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.

A statistical assessment of wave, tide, and river power was carried out using a database of 721 Australian clastic coastal depositional environments to test whether their geomorphology could be predicted from numerical values. The geomorphic classification of each environment (wave- and tide-dominated deltas, wave- and tide-dominated estuaries, lagoons, strand plains, and tidal flats) was established independently from remotely sensed imagery. To our knowledge, such a systematic numerical analysis has not been previously attempted for any region on earth.

Simple, conceptual geomorphic models can assist environmental managers in making informed decisions regarding management of the coast at continental and regional scales. This basic information, detected from aerial photographs and/or satellite images, can be used to ascertain the relative significance of several common environmental issues, including: sediment trapping efficiency, turbidity, water circulation, and habitat change due to sedimentation for different types of clastic coastal depositional environments.

The dataset provides the spatially continuous data of the seabed gravel content (sediment fraction >2000 µm) expressed as a weight percentage ranging from 0 to 100%, presented in 0.01 decimal degree resolution raster format. The dataset covers the Australian continental EEZ, including seabed surrounding Tasmania. It does not include areas surrounding Macquarie Island, and the Australian Territories of Norfolk Island, Christmas Island, and Cocos (Keeling) Islands or Australia's marine jurisdiction off of the Territory of Heard and McDonald Islands and the Australian Antarctic Territory. This dataset supersedes previous predictions of sediment gravel content for the Australian Margin with demonstrated improvements in accuracy. Accuracy of predictions varies based on density of underlying data and level of seabed complexity. Artefacts occur in this dataset as a result of insufficient samples in relevant regions. This dataset is intended for use at national and regional scales. The dataset may not be appropriate for use at local scales in areas where sample density is insufficient to detect local variation in sediment properties. To obtain the most accurate interpretation of sediment distribution in these areas, it is recommended that additional samples be collected and interpolations updated.

This dataset provides the spatially continuous data of the seabed sand content (sediment fraction 63-2000 mm) expressed as a weight percentage ranging from 0 to 100%, presented in 0.01 decimal degree resolution raster format. The dataset covers the Australian continental EEZ, including seabed surrounding Tasmania. It does not include areas surrounding Macquarie Island, and the Australian Territories of Norfolk Island, Christmas Island, and Cocos (Keeling) Islands or Australia's marine jurisdiction off of the Territory of Heard and McDonald Islands and the Australian Antarctic Territory. This dataset supersedes previous predictions of sediment sand content for the Australian Margin with demonstrated improvements in accuracy. Accuracy of predictions varies based on density of underlying data and level of seabed complexity. Artefacts occur in this dataset as a result of insufficient samples in relevant regions. This dataset is intended for use at national and regional scales. The dataset may not be appropriate for use at local scales in areas where sample density is insufficient to detect local variation in sediment properties. To obtain the most accurate interpretation of sediment distribution in these areas, it is recommended that additional samples be collected and interpolations updated.

Multibeam sonar swath-mapping has revealed small submarine volcanic cones on the northeastern Lord Howe Rise (LHR), a submerged ribbon continent. Two such cones, aligned NNW and 120 km apart, were dredged at 23-24Degrees S. Water depth is about 1150 m nearby: the southern cone rises to 750 m and the northern to 900 m. Volcanic rocks dredged from the cones are predominantly highly altered hyaloclastites with minor basalt. The clasts are mostly intensely altered vesicular brownish glass with lesser basalt, in zeolitic, clayey, micritic or ferruginous cement. Lavas and hyaloclastites contain altered phenocrysts of olivine and plagioclase, and fresh clinopyroxene. The latter have compositions between acmite and Ti-augite, and match well clinopyroxene phenocrysts in undersaturated intraplate basanitic mafic lavas. Interbedded micrites in the volcaniclastics represent calcareous ooze that was deposited with (or later than) the volcanic pile. Foraminifera indicate that the oldest micrite is late Early Miocene (~16 Ma), and that the original ooze was deposited in cool water. Late Miocene to Pliocene micrites, presumed to be later infillings, all contain warm water forms. This evidence strongly suggests that both cones formed in pelagic depths in the Early Miocene. Ferromanganese crusts from the two cones are up to 7 cm thick and similar physically, but different chemically. The average growth rate is 3 mm/m.y.. Copper, nickel and cobalt content are relatively high in the north, but copper does not exceed 0.08 wt %, nickel 0.65% and cobalt 0.25%. The Mn:Fe ratio is high in the south (average 13.7) suggesting strong hydrothermal influence. Such small volcanic cones related to intraplate hotspot-type magmatism may occur in extensive fields like those off southern Tasmania. On Lord Howe Rise, the known small volcanic cones coincide with broad gravity highs in areas of shallow continental basement. The highs probably represent Neogene plume-related magmatism. The thick continental crust may dissipate and spread the magma widely, whereas plumes may penetrate thin oceanic crust more readily and build larger edifices. The correspondence of the ages derived from micropalaeontology and from extrapolating from nearby dated hotspot traces support such a genesis. Accordingly, gravity highs in the right setting may help predict fields of small volcanic seamounts.

The Australian exclusive economic zone (EEZ) contains1.6 million km2 of submarine plateaus, equal to about 13.8% of the world's known inventory of these features. This disproportionate occurrence of plateaus presents Australia with an increased global responsibility to understand and protect the benthic habitats and associated ecosystems. This special volume presents the results of two major marine surveys carried out on the Lord Howe Rise plateau during 2003 and 2007, during which benthic biological and geological samples, underwater photographs, video and multibean sonar bathymetry data were collected. The benthic habitats present on Lord Howe Rise include hard/rocky substrates covering a small area of volcanic peaks (around 31 km2) and parts of other larger seamounts (eg. the Lord Howe Island seamount) which support rich and abundant epifaunal assemblages dominated by suspension feeding invertebrates. These habitats appear to qualify as ecologically and biologically significant areas under the United Nations Convention on Biological Diversity (CBD) scientific selection criterion 1 (uniqueness or rarity), 4 (vulnerability, fragility, sensitivity or slow recovery) and 7 (naturalness). The collection of papers included in this special volume represents a major advance in knowledge about benthic habitats of the Lord Howe Rise, but also about the ecology of plateaus in general.

This report details the keystroke methodology used to create the seascape maps for planning areas of the Australian margin.

This report describes the iterative methods used to create the seascapes, including a detailed appendix documenting the different datasets used in the different planning zones. Creating the seascapes is necessarily an iterative process whereby the available datasets are combined in different combinations, or added as they become available, using an unsupervised 'crisp' ISOClass classification in ERMapper. In each classification only biophysical properties that have consistent and definable relationships with the benthic biota and are known in sufficient detail across Australia's entire marine region are used to create the seascapes. An initial validation of the classification technique has been undertaken on a subset of the data for the shelf surrounding Tasmania using an alternative unsupervised 'fuzzy' classification. Results of this validation indicate that the unsupervised classification methodology provides consistent and reliable classes for defining the seascapes.

Australian estuaries and coastal waterways were classified into six subclasses according to the wave-, tide- and river-energies that shape them, and also according to their overall geomorphology. The geomorphic classification confirmed the energy classification. Within this framework: - 17% were classified as wave-dominated estuaries; - 11% were classified as tide-dominated estuaries; - 10% were classified as wave-dominated deltas; and - 9% were classified as tide-dominated deltas Therefore, only ~28% of Australian coastal waterways are actually estuaries. The remainder are delta's (19%), strandplains (~5%), or tidal creeks (~35%). A seventh subclass others (13%) includes: Drowned River Valleys, Embayments and Coastal Lakes/Lagoons/Creeks. Strandplains and Tidal Creeks are indicative of very low river-energy, and their joint dominance in the data set (~40%) reflects the fact that Australia is a dry continent, with relatively little river runoff by world standards.