Spatial interpolation methods for generating spatially continuous data from point samples of environmental variables are essential for environmental management and conservation. They may fall into three groups: non-geostatistical methods (e.g., inverse distance weighting), geostatistical methods (e.g., ordinary kriging) and combined/hybrid methods (e.g. regression kriging); and their performance is often data-specific (Li and Heap, 2008). Because of the robustness of machine learning methods, like random forest and support vector machine, in data mining fields, we introduced them into spatial statistics by applying them to the spatial predictions of seabed mud content in combination with existing spatial interpolation methods (Li et al., 2011). This development can be viewed as an extension of the combined methods from statistical methods to machine learning field. These applications have significantly improved the prediction accuracy and opened an alternative source of methods for spatial interpolation. Given that they have only been applied to one variable, several questions remain, namely: are they dataset- specific? How reliable are their predictions for different datasets and variables? Could other machine learning methods (such as boosted regression trees) improve the spatial interpolations? To address these questions, we experimentally compared the predictions of several methods for sand content on the southwest Australian marine margin. We tested a variety of existing spatial interpolation methods, machine learning methods and their combinations. In this study, we discuss the experimental results and the value of this advancement in spatial interpolation, visually examine the spatial predictions, and compare the results with the findings in the previous publications. The outcomes of this study can be applied to the spatial prediction of marine and terrestrial environmental variables.

Australian hourly temperature, humidity and pressure data as produced by the Bureau of Meteorology. Dataset contains: Air Temperature; Dew Point Temperature; Wet Bulb Temperature; Relative Humidity; Mean Sea Level Pressure; Station Level Pressure; Saturated Vapour Pressure; plus additional supporting information.

Australian Daily Wind Data as produced by the Bureau of Meteorology. Dataset contains: Mean daily wind speed; Daily maximum wind gust; Daily wind run from instruments at a height below 3 metre; Daily wind run from instruments at a height above 3 metre; plus additional supporting information.

Australian synoptic wind data as produced by the Bureau of Meteorology. Dataset contains: Synoptic wind speed and direction data; plus additional supporting information.

Australian present and past weather data as produced by the Bureau of Meteorology. Dataset contains: Present weather data as international code; Past weather data as international code; plus additional supporting information.

This dataset contains species identifications of molluscs collected during survey SOL4934 (R.V. Solander, 27 August - 24 September, 2009). Animals were collected from the Joseph Bonaparte Gulf with a benthic sled. Specimens were lodged at Northern Territory Museum on the 3 May 2010. Species-level identifications were undertaken by Richard Willan at the Northern Territory Museum and were delivered to Geoscience Australia on the 5 May 2010 (leg 1 only). See GA Record 2010/09 for further details on survey methods and specimen acquisition. Data is presented here exactly as delivered by the taxonomist, and Geoscience Australia is unable to verify the accuracy of the taxonomic identifications.

CAML is a five year International Program which will be undertaken as a major activity during the International Polar Year. This project will bring together all known data on Antarctic marine biodiversity and ocean change. The Antarctic Ocean is one of the most sensitive ecosystems in the world. Research undertaken via CAML will produce fascinating images of the Southern Ocean Geoscience Australia's Marine and Coastal Group is contributing expertise in sea floor mapping and sediment core collection to CAML. The Australian Government Antarctic Division is collecting oceanographic data, video footage and sediment cores through hot-water drill holes in the Amery Ice Shelf. The sediment cores are collected using a corer designed and built by Geoscience Australia, and are being analysed by scientists at Geoscience Australia to understand the environmental history beneath this ice shelf. This project has now produced four cores. The only other core ever obtained from beneath an extant ice shelf from under the Ross Ice Shelf in the early 1970s showed no signs of life. However, several Amery cores contain diatom-rich sediments, and one contains a succession of benthic faunas that indicate progressive colonisation of the sub-ice sea floor as ice retreated and currents began to seep nutrients and plankton into the sub-ice shelf cavity.

This record gives a brief account of the conditions encountered in a geological reconnaissance of the south-western portion of the Canning Basin - an area covered mostly by sand and seif dune, interspersed by scattered low rock outcrops.

The National Geochemical Survey of Australia (NGSA) project (www.ga.gov.au/ngsa) was part of Geoscience Australia's Onshore Energy Security Program 2006-2011 and was carried out in collaboration with the geological surveys of all States and the Northern Territory. It delivered (1) Australia's first national geochemical atlas, (2) an underpinning geochemical database, and (3) a series of reports. Catchment outlet sediments (similar to floodplain sediments in most cases) were sampled in 1186 catchments covering ~80% of the country (average sample density 1 sample per 5500 km2). Samples were collected at 2 depths each sieved to 2 grain size fractions. Chemical analyses carried out on the samples fall into 3 main categories: (1) total (using mainly XRF and total digestion ICP-MS), (2) aqua regia, and (3) Mobile Metal Ion® element contents. Results to date indicate a common spatial coincidence of elevated commodity element concentrations near areas of known mineralisation, for instance of U, Au and REEs. The survey data also identifies areas with elevated concentrations of energy and ore-related elements away from known deposits or occurrences, information which may be useful to the exploration industry. Comparison with airborne radiometric data indicates reasonable correlations between ground and airborne concentrations of K, U and Th. The phenomenon of disequilibrium in the radioactive decay chain of U does lead to some insights about leaching and accumulation of the more mobile daughter products (e.g., Rn, Ra). A continental-scale correction factor for airborne gamma-ray U surveys applicable to depositional areas is being developed.

The upper Swan River estuary located in the eastern suburban area of Perth in Western Australia experiences periods of poor water quality in the form high nutrient levels, anoxic bottom water conditions and occasional nuisance algae blooms. It has long been suspected that oxygen uptake and nutrient release from estuarine sediments are major drivers for these poor water quality conditions. Geoscience Australia in conjunction with the Department of Water in Western Australia investigated water quality in the upper Swan River estuary through water and sediment quality studies in October 2006, September 2007 and May 2008. The objectives of these studies were (1) to characterise the distribution of sediments, in particular to identify areas of high nutrient release, (2) to better understand conditions leading to high oxygen consumption and nutrient release, and (3) to determine the influence of the bottom water oxygen status on nutrient release from sediments.