Source: Geochemistry, Geophysics, Geosystems
With dozens of active volcanoes in the Alaska-Aleutian region, it can be extremely challenging to identify the source volcano of a distal ash deposit. This limits the utility of marine sediment cores, even though they record numerous ash layers, for evaluating the hazard associated with each volcano. Especially in cases where the proximal record is short and fragmentary, an accurate and fast classification of such ash layers by source enables determination of the sizes and frequencies of past eruptions over a longer time scale and hence better forecasting of future eruptions.
Lubbers et al.  examine whether the major element or the trace element composition of ash fragments forms a more sensitive indicator and then develop a model based on an ensemble of machine learning strategies that uses ash trace element measurements to match layers to source volcanoes. The model is trained with the relatively short Holocene record of proximal deposits whose source volcanoes are known. It is then applied to reveal, over a much longer timescale, which volcanoes most often produce large explosive eruptions that may constitute major regional hazards.
Citation: Lubbers, J., Loewen, M., Wallace, K., Coombs, M., & Addison, J. (2023). Probabilistic source classification of large tephra producing eruptions using supervised machine learning: An example from the Alaska-Aleutian arc. Geochemistry, Geophysics, Geosystems, 24, e2023GC011037. https://doi.org/10.1029/2023GC011037
—Paul Asimow, Editor, G-Cubed