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

Strontium isotope ratios (Sr-87/Sr-86) 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 Sr-87/Sr-86 variations ("isoscapes"). A variety of empirically-based and process-based models have been proposed to build terrestrial Sr-87/Sr-86 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 Sr-87/Sr-86 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 Sr-87/Sr-86 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 Sr-87/Sr-86 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 Sr-87/Sr-86 predictions in bioavailable strontium for Western Europe (R-2 = 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 Sr-87/Sr-86 data and satellite geospatial products will extend the applicability of the Sr-87/Sr-86 geo-profiling tool in provenance applications.