Elisabeth N. Bui

Spatial data mining for enhanced soil map modelling

The principle of using induction rules based on spatial environmental data to model a soil map has previously been demonstrated. Whilst the general pattern of classes of large spatial extent and those with close association with geology were delineated, small classes and the detailed spatial pattern of the map were less well rendered. Here we examine several strategies to improve the quality of the soil map models generated by rule induction. Terrain attributes that are better-suited to landscape description at a resolution of 250 m are introduced as predictors of soil type. A map sampling strategy is developed. Classification error is reduced by using boosting rather than cross-validation to improve the model. Further, the benefit of incorporating the local spatial context for each environmental variable into the rule induction is examined. The best model was achieved by sampling in proportion to the spatial extent of the mapped classes, boosting the decision trees, and using spatial contextual information extracted from the environmental variables.

ASRIS: the database

The Australian Soil Resources Information System (ASRIS) database compiles the best publicly available information available across Commonwealth, State, and Territory agencies into a national database of soil profile data, digital soil and land resources maps, and climate, terrain, and lithology datasets. These datasets are described in detail in this paper. Most datasets are thematic grids that cover the intensively used agricultural zones in Australia.

Disaggregation of polygons of surficial geology and soil maps using spatial modelling and legacy data

Examples from the Murray-Darling basin in Australia are used to illustrate different methods of disaggregation of reconnaissance-scale maps. One approach for disaggregation revolves around the de-convolution of the soil-landscape paradigm elaborated during a soil survey. The descriptions of soil ma units and block diagrams in a soil survey report detail soil-landscape relationships or soil toposequences that can be used to disaggregate map units into component landscape elements. Toposequences can be visualised on a computer by combining soil maps with digital elevation data. Expert knowledge or statistics can be used to implement the disaggregation. Use of a restructuring element and k-means clustering are illustrated. Another approach to disaggregation uses training areas to develop rules to extrapolate detailed mapping into other, larger areas where detailed mapping is unavailable. A two-level decision tree example is presented. At one level, the decision tree method is used to capture mapping rules from the training area; at another level, it is used to define the domain over which those rules can be extrapolated

Baseline map of organic carbon in Australian soil to support national carbon accounting and monitoring under climate change.

We can effectively monitor soil condition—and develop sound policies to offset the emissions of greenhouse gases—only with accurate data from which to define baselines. Currently, estimates of soil organic C for countries or continents are either unavailable or largely uncertain because they are derived from sparse data, with large gaps over many areas of the Earth. Here, we derive spatially explicit estimates, and their uncertainty, of the distribution and stock of organic C in the soil of Australia. We assembled and harmonized data from several sources to produce the most comprehensive set of data on the current stock of organic C in soil of the continent. Using them, we have produced a fine spatial resolution baseline map of organic C at the continental scale. We describe how we made it by combining the bootstrap, a decision tree with piecewise regression on environmental variables and geostatistical modelling of residuals. Values of stock were predicted at the nodes of a 3-arc-sec (approximately 90 m) grid and mapped together with their uncertainties. We then calculated baselines of soil organic C storage over the whole of Australia, its states and territories, and regions that define bioclimatic zones, vegetation classes and land use. The average amount of organic C in Australian topsoil is estimated to be 29.7 t ha−1 with 95% confidence limits of 22.6 and 37.9 t ha−1. The total stock of organic C in the 0–30 cm layer of soil for the continent is 24.97 Gt with 95% confidence limits of 19.04 and 31.83 Gt. This represents approximately 3.5% of the total stock in the upper 30 cm of soil worldwide. Australia occupies 5.2% of the global land area, so the total organic C stock of Australian soil makes an important contribution to the global carbon cycle, and it provides a significant potential for sequestration. As the most reliable approximation of the stock of organic C in Australian soil in 2010, our estimates have important applications. They could support Australias National Carbon Accounting System, help guide the formulation of policy around carbon offset schemes, improve Australias carbon balances, serve to direct future sampling for inventory, guide the design of monitoring networks and provide a benchmark against which to assess the impact of changes in land cover, land management and climate on the stock of C in Australia. In this way, these estimates would help us to develop strategies to adapt and mitigate the effects of climate change.

A strategy to fill gaps in soil survey over large spatial extents: an example from the Murray–Darling basin of Australia

We re-mapped the soils of the Murray-Darling Basin (MDB) in 1995-1998 with a minimum of new fieldwork, making the most out of existing data. We collated existing digital soil maps and used inductive spatial modelling to predict soil types from those maps combined with environmental predictor variables. Lithology, Landsat Multi Spectral Scanner (Landsat MSS), the 9-s digital elevation model (DEM) of Australia and derived terrain attributes, all gridded to 250-m pixels, were the predictor variables. Because the basin-wide datasets were very large data mining software was used for modelling. Rule induction by data mining was also used to define the spatial domain of extrapolation for the extension of soil-landscape models from existing soil maps. Procedures to estimate the uncertainty associated with the predictions and quality of information for the new soil-landforms map of the MDB are described

A multi-objective model for environmental investment decision making

Investment in landscapes to achieve outcomes that have multiple environmental benefits has become a major priority in many countries. This gives rise to opportunities for mathematical programming methods to provide solutions on where investments could be made on the landscape, to maximise multiple environmental benefits. The problem was formulated as a multi-objective integer programming model, with objective functions representing biodiversity, water run-off and carbon sequestration. We applied a multi-objective Greedy Randomised Adaptive Search Procedure (GRASP) as an evolutionary programming method to find solutions along the Pareto front. This allows the decision maker to explore trade-offs between the objectives. A 142,000ha case study catchment in eastern Australia was used to test the methodology and assess the sensitivity of the different and often competing environmental benefits.

Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia

[1] We present a piecewise linear decision tree model for predicting percent of soil organic C (SOC) in the agricultural zones of Australia generated using a machine learning approach. The inputs for the model are a national database of soil data, national digital surfaces of climate, elevation, and terrain variables, Landsat multispectral scanner data, lithology, land use, and soil maps. The model and resulting map are evaluated, and insights into biogeological surficial processes are discussed. The decision tree splits the overall data set into more homogenous subsets, thus in this case, it identifies areas where SOC responds closely to climatic and other environmental variables. The spatial pattern of SOC corresponds well to maps of estimated primary productivity and bioclimatic zones. Topsoil organic C levels are highest in the high rainfall, temperate regions of Tasmania, Victoria, and Western Australia, along the coast of New South Wales and in the wet tropics of Queensland; and lowest in arid and semiarid inland regions. While this pattern broadly follows continental vegetation, soil moisture, and temperature patterns, it is governed by a spatially variable hierarchy of different climatic and other variables across bioregions of Australia. At the continental scale, soil moisture level, rather than temperature, seems most important in controlling SOC.

C:N:P stoichiometry in Australian soils with respect to vegetation and environmental factors

AimsWe estimate organic carbon (C): total nitrogen (N): total phosphorus (P) ratios in soils under Australia’s major native vegetation groups.MethodsWe use digital datasets for climate, soils, and vegetation created for the National Land and Water Resources Audit in 2001. Analysis-of-variance is used to investigate differences in nutrient ratios between ecosystems. Linear discriminant analysis and logistic regression are used to investigate the relative importance of climatic variables and soil nutrients in vegetation patterns.ResultsWe find that the N:P and C:P ratios have a greater range of values than the C:N ratio, although major vegetation groups tend to show similar trends across all three ratios. Some apparently homeostatic groupings emerge: those with very low, low, medium, or high N:P and C:P. Tussock grasslands have very low soil N, N:P, and C:P, probably due to frequent burning. Eucalypt woodlands have low soil N:P and C:P ratios, although their total P level varies. Rainforests and Melaleuca forests have medium soil N:P and C:P ratios, although their total P level is different. Heathlands, tall open eucalypt forests, and shrublands occur on soils with low levels of total P, and high N:P and C:P ratios that reflect foliar nutrient ratios and recalcitrant litter.ConclusionsCertain plant communities have typical soil nutrient stoichiometries but there is no single Redfield-like ratio. Vegetation patterns largely reflect soil moisture but for several plant communities, eucalypt communities in particular, soil N and P (or N:P) also play a significant role. Soil N:P and the presence of Proteaceae appear indicative of nutrient constraints in ecosystems.

PBL-GIS in Secondary Geography Education: Does It Result in Higher-Order Learning Outcomes?.

Abstract This article presents research on evaluating problem-based learning using GIS technology in a Singapore secondary school. A quasi-experimental research design was carried to test the PBL pedagogy (PBL-GIS) with an experimental group of students and compare their learning outcomes with a control group who were exposed to PBL but not GIS. The results show significant differences in the learning outcomes between the two groups. Specifically, students in the control group show more memorization skill while students in the experimental group demonstrate more analytical and evaluation skills. The conclusion is that learning with PBL-GIS pedagogy can result in higher-order learning outcomes.

An improved calibration curve between soil pH measured in waterand CaCl2

A new pH water to pH CaCl2 calibration curve was derived from data pooled from 2 National Land and Water Resources Audit projects. A total of 70465 observations with both pH in water and pH in CaCl2 were available for statistical analysis. An additive model for pH in CaCl2 was fitted from a smooth function of pH in water created by a smoothing spline with 6 degrees of freedom. This model appeared stable outside the range of the data and performed well (R2 = 96.2, s = 0.24). The additive model for conversion of pHw to pHCa is sigmoidal over the range of pH 2.5 to 10.5 and is similar in shape to earlier models. Using this new model, a look-up table for converting pHw to pHCa was created.