glossa1.2.4 package

User-Friendly 'shiny' App for Bayesian Species Distribution Models

buffer_polygon

Enlarge/Buffer a Polygon

clean_coordinates

Clean Coordinates of Presence/Absence Data

contBoyce

Continuous Boyce Index (CBI) with weighting

create_coords_layer

Create Geographic Coordinate Layers

cross_validate_model

Cross-validation for BART model

downloadActionButton

Create a Download Action Button

evaluation_metrics

Evaluation metrics for model predictions

export_plot_server

Server Logic for Export Plot Functionality

export_plot_ui

Create UI for Export Plot Button

extract_noNA_cov_values

Extract Non-NA Covariate Values

file_input_area_server

Server-side Logic for Custom File Input

file_input_area_ui

Custom File Input UI

fit_bart_model

Fit a BART Model Using Environmental Covariate Layers

generate_cv_folds

Generate cross-validation folds

generate_pa_buffer_out

Generate Pseudo-Absences Using Buffer-Out Strategy

generate_pa_env_space_flexsdm

Generate Environmental-space Pseudo-Absences via flexsdm (per temporal...

generate_pa_random

Generate Random Pseudo-Absences

generate_pa_target_group

Generate Pseudo-Absences Using Target-Group Background

generate_prediction_plot

Generate Prediction Plot

generate_pseudo_absences

Generate Pseudo-Absence Points Using Different Methods Based on Presen...

get_covariate_names

Get Covariate Names

getFprTpr

Compute specificity and sensitivity

glossa_analysis

Main Analysis Function for GLOSSA Package

glossa_export

Export Glossa Model Results

invert_polygon

Invert a Polygon

layer_mask

Apply Polygon Mask to Raster Layers

misClassError

Misclassification Error

optimalCutoff

Compute the optimal probability cutoff score

pa_optimal_cutoff

Optimal Cutoff for Presence-Absence Prediction

plot_cv_folds_points

Plot cross-validation fold assignments

plot_cv_metrics

Plot cross-validation metrics

predict_bart

Make Predictions Using a BART Model

read_extent_polygon

Read and Validate Extent Polygon

read_layers_zip

Load Covariate Layers from ZIP Files

read_presences_absences_csv

Read and validate presences/absences CSV file

remove_duplicate_points

Remove Duplicated Points from a Dataframe

remove_points_polygon

Remove Points Inside or Outside a Polygon

response_curve_bart

Calculate Response Curve Using BART Model

run_glossa

Run GLOSSA Shiny App

sensitivity

Calculate the sensitivity for a given logit model

sparkvalueBox

Create a Sparkline Value Box

specificity

Calculate the specificity for a given logit model

validate_fit_projection_layers

Validate Fit and Projection Layers

validate_layers_zip

Validate Layers Zip

validate_pa_fit_time

Validate Match Between Presence/Absence Files and Fit Layers

variable_importance

Variable Importance in BART Model

youdensIndex

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.

  • Maintainer: Jorge Mestre-Tomás
  • License: GPL-3
  • Last published: 2025-09-19