐Roselló, Emilio; Heine, Jürgen; González‐Dacosta, Jacinto; Vilas, Luis González; Pérez, Baltasar J. García; Lobo, Jorge M.

doi:10.1016/j.ecoinf.2016.11.004

Cited by 31 publications

(22 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For SDMs, virtual species were already used in several instances (see Miller, 2014 for examples of recent applications) to validate proposed methods (e.g. Zurell et al, 2016;Guisande et al, 2017;Hattab et al, 2017), but also to test the effects of observation errors on model performance and the efficiency of currently used evaluation metrics (Fernandes et al, in press), to test different approaches to sample species data (Hirzel & Guisan, 2002), to test different downscaling methods (Bombi & D'Amen, 2012) or to assess the effectiveness of different hierarchical modelling frameworks when compared to more traditional methods (Fernandes et al, unplub.). Other potential uses worth exploring might include the testing of methods or software used for spatial conservation planning (e.g.…”

Section: A Critical Assessment Of Our Framework and How To Go Forwardmentioning

confidence: 99%

How much should one sample to accurately predict the distribution of species assemblages? A virtual community approach

Fernandes

Scherrer

Guisan

2018

Ecological Informatics

View full text Add to dashboard Cite

Correlative species distribution models (SDMs) are widely used to predict species distributions and assemblages, with many fundamental and applied uses. Different factors were shown to affect SDM prediction accuracy. However, real data cannot give unambiguous answers on these issues, and for this reason, artificial data have been increasingly used in recent years. Here, we move one step further by assessing how different factors can affect the prediction accuracy of virtual assemblages obtained by stacking individual SDM predictions (stacked SDMs, S-SDM). We modelled 100 virtual species in a real study area, testing five different factors: sample size (200-800-3200), sampling method (nested, non-nested), sampling prevalence (25%, 50%, 75% and species true prevalence), modelling technique (GAM, GLM, BRT and RF) and thresholding method (ROC, MaxTSS, and MaxKappa). We showed that the accuracy of S-SDM predictions is mostly affected by modelling technique followed by sample size. Models fitted by GAM/GLM had a higher accuracy and lower variance than BRT/RF. Model accuracy increased with sample size and a sampling strategy reflecting the true prevalence of the species was most successful. However, even with sample sizes as high as >3000 sites, residual uncertainty remained in the predictions, potentially reflecting a bias introduced by creating and/or resampling the virtual species. Therefore, when evaluating the accuracy of predictions from S-SDMs fitted with real field data, one can hardly expect reaching perfect accuracy, and reasonably high values of similarity or predictive success can already be seen as valuable predictions. We recommend the use of a 'plot-like' sampling method (best approximation of the species' true prevalence) and not simply increasing the number of presences-absences of species. As presented here, virtual simulations might be used more systematically in future studies to inform about the best accuracy level that one could expect given the characteristics of the data and the methods used to fit and stack SDMs.

show abstract

Section: A Critical Assessment Of Our Framework and How To Go Forwardmentioning

confidence: 99%

How much should one sample to accurately predict the distribution of species assemblages? A virtual community approach

Fernandes

Scherrer

Guisan

2018

Ecological Informatics

View full text Add to dashboard Cite

show abstract

“…VIF values higher than 30 (default) are considered as those indicating high collinearity among the explanatory variables, but this VIF value can be modified by the user at convenience. The selected predictors were subsequently submitted to a recently proposed Instability Index (Guisande 2016, Guisande et al 2017) that does not require normalized data. Dividing each predictor into a number of intervals or bins decided by the user, the number of records in each bin was calculated considering separately the cells where the species occurs and those of the selected studied area.…”

Section: The Noo Approachmentioning

confidence: 99%

“…A peak of instability is observed when there are important differences in the predictor comparing the bins of presence with the corresponding ones of the study area. This index outperforms other methods proposed to identify the most appropriate environmental factors (Guisande et al 2017, Fan et al 2018. The explanatory variables with a higher percentage of contribution to the instability index are assumed to be those that most affect the distribution of the species in the accessible area or GE.…”

Section: The Noo Approachmentioning

confidence: 99%

A simple method to estimate the probable distribution of species

et al. 2019

Self Cite

View full text Add to dashboard Cite

Species distribution models (SDMs) are broadly used to predict species distributions from available presence data. However, SDMs results have been criticized for several reasons mainly related to two basic characteristics of most SDMs: 1) general lack of reliable species absence information, 2) the frequent use of an arbitrary geographical extent (GE) or accessible area of the species. These impediments have motivated us to generate a procedure called niche of occurrence (NOO). NOO provides the probable distribution of species (realized niche) relying solely on partial information about presence of species. It operates within a natural geographical extent delimited by available observations and avoids using misleading thresholds to obtain binary presence–absence estimations when the species prevalence is unknown. In this study the main characteristics of NOO are presented, comparing its performance with other recognized and more complex SDMs by using virtual species to avoid the omnipresent error sources of real data sets.

show abstract

“…Aragón et al ., ; Pertierra et al ., ). Finally, a newly released algorithm based on fluctuation index (FI, Guisande et al ., ) offers an additional alternative.…”

Section: Introductionmentioning

confidence: 99%

What are the best predictors for invasive potential of weeds? Transferability evaluations of model predictions based on diverse environmental data sets for Flaveria bidentis

Fan

Zhao

et al. 2018

Weed Research

View full text Add to dashboard Cite

Ecological niche models are widely used in the study of weed invasions, yet best approaches for selecting ecologically relevant environmental predictors for weeds remain unresolved. Here, we evaluate niche model transferability based on diverse environmental data sets for an invasive herb, Flaveria bidentis. This species is native to South America, but has established populations in China that pose a threat to agriculture and animal husbandry. Relevant environmental data sets were selected via five statistical approaches: permutation importance (PI) and jackknife test (JK) in Maxent, variable importance identified by boosting regression trees (BRT), ecological niche factor analysis (ENFA) and a newly released algorithm based on a fluctuation index (FI). Climate spaces occupied by native South American and introduced Chinese populations were compared based on these environmental data sets. Native niche model predictions in China were compared across environmental data sets and model settings (i.e. default versus fine-tuned Maxent settings). Results suggest that native and introduced populations occupy two distinct climate spaces, but that this divergence likely results from background effects. Niche models based on fine-tuned Maxent settings generally showed better discrimination ability than those based on default settings. The best model discrimination in China was attained in the FI model using fine-tuned settings, followed by the BRT model on default settings. The best models suggest that highly suitable areas at risk of invasion in China are to the west and north-east of present distributional areas. Results presented here provide predictions for F. bidentis in particular, but also shed light on procedures for selecting ecologically relevant predictors for invasive species distributional predictions more generally.

show abstract

SPEDInstabR: An algorithm based on a fluctuation index for selecting predictors in species distribution modeling

Cited by 31 publications

References 24 publications

How much should one sample to accurately predict the distribution of species assemblages? A virtual community approach

How much should one sample to accurately predict the distribution of species assemblages? A virtual community approach

A simple method to estimate the probable distribution of species

What are the best predictors for invasive potential of weeds? Transferability evaluations of model predictions based on diverse environmental data sets for Flaveria bidentis

Contact Info

Product

Resources

About