Application of random forest, generalised linear model and their hybrid methods with geostatistical techniques to count data: Predicting sponge species richness. (November 2017)

• Record Type: Journal Article
• Authors: Li, Jin; Alvarez, Belinda; Siwabessy, Justy; Tran, Maggie; Huang, Zhi; Przeslawski, Rachel; Radke, Lynda; Howard, Floyd; Nichol, Scott
• Is Part Of: Environmental modelling & software. Volume 97(2017)
• Page Start: 112
• Page End: 129
• Publication Date: 2017-11
• Subjects: Machine learning -- Feature selection -- Model selection -- Predictive accuracy -- Spatial predictive model -- Spatial prediction; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2017.07.016
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: 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. Highlights: 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.