User-Friendly 'shiny' App for Bayesian Species Distribution Models
Enlarge/Buffer a Polygon
Clean Coordinates of Presence/Absence Data
Continuous Boyce Index (CBI) with weighting
Create Geographic Coordinate Layers
Cross-validation for BART model
Create a Download Action Button
Evaluation metrics for model predictions
Server Logic for Export Plot Functionality
Create UI for Export Plot Button
Extract Non-NA Covariate Values
Server-side Logic for Custom File Input
Custom File Input UI
Fit a BART Model Using Environmental Covariate Layers
Generate cross-validation folds
Generate Pseudo-Absences Using Buffer-Out Strategy
Generate Environmental-space Pseudo-Absences via flexsdm (per temporal...
Generate Random Pseudo-Absences
Generate Pseudo-Absences Using Target-Group Background
Generate Prediction Plot
Generate Pseudo-Absence Points Using Different Methods Based on Presen...
Get Covariate Names
Compute specificity and sensitivity
Main Analysis Function for GLOSSA Package
Export Glossa Model Results
Invert a Polygon
Apply Polygon Mask to Raster Layers
Misclassification Error
Compute the optimal probability cutoff score
Optimal Cutoff for Presence-Absence Prediction
Plot cross-validation fold assignments
Plot cross-validation metrics
Make Predictions Using a BART Model
Read and Validate Extent Polygon
Load Covariate Layers from ZIP Files
Read and validate presences/absences CSV file
Remove Duplicated Points from a Dataframe
Remove Points Inside or Outside a Polygon
Calculate Response Curve Using BART Model
Run GLOSSA Shiny App
Calculate the sensitivity for a given logit model
Create a Sparkline Value Box
Calculate the specificity for a given logit model
Validate Fit and Projection Layers
Validate Layers Zip
Validate Match Between Presence/Absence Files and Fit Layers
Variable Importance in BART Model
Calculate Youden's index
A user-friendly 'shiny' application for Bayesian machine learning analysis of marine species distributions. GLOSSA (Global Ocean Species Spatio-temporal Analysis) uses Bayesian Additive Regression Trees (BART; Chipman, George, and McCulloch (2010) <doi:10.1214/09-AOAS285>) to model species distributions with intuitive workflows for data upload, processing, model fitting, and result visualization. It supports presence-absence and presence-only data (with pseudo-absence generation), spatial thinning, cross-validation, and scenario-based projections. GLOSSA is designed to facilitate ecological research by providing easy-to-use tools for analyzing and visualizing marine species distributions across different spatial and temporal scales. Optionally, pseudo-absences can be generated within the environmental space using the external package 'flexsdm' (not on CRAN), which can be downloaded from <https://github.com/sjevelazco/flexsdm>; this functionality is used conditionally when available and all core features work without it.
Useful links