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

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 tech...

Full description

Saved in:
Bibliographic Details
Published in:Environmental modelling & software : with environment data news 2017-11, Vol.97, p.112-129
Main Authors: Li, Jin, Alvarez, Belinda, Siwabessy, Justy, Tran, Maggie, Huang, Zhi, Przeslawski, Rachel, Radke, Lynda, Howard, Floyd, Nichol, Scott
Format: Article
Language:English
Subjects:
Artificial intelligence
Data processing
Ecosystem management
Environmental management
Feature selection
Geostatistics
Identification methods
Machine learning
Marine ecosystems
Model accuracy
Model selection
Prediction models
Predictive accuracy
Spatial distribution
Spatial prediction
Spatial predictive model
Species richness
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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. •Five feature selection methods for selecting RF predictive models are assessed.•Jointly using RF and AIC can select accuracy-improved GLM predictive models.•Hybrid methods of RF and geostatistical methods can accurately predict count data.•High sponge species richness is usually associated with hard seabed features.•Spatial distribution of sponge species richness is predicted with a high accuracy.
ISSN:1364-8152
1873-6726
DOI:10.1016/j.envsoft.2017.07.016