A study compares 18 spatial interpolation methods for predicting seabed mud content across three regions of the Australian Exclusive Economic Zone. The work uses samples from Geoscience Australia's Marine Samples Database and evaluates combinations of machine learning with ordinary kriging and inverse distance squared. The methods identified reduce prediction error by up to 19% and better depict transitional zones between geomorphic features.
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 and search window size on prediction accuracy.
- Combining machine learning with traditional geostatistical methods like ordinary kriging.
- Creating prediction maps for seabed sediment composition in transitional zones.
Strengths
- Compares 18 distinct spatial interpolation methods, including machine learning and hybrid approaches.
- Identifies methods that reduce prediction error by up to 19%.
- Focuses on three specific regions (N, NE, SW) within the Australian Exclusive Economic Zone.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
Provenance
- Source
- Australian Ocean Data Network
- Collection Method
- Samples extracted from Geoscience Australia's Marine Samples Database (MARS).
- Freshness
- Last updated 2026-04-16 13:58:55.398914; freshness should be verified.
- Geography
- Australian Exclusive Economic Zone, specifically N, NE, and SW regions.