GLOSSA: A user-friendly R Shiny application for Bayesian machine learning analysis of marine species distribution

Abstract

[EN] Species distribution models (SDMs) are one of the most common statistical methods to assess species occupancy and geographic distribution patterns. With the increasing complexity and availability of ecological data in the marine context, many methodological approaches have been developed to support SDM analysis. However, their application often requires expertise in data analysis, statistical modelling and programming, which limits their accessibility for broader use. Here we introduce GLOSSA, an open-source R package and Shiny application designed to make marine species distribution modelling more accessible. GLOSSA provides a user-friendly interface for fitting Bayesian Additive Regression Trees (BART) SDMs using species occurrence and environmental data. GLOSSA guides users through key SDM steps, including data uploading, filtering occurrence data, harmonizing environmental layers, generating pseudo-absences, tuning BART complexity, performing spatial and temporal block cross-validation, visualizing predictions and uncertainty and exporting configuration files to ensure reproducibility. We demonstrate the functionality of GLOSSA through three marine case studies, addressing a range of ecological scenarios at regional and global scales. Along with detailed documentation, examples and tutorials, GLOSSA provides an example of how an intuitive graphical interface can make species distribution modelling accessible to a broad audience.