Abstract
Prediction of true classes of surficial and deep earth materials using multivariate spatial data is a common challenge for geoscience modelers. 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. This paper proposes a spatial predictive model for classification of surficial and deep earth materials derived from the geochemical composition of surface regolith. The model is based on a combination of geostatistical simulation and machine learning approaches. A random forest 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 predictive model is used to estimate the probability of classes for simulated compositions. 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.
Highlights
Prediction of true classes of surficial and deep earth materials using multivariate spatial data is a common challenge for geoscience modelers
Class prediction and spatial uncertainty modeling using multivariate spatial data are a common challenge for geoscience modelers
We introduce and implement a new method for modeling spatial uncertainty of Australian MCBs based on surface regolith geochemistry and for predicting MCBs in areas lacking/between geochemical samples
Summary
Prediction of true classes of surficial and deep earth materials using multivariate spatial data is a common challenge for geoscience modelers. Most geological processes leave some sort of footprint that can be explored by advanced geochemical data analysis These footprints are complex multivariate statistical and/or spatial patterns hidden deep in the geochemical compositional space. Spatial relationships are taken into account via means such as second-order ((cross-)variograms) and/or higher-order statistics (training images) To address this limitation of MLAs, an alternative solution is proposed in this study based on the combined use of advanced multivariate geostatistical simulation and MLAs. The proposed spatial compositional predictive model is twofold: first, spatial simulation of geochemical compositions at unsampled locations and second class prediction for each simulated map via a trained random forest (RF) algorithm (Breiman 2001). Minimum, expected, and maximum probability scenarios are defined for each class from simulated probabilities
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
