Projects per year
Abstract
Prediction of true classes of surficial and deep earth materials using multivariate geospatial data is a common challenge for geoscience modellers. Most geological processes leave a footprint that can be explored by geochemical data analysis. These footprints are normally complex statistical and spatial patterns buried deep in the high-dimensional compositional space. To explore these patterns, advanced spatial data analysis techniques should be implemented. This paper proposes a spatial predictive model for classification of surficial and deep earth materials derived from the geochemical composition of surface regolith that fully accounts for spatial uncertainty. The model is based on a combination of geostatistical simulation and machine learning approaches. A random forest (RF) predictive model is trained and features are ranked based on their contribution to the predictive model. To generate potential and uncertainty maps, compositional data are simulated at unsampled locations via a chain of transformations (isometric log-ratio transformation followed by the flow anamorphosis) and geostatistical simulation). The simulated results are subsequently back-transformed to the original compositional space. The trained RF model is used to predict the true classes for simulated compositions at unsampled locations. The proposed approach is illustrated through two case studies. In the first case study the major crustal blocks of the Australian continent are predicted from the surface regolith geochemistry of the National Geochemical Survey of Australia project. The aim of the second case study is to discover the superficial deposits (peat) from the regional-scale soil geochemical data of the Tellus project. The accuracy of the results in these two case studies confirms the usefulness of the proposed method for geological class prediction and geological process discovery.
Original language | English |
---|---|
Pages (from-to) | 869-891 |
Number of pages | 23 |
Journal | Natural Resources Research |
Volume | 28 |
Issue number | 3 |
Early online date | 31 Oct 2018 |
DOIs | |
Publication status | Published - Jul 2019 |
Keywords
- Compositional data, Log-ratio, flow anamorphosis, geostatistical simulation, machine learning
ASJC Scopus subject areas
- Earth-Surface Processes
- General Environmental Science
- Environmental Chemistry
- Geochemistry and Petrology
- Computational Theory and Mathematics
Fingerprint
Dive into the research topics of 'Surficial and Deep Earth Material Prediction from Geochemical Compositions'. Together they form a unique fingerprint.Projects
- 1 Active
Profiles
Research output
- 24 Citations
- 1 Abstract
-
Determining elemental associations by multivariate analysis of regional-scale geochemical data
Grunsky, E. & Mueller, U., 01 Sept 2016, (Unpublished) p. 1. 1 p.Research output: Contribution to conference › Abstract › peer-review