Citation

Geoscience Australia provides most of its products for free under a Creative Commons Attribution 3.0 Australia Licence. We only require that you reference the use of our data or information using the following citation:
Li, J., Heap, A.D., Potter, A. & Daniell, J.J., 2011. Predicting Seabed Mud Content across the Australian Margin: Performance of Machine Learning Methods and their combinations with Ordinary Kriging and Inverse Distance Squared. Record  2011/007. Geoscience Australia, Canberra.

Abstract

In 2008, the performance of 14 statistical and mathematical methods for spatial interpolation was compared using samples of seabed mud content across the Australian Exclusive Economic Zone (AEEZ), which indicated that machine learning methods are generally among the most accurate methods. In this study, we further test the performance of machine learning methods in combination with ordinary kriging (OK) and inverse distance squared (IDS). We aim to identify the most accurate methods for spatial interpolation of seabed mud content in three regions (i.e., N, NE and SW) in AEEZ using samples extracted from Geoscience Australia's Marine Samples Database (MARS). The performance of 18 methods (machine learning methods and their combinations with OK or IDS) is compared using a simulation experiment. The prediction accuracy changes with the methods, inclusion and exclusion of slope, search window size, model averaging and the study region. The combination of RF and OK (RFOK) and the combination of RF and IDS (RFIDS) are, on average, more accurate than the other methods based on the prediction accuracy and visual examination of prediction maps in all three regions when slope is included and when their searching widow size is 12 and 7, respectively. Averaging the predictions of these two most accurate methods could be an alternative for spatial interpolation. The methods identified in this study reduce the prediction error by up to 19% and their predictions depict the transitional zones between geomorphic features in comparison with the control. This study confirmed the effectiveness of combining machine learning methods with OK or IDS and produced an alternative source of methods for spatial interpolation. Procedures employed in this study for selecting the most accurate prediction methods provide guidance for future studies.
Google map showing geographic bounding box with values North bound -8.0 East bound 160.0 West bound 105.0 South bound -40.0
Downloads
This product is available for purchase for $32.45.

To purchase it, complete the order form
[PDF 45 kB] and submit it to the
Geoscience Australia Sales Centre via:

fax:
+61 2 6249 9960; or
phone:
1800 800 173 (within Australia);
 
+61 2 6249 9966 (outside Australia).

Product Type/Sub Type

dataset - GA Publication - Record

Constraints

license
Creative Commons Attribution 3.0 Australia Licence

IP Owner

Commonwealth of Australia (Geoscience Australia)

Author(s)

Date (publication)

2011

Product Type

dataset

Topic Category

geoscientificInformation

Keywords

GA Publication
Record
marine
numerical modelling
model
mapping
environmental
geoscience
Earth Sciences

Resource Language

English

Resource Character Set

utf8

Resource Security Classification

unclassified

Geographic Extent

North bound
-8.0
East bound
160.0
West bound
105.0
South bound
-40.0

Lineage

Unknown

Digital Transfer Options

onLine+hardcopy

Distribution Information

Price AUD$ INCL GST
32.45

DISTRIBUTION Format

pdf

Ordering Instructions

http://www.ga.gov.au/products-services/how-to-order-products/sales-centre.html

Distributor

Role
distributor
Organisation Name
Geoscience Australia
City
Canberra
Administrative Area
ACT
Postal Code
2601
Country
Australia
Email Address

Metadata File Identifier

a05f7892-fb54-7506-e044-00144fdd4fa6

Metadata Standard Name

ANZLIC Metadata Profile: An Australian/New Zealand Profile of AS/NZS ISO 19115:2005, Geographic information - Metadata

Metadata Standard Version

1.1

Metadata Date Stamp

2011-01-07

METADATA SECURITY CLASSIFICATION

unclassified

Metadata Contact

Role
pointOfContact
Organisation Name
Geoscience Australia
City
Canberra
Administrative Area
ACT
Postal Code
2601
Country
Australia
Email Address
Downloads
This product is available for purchase for $32.45.

To purchase it, complete the order form
[PDF 45 kB] and submit it to the
Geoscience Australia Sales Centre via:

fax:
+61 2 6249 9960; or
phone:
1800 800 173 (within Australia);
 
+61 2 6249 9966 (outside Australia).