A bioavailable strontium isoscape for Western Europe: A machine learning approach

Clement P. Bataille, Isabella C.C. von Holstein, Jason E. Laffoon, Malte Willmes, Xiao Ming Liu, Gareth R. Davies

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Strontium isotope ratios (87Sr/86Sr) are gaining considerable interest as a geolocation tool and are now widely applied in archaeology, ecology, and forensic research. However, their application for provenance requires the development of baseline models predicting surficial 87Sr/86Sr variations (“isoscapes”). A variety of empirically-based and process-based models have been proposed to build terrestrial 87Sr/86Sr isoscapes but, in their current forms, those models are not mature enough to be integrated with continuous-probability surface models used in geographic assignment. In this study, we aim to overcome those limitations and to predict 87Sr/86Sr variations across Western Europe by combining process-based models and a series of remote-sensing geospatial products into a regression framework. We find that random forest regression significantly outperforms other commonly used regression and interpolation methods, and efficiently predicts the multi-scale patterning of 87Sr/86Sr variations by accounting for geological, geomorphological and atmospheric controls. Random forest regression also provides an easily interpretable and flexible framework to integrate different types of environmental auxiliary variables required to model the multi-scale patterning of 87Sr/86Sr variability. The method is transferable to different scales and resolutions and can be applied to the large collection of geospatial data available at local and global levels. The isoscape generated in this study provides the most accurate 87Sr/86Sr predictions in bioavailable strontium for Western Europe (R2 = 0.58 and RMSE = 0.0023) to date, as well as a conservative estimate of spatial uncertainty by applying quantile regression forest. We anticipate that the method presented in this study combined with the growing numbers of bioavailable 87Sr/86Sr data and satellite geospatial products will extend the applicability of the 87Sr/86Sr geo-profiling tool in provenance applications.

LanguageEnglish
Article numbere0197386
JournalPLoS ONE
Volume13
Issue number5
DOIs
StatePublished - 30 May 2018

Fingerprint

Strontium
strontium
artificial intelligence
Western European region
Learning systems
Strontium Isotopes
Archaeology
Ecology
provenance
Uncertainty
spatial data
Research
remote sensing
Forests
Machine Learning
Remote sensing
isotopes
Interpolation
uncertainty
methodology

Cite this

@article{0457fad1a9574599a6916a7c3f871c53,
title = "A bioavailable strontium isoscape for Western Europe: A machine learning approach",
abstract = "Strontium isotope ratios (87Sr/86Sr) are gaining considerable interest as a geolocation tool and are now widely applied in archaeology, ecology, and forensic research. However, their application for provenance requires the development of baseline models predicting surficial 87Sr/86Sr variations (“isoscapes”). A variety of empirically-based and process-based models have been proposed to build terrestrial 87Sr/86Sr isoscapes but, in their current forms, those models are not mature enough to be integrated with continuous-probability surface models used in geographic assignment. In this study, we aim to overcome those limitations and to predict 87Sr/86Sr variations across Western Europe by combining process-based models and a series of remote-sensing geospatial products into a regression framework. We find that random forest regression significantly outperforms other commonly used regression and interpolation methods, and efficiently predicts the multi-scale patterning of 87Sr/86Sr variations by accounting for geological, geomorphological and atmospheric controls. Random forest regression also provides an easily interpretable and flexible framework to integrate different types of environmental auxiliary variables required to model the multi-scale patterning of 87Sr/86Sr variability. The method is transferable to different scales and resolutions and can be applied to the large collection of geospatial data available at local and global levels. The isoscape generated in this study provides the most accurate 87Sr/86Sr predictions in bioavailable strontium for Western Europe (R2 = 0.58 and RMSE = 0.0023) to date, as well as a conservative estimate of spatial uncertainty by applying quantile regression forest. We anticipate that the method presented in this study combined with the growing numbers of bioavailable 87Sr/86Sr data and satellite geospatial products will extend the applicability of the 87Sr/86Sr geo-profiling tool in provenance applications.",
author = "Bataille, {Clement P.} and {von Holstein}, {Isabella C.C.} and Laffoon, {Jason E.} and Malte Willmes and Liu, {Xiao Ming} and Davies, {Gareth R.}",
year = "2018",
month = "5",
day = "30",
doi = "10.1371/journal.pone.0197386",
language = "English",
volume = "13",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "5",

}

A bioavailable strontium isoscape for Western Europe : A machine learning approach. / Bataille, Clement P.; von Holstein, Isabella C.C.; Laffoon, Jason E.; Willmes, Malte; Liu, Xiao Ming; Davies, Gareth R.

In: PLoS ONE, Vol. 13, No. 5, e0197386, 30.05.2018.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - A bioavailable strontium isoscape for Western Europe

T2 - PLoS ONE

AU - Bataille,Clement P.

AU - von Holstein,Isabella C.C.

AU - Laffoon,Jason E.

AU - Willmes,Malte

AU - Liu,Xiao Ming

AU - Davies,Gareth R.

PY - 2018/5/30

Y1 - 2018/5/30

N2 - Strontium isotope ratios (87Sr/86Sr) are gaining considerable interest as a geolocation tool and are now widely applied in archaeology, ecology, and forensic research. However, their application for provenance requires the development of baseline models predicting surficial 87Sr/86Sr variations (“isoscapes”). A variety of empirically-based and process-based models have been proposed to build terrestrial 87Sr/86Sr isoscapes but, in their current forms, those models are not mature enough to be integrated with continuous-probability surface models used in geographic assignment. In this study, we aim to overcome those limitations and to predict 87Sr/86Sr variations across Western Europe by combining process-based models and a series of remote-sensing geospatial products into a regression framework. We find that random forest regression significantly outperforms other commonly used regression and interpolation methods, and efficiently predicts the multi-scale patterning of 87Sr/86Sr variations by accounting for geological, geomorphological and atmospheric controls. Random forest regression also provides an easily interpretable and flexible framework to integrate different types of environmental auxiliary variables required to model the multi-scale patterning of 87Sr/86Sr variability. The method is transferable to different scales and resolutions and can be applied to the large collection of geospatial data available at local and global levels. The isoscape generated in this study provides the most accurate 87Sr/86Sr predictions in bioavailable strontium for Western Europe (R2 = 0.58 and RMSE = 0.0023) to date, as well as a conservative estimate of spatial uncertainty by applying quantile regression forest. We anticipate that the method presented in this study combined with the growing numbers of bioavailable 87Sr/86Sr data and satellite geospatial products will extend the applicability of the 87Sr/86Sr geo-profiling tool in provenance applications.

AB - Strontium isotope ratios (87Sr/86Sr) are gaining considerable interest as a geolocation tool and are now widely applied in archaeology, ecology, and forensic research. However, their application for provenance requires the development of baseline models predicting surficial 87Sr/86Sr variations (“isoscapes”). A variety of empirically-based and process-based models have been proposed to build terrestrial 87Sr/86Sr isoscapes but, in their current forms, those models are not mature enough to be integrated with continuous-probability surface models used in geographic assignment. In this study, we aim to overcome those limitations and to predict 87Sr/86Sr variations across Western Europe by combining process-based models and a series of remote-sensing geospatial products into a regression framework. We find that random forest regression significantly outperforms other commonly used regression and interpolation methods, and efficiently predicts the multi-scale patterning of 87Sr/86Sr variations by accounting for geological, geomorphological and atmospheric controls. Random forest regression also provides an easily interpretable and flexible framework to integrate different types of environmental auxiliary variables required to model the multi-scale patterning of 87Sr/86Sr variability. The method is transferable to different scales and resolutions and can be applied to the large collection of geospatial data available at local and global levels. The isoscape generated in this study provides the most accurate 87Sr/86Sr predictions in bioavailable strontium for Western Europe (R2 = 0.58 and RMSE = 0.0023) to date, as well as a conservative estimate of spatial uncertainty by applying quantile regression forest. We anticipate that the method presented in this study combined with the growing numbers of bioavailable 87Sr/86Sr data and satellite geospatial products will extend the applicability of the 87Sr/86Sr geo-profiling tool in provenance applications.

UR - http://www.scopus.com/inward/record.url?scp=85047828662&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047828662&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0197386

DO - 10.1371/journal.pone.0197386

M3 - Article

VL - 13

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 5

M1 - e0197386

ER -