Journal: PeerJ

Article Title: EcoNicheS: enhancing ecological niche modeling, niche overlap and connectivity analysis using the shiny dashboard and R package

doi: 10.7717/peerj.19136

Figure Lengend Snippet: Overview of each module’s analyses, including relevant references and the corresponding R packages used.

Article Snippet: The plataform employs the biomod2 R package, a widely used ecological niche modeling framework that supports 12 correlative algorithms: generalized linear models (GLMs), generalized additive models (GAMs), generalized boosting models (often called boosted regression trees; GBM), classification tree analysis (CTA), artificial neural networks (ANNs), surface range envelopes or BIOCLIM (SRE), flexible discriminant analysis (FDA), multiple adaptive regression splines (MARS), random forest (RF), and maximum entropy (MAXENT) using the MIAmaxent ( ) R package MAXNET and extreme gradient boosting (XGBOOST) ( ).

Techniques: Sampling, Generated, Functional Assay

Journal: PeerJ

Article Title: EcoNicheS: enhancing ecological niche modeling, niche overlap and connectivity analysis using the shiny dashboard and R package

doi: 10.7717/peerj.19136

Figure Lengend Snippet: Comparison of analyses performed by different software packages for ecological niche modeling.

Article Snippet: The plataform employs the biomod2 R package, a widely used ecological niche modeling framework that supports 12 correlative algorithms: generalized linear models (GLMs), generalized additive models (GAMs), generalized boosting models (often called boosted regression trees; GBM), classification tree analysis (CTA), artificial neural networks (ANNs), surface range envelopes or BIOCLIM (SRE), flexible discriminant analysis (FDA), multiple adaptive regression splines (MARS), random forest (RF), and maximum entropy (MAXENT) using the MIAmaxent ( ) R package MAXNET and extreme gradient boosting (XGBOOST) ( ).

Techniques: Comparison, Software, Selection, Generated, Sampling

Journal: Journal of Economic Entomology

Article Title: Evaluating the establishment potential of cabbage stem flea beetle (Coleoptera: Chrysomelidae) and pollen beetle (Coleoptera: Nitidulidae) in canola-growing regions of North America using ensemble species distribution models

doi: 10.1093/jee/toaf071

Figure Lengend Snippet: Schematic illustrating methods used for constructing the weighted-means ensemble species distribution models (SDMs) predicting habitat suitability for cabbage stem flea beetle, Psylliodes chrysocephala , and pollen beetle, Brassicogethes viridescens . Models were created using biomod2 version 4.2-6-1 ( , ) in RStudio version 2022.12.0 + 353 (R version 4.2.1; , ) and evaluated using True Skill Statistic (TSS; ) values and area under the curve (AUC) values of the receiver operating characteristic (ROC) curve . See “Materials and Methods” section in the main text for additional details on species occurrence [presence-only (PO)] and pseudo-absence (PA) data, environmental predictor variable selection, model development, training, and evaluation, and sensitivity (i.e., uncertainty) and variable importance analysis.

Article Snippet: The package biomod2 version 4.2-6-1 ( , ) within RStudio version 2022.12.0 + 353 (R version 4.2.1; , ) was used to develop SDMs for P. chrysocephala and B. viridescens , implementing the selected algorithms: Generalized Linear Model (GLM; ), Boosted Regression Trees (i.e., Generalized Boosting Model, GBM; , ), Random Forest (RF; ), Classification Tree Analysis (CTA; ), Maximum Entropy [MAXNET; an alternative implementation of MAXENT ( )], and eXtreme Gradient Boosting Training (XGBOOST; ).

Techniques: Selection