Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 1
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

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

  • Mestre-Tomás, Jorge
  • Fuster-Alonso, Alba
  • Bellido, José M.
  • Coll, Marta
[Data availability statement] GLOSSA is developed openly on GitHub (https://github.com/iMARES-group/glossa), with releases archived on Zenodo (https://doi.org/10.5281/zenodo.17161715; Mestre-Tomás et al., 2025a). The R package glossa is also available via the Comprehensive R Archive Network (CRAN; https://cran.r-project.org/package=glossa). Documentation is available at https://imares-group.github.io/glossa/. Data and code used in the examples are available on Zenodo (https://doi.org/10.5281/zenodo.17177436; Mestre-Tomás et al., 2025b). Occurrence data for Thunnus albacares are available from OBIS (https://obis.org/taxon/127027; OBIS, 2025), for Caretta caretta from GBIF (https://doi.org/10.15468/dl.es7562; GBIF.org, 2024) and for Siganus luridus from the GreekMarineICAS geodataset (https://doi.org/10.25607/t2smha; Sini et al., 2024)., Special Feature: Conservation, Ecology and Artificial Intelligence — Advances and Symbiotic Solutions, 1. 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., 2. 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., 3. 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., 4. 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., We would like to thank the iMARES group for their helpful feedback on the app design. This study is part of the ProOceans project (PID2020-118097RB-I00) funded by the Spanish Ministry of Science and Innovation. We also acknowledge support from the SOSPen (PID2021-124831OA-I00) project funded by the Spanish Ministry of Science and Innovation and the GES4SEAS project (grant agreement no. 101059877) funded by the European Union under the Horizon Europe program. The authors also acknowledge the institutional support of the ‘Severo Ochoa Center of Excellence’ accreditation (CEX2024-001494-S funded by AEI 10.13039/501100011033) to the Institute of Marine Science (ICM-CSIC). Additionally, this research is part of the Integrated Marine Ecosystem Assessments (iMARES) research group, funded by the Agència de Gestió d'Ajuts Universitaris i de Recerca of the Generalitat de Catalunya (2021 SGR 00435), and the Global Ecology and Fisheries (GLOFISH) research group of the IEO-CSIC. The authors acknowledge partial funding from Ministerio para la Transición Ecológica y el Reto Demográfico (MITECO)., With funding form the Spanish government through the "Severa Ochoa Centre of Excellence" accreditation (CEX2024-001494-S)., Peer reviewed