Four-class hardness prediction grids in the eastern Joseph Bonaparte Gulf of Timor Sea  

Authors / CoAuthors

Li, J. | Tran, M. | Siwabessy, J.

Abstract

This dataset contains four-class hardness (i.e., hard-1, hard-soft-2, soft-3 and soft-hard-4) prediction data from seabed mapping surveys on the Van Diemen Rise in the eastern Joseph Bonaparte Gulf of the Timor Sea. This dataset was generated based on hard90 seabed hardness classification scheme using random forest methods based on the point data of seabed hardness classification using video images and multibeam data. Refer to Selecting optimal random forest predictive models: a case study on predicting the spatial distribution of seabed hardness for further information on processing techniques applied [1]. [1] Li, J., Tran, M., Siwabessy, J., 2016. Selecting optimal random forest predictive models: a case study on predicting the spatial distribution of seabed hardness PLOS ONE 11(2) e0149089.

Product Type

dataset

eCat Id

90645

Contact for the resource

Digital Object Identifier

http://dx.doi.org/10.4225/25/570732FF9FEB2

Keywords

• Data Package

( Theme )

• Marine

( Theme )

• seabed

( Theme )

• Data

Australian and New Zealand Standard Research Classification (ANZSRC)

• Earth Sciences

• Published_External

Publication Date

2016-01-01T00:00:00

Creation Date

Security Constraints

Australian Government Security ClassificationSystem    

Classification - unclassified

Legal Constraints

Creative Commons Attribution 4.0 International Licence    

Access - license

Use - license

Status

Purpose

Maintenance Information

unknown

Topic Category

geoscientificInformation

Series Information

Lineage

A prediction-based classification is produced using the Random Forest method based on bathymetry, backscatter data and their derivatives, with support from video. The prediction accuracy of hard, hard-soft, soft-hard and soft seabed types achieved a total classification accuracy of 90% based on 10-fold cross-validation. Based on the strong performance of the predictive model, the Random Forest was also used to predict the distribution of hard and soft seabed types across the four study areas.

Parent Information

Extents

[-12.287, -10.285, 129.451, 130.063]

Reference System

Spatial Resolution

Service Information

Associations

Downloads and Links

File download  

Source Information

Source data not available.