From Geoscience Australia
JSON format icon JSON RDF format icon RDF ISO19115-3 XML

Application of random forest, generalised linear model and their hybrid methods with geostatistical techniques to count data: Predicting sponge species richness

Created 19/11/2025

Updated 19/11/2025

JSON format icon JSON RDF format icon RDF ISO19115-3 XML

Spatial distribution of sponge species richness (SSR) and its relationship with environment are important for marine ecosystem management, but they are either unavailable or unknown. Hence we applied random forest (RF), generalised linear model (GLM) and their hybrid methods with geostatistical techniques to SSR data by addressing relevant issues with variable selection and model selection. It was found that: 1) of five variable selection methods, one is suitable for selecting optimal RF predictive models; 2) traditional model selection methods are unsuitable for identifying GLM predictive models and joint application of RF and AIC can select accuracy-improved models; 3) highly correlated predictors may improve RF predictive accuracy; 4) hybrid methods for RF can accurately predict count data; and 5) effects of model averaging are method-dependent. This study depicted the non-linear relationships of SSR and predictors, generated spatial distribution of SSR with high accuracy and revealed the association of high SSR with hard seabed features. Citation: Jin Li, Belinda Alvarez, Justy Siwabessy, Maggie Tran, Zhi Huang, Rachel Przeslawski, Lynda Radke, Floyd Howard, Scott Nichol, Application of random forest, generalised linear model and their hybrid methods with geostatistical techniques to count data: Predicting sponge species richness, Environmental Modelling & Software, Volume 97, 2017, Pages 112-129, https://doi.org/10.1016/j.envsoft.2017.07.016

Files and APIs

Tags

Additional Info

Field Value
Title Application of random forest, generalised linear model and their hybrid methods with geostatistical techniques to count data: Predicting sponge species richness
Language eng
Licence Not Specified
Landing Page https://data.gov.au/data/en/dataset/37be7db8-8e08-4dbf-b38a-07024f2ecec1
Contact Point
Geoscience Australia Data
clientservices@ga.gov.au
Reference Period 19/06/2025
Geospatial Coverage
Map data © OpenStreetMap contributors
{
  "coordinates": [
    [
      [
        112.92,
        -54.75
      ],
      [
        159.11,
        -54.75
      ],
      [
        159.11,
        -9.2402
      ],
      [
        112.92,
        -9.2402
      ],
      [
        112.92,
        -54.75
      ]
    ]
  ],
  "type": "Polygon"
}
Data Portal Geoscience Australia

Data Source

This dataset was originally found on Geoscience Australia "Application of random forest, generalised linear model and their hybrid methods with geostatistical techniques to count data: Predicting sponge species richness". Please visit the source to access the original metadata of the dataset:
https://ecat.ga.gov.au/geonetwork/srv/eng/csw/dataset/application-of-random-forest-generalised-linear-model-and-their-hybrid-methods-with-geostatisti1