Probabilistic source classification of large tephra producing eruptions using supervised machine learning: An example from the Alaska-Aleutian arc

Alaska contains over 130 volcanoes and volcanic fields that have been active within the last 2 million years. Of these, roughly 90 have erupted during the Holocene, with many characterized by at least one large explosive eruption. These large tephra-producing eruptions (LTPEs) generate orders of magnitude more erupted material than a “typical” arc explosive eruption and distribute ash thousands of kilometers from their source. Because LTPEs occur infrequently, and the proximal explosive deposit record in Alaska is generally limited to the Holocene, we require a method that links distal deposits to a source volcano where the correlative proximal deposits from that eruption are no longer preserved. We present a model that accurately and confidently identifies LTPE volcanic sources in the Alaska-Aleutian arc using only in situ geochemistry. The model is a voting ensemble classifier comprised of six conceptually different machine learning algorithms trained on proximal tephra deposits that have had their source positively identified. We show that incompatible trace element ratios (e.g., Nb/U, Th/La, Rb/Sm) help produce a feature space that contains significantly more variance than one produced by major element concentrations, ultimately creating a model that can achieve high accuracy, precision, and recall on predicted volcanic sources, regardless of the perceived 2D data distribution (i.e., bimodal, uniform, normal) or composition (i.e., andesite, trachyte, rhyolite) of that source. Finally, we apply our model to unidentified distal marine tephra deposits in the region to better understand explosive volcanism in the Alaska-Aleutian arc, specifically its pre-Holocene spatiotemporal distribution.