Predicting the spatial distribution of seabed gravel content using random forest, spatial interpolation methods and their hybrid methods  

Authors / CoAuthors

Li, J.

Abstract

In this study, we aim to identify the most accurate methods for spatial prediction of seabed gravel content in the northwest Australian Exclusive Economic Zone. We experimentally examined: 1) whether input secondary variables affect the performance of RFOK and RFIDW, 2) whether the performances of RF, SIMs and their hybrid methods are data-specific, and 3) whether model averaging improves predictive accuracy of these methods in the study region. For RF and the hybrid methods, up to 21 variables were used as predictors. The predictive accuracy was assessed in terms of relative mean absolute error and relative root mean squared error based on the average of 100 iterations of 10-fold cross validation. In this study, the following important findings were achieved: - the predictive errors fluctuate with the input secondary variables; - the existence of correlated variables can alter the results of model selection, leading to different models; - the set of initial input variables affects the model selected; - the most accurate model can be missed out during the model selection; - RF, RFOK and RFIDW prove to be the most accurate methods in this study, with RFOK preferred; and these methods are not data-specific, but their models are, so best model needs to be identified; and - Model averaging is clearly data-specific. In conclusion, model selection is essential for RF and the hybrid methods. RF and the hybrid methods are not data-specific, but their models are. RFOK is the most accurate method. Model averaging is also data-specific. Hence best model needs to be identified for individual studies and application of model averaging should also be examined accordingly. RF and the hybrid methods have displayed substantial potentials for predicting environmental properties and are recommended for further test for spatial predictions in environmental sciences and other relevant disciplines in the future. This study provides suggestions and guidelines for improving the spatial predictions of biophysical variables in both marine and terrestrial environments.

Product Type

nonGeographicDataset

eCat Id

75615

Contact for the resource

Keywords

• External Publication

( Theme )

• marine

Australian and New Zealand Standard Research Classification (ANZSRC)

• Environmental Science and Management

• Published_Internal

Publication Date

2013-01-01T00:00:00

Creation Date

Security Constraints

Australian Government Security ClassificationSystem    

Classification - unclassified

Legal Constraints

Creative Commons Attribution 4.0 International Licence    

Access - restricted

Use - license

Status

Purpose

Maintenance Information

unknown

Topic Category

environment

Series Information

Lineage

Unknown

Parent Information

Extents

Reference System

Spatial Resolution

Service Information

Associations

Downloads and Links

Source Information

Source data not available.