A machine learning approach to geochemical mapping

Abstract

The version presented here may differ from the published version or from the version of record. If you wish to cite this item you are advised to consult the publisher's version. Please see the repository url above for details on accessing the published version and note that access may require a subscription. Geochemical maps provide invaluable evidence to guide decisions on issues of mineral exploration, 9 agriculture, and environmental health. However, the high cost of chemical analysis means that the 10 ground sampling density will always be limited. Traditionally, geochemical maps have been 11 produced through the interpolation of measured element concentrations between sample sites 12 using models based on the spatial autocorrelation of data (e.g semivariogram models for ordinary 13 kriging). In their simplest form such models fail to consider potentially useful auxiliary information 14 about the region and the accuracy of the maps may suffer as a result. In contrast, this study uses 15 quantile regression forests (an elaboration of random forest) to investigate the potential of high 16 resolution auxiliary information alone to support the generation of accurate and interpretable 17 geochemical maps. This paper presents a summary of the performance of quantile regression forests 18 in predicting element concentrations, loss on ignition and pH in the soils of south west England using 19 high resolution remote sensing and geophysical survey data. 20Through stratified 10-fold cross validation we find the accuracy of quantile regression forests in 21 predicting soil geochemistry in south west England to be a general improvement over that offered 22 by ordinary kriging. Concentrations of immobile elements whose distributions are most tightly 23 controlled by bedrock lithology are predicted with the greatest accuracy (e.g. Al with a 24 cross-validated R 2 of 0.79), while concentrations of more mobile elements prove harder to predict. 25In addition to providing a high level of prediction accuracy, models built on high resolution auxiliary 26 variables allow for informative, process based, interpretations to be made. In conclusion, this study 27 has highlighted the ability to map and understand the surface environment with greater accuracy 28 2 and detail than previously possible by combining information from multiple datasets. As the quality 29 and coverage of remote sensing and geophysical surveys continue to improve, machine learning 30 methods will provide a means to interpret the otherwise-uninterpretable. 31 32 33

Grid‐based sediment tracing approach to determine sediment sources

“…In this study, the spatially distributed maps of the tracers were produced through the interpolation of the tracer concentrations between the sampling sites using a model based on the spatial autocorrelation of the data (natural neighbours). Recommended future research includes the application of recent developments on spatial modelling, for example, the machine learning approach (Kirkwood, Cave, Beamish, Grebby, & Ferreira, ) and decision tree‐based models (Wilford, de Caritat, & Bui, ), using points with measured element concentrations coupled with environmental covariates at those points to map the distribution of the tracers. These new techniques would provide the map with higher accuracy and detail than previously possible.…”

Geochemical zones and environmental gradients for soils from the Central Transantarctic Mountains, Antarctica

“…Recently, these techniques have been used for Earth Science applications, including geologic mapping (Heung et al, 2014;Kirkwood et al, 2016), air quality monitoring (Stafoggia et al, 2019), and water contaminant tracing (Tesoriero et al, 2017).…”

Artificial Intelligence & Machine Learning in the Earth Sciences

“…Perhaps the field in which these procedures have had the most impact to date is in the utilization of remote sensing data from images of the Earth's surface (e.g., Lary et al, 2016). However, reviews and tentative explorations of potential have been published recently in a variety of earth science fields, including: archeology (van der Maaten, 2006), biology (Tarca et al, 2007), taxonomy/systematics (MacLeod, 2007(MacLeod, , 2017, mineralogy (Rodriguez-Galliana et al, 2015), geochemistry (Kirkwood et al, 2016) and general geosciences (Caté et al, 2017).…”