Geothermal heat flow (GHF) data measured directly from boreholes are sparse. Purely physics-based models for geothermal heat flow prediction require various simplifications and are feasible only for few geophysical observables. Thus, data-driven multi-observable approaches need to be explored for continental-scale models. In this study, we generate a geothermal heat flow model over Africa using random forest regression, originally based on sixteen different geophysical and geological quantities. Due to an intrinsic importance ranking of the observables, the number of observables used for the final GHF model has been reduced to eleven (among them are Moho depth, Curie temperature depth, gravity anomalies, topography, and seismic wave velocities). The training of the random forest is based on direct heat flow measurements collected in the compilation of (Lucazeau et al., Geochem. Geophys. Geosyst. 2019, 20, 4001–4024). The final model reveals structures that are consistent with existing regional geothermal heat flow information. It is interpreted with respect to the tectonic setup of Africa, and the influence of the selection of training data and observables is discussed.
We generate a geothermal heat flow model over Africa using random forest regression basedon sixteen different geophysical and geological quantities (among them are Moho depth, Curietemperature depth, gravity anomalies, topography, and seismic wave velocities). The training of the random forest is based on direct heat flow measurements collected in the compilation of Lucazeau (2019). The final model reveals structures that are consistent with existing regional geothermal heat flow information. It is interpreted with respect to the tectonic setup of Africa, and the influence ofthe selection of training data and target observables is illustrated in the supplementary material
<p><span>Reliable and direct geothermal heat flow (GHF) measurements in Africa are sparse. It is a challenging task to create a map that reflects the GHF and covers the African continent in in its entirety.</span></p><p><span>We approached this task by training a random forest regression algorithm. After carefully tuning the algorithm's hyperparameters, the trained model relates the GHF to various geophysical and geological covariates that are considered to be statistically significant for the GHF. The covariates are mainly global datasets and models like Moho depth, Curie depth, gravity anomalies. To improve the predictions, we included some regional datasets. The quality and reliability of the datasets are assessed before the algorithm is trained.</span></p><p><span>The model's performance is validated against Australia, which has a large database of GHF measurements. The predicted GHF map of Africa shows acceptable performance indicators and is consistent with existing recognized GHF maps of Africa.</span></p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.