Seabed Mud Content Predictions Across the Australian Margin Using Machine Learning

Australian Exclusive Economic Zone seabed mud content data extracted from Geoscience Australia's Marine Samples Database (MARS). The dataset compares the performance of 18 spatial interpolation methods, including machine learning combinations with ordinary kriging and inverse distance squared, across three regions. The study, hosted by the Australian Ocean Data Network, was last updated in June 2026.

Use Cases

• Benchmarking spatial interpolation methods based on the comparison of 18 techniques.
• Predicting seabed mud content across marine regions based on sample data.
• Evaluating the impact of slope inclusion on prediction accuracy as described in the study.
• Assessing the effect of search window size on model performance as tested in the simulation.

Strengths

• Compares 18 distinct spatial interpolation methods, including machine learning hybrids.
• Focuses on three specific Australian marine regions (N, NE, SW) for targeted analysis.
• Identifies methods that reduce prediction error by up to 19% according to the description.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data may reflect geographic bias inherent to the Australian Ocean Data Network source.

Provenance

Source

Australian Ocean Data Network via data_gov_au.

Collection Method

Samples extracted from Geoscience Australia's Marine Samples Database (MARS).

Freshness

Last updated 2026-06-17 01:11:07.282005; freshness should be verified.

Geography

Australian Exclusive Economic Zone, specifically N, NE, and SW regions.