@article{0685edd9b58447fcba9b41c27bff5116,
title = "Machine learning classifiers for attributing tephra to source volcanoes: an evaluation of methods for Alaska tephras",
abstract = "Glass composition-based correlations of volcanic ash (tephra) traditionally rely on extensive manual plotting. Many previous statistical methods for testing correlations are limited by using geochemical means, masking diagnostic variability. We suggest that machine learning classifiers can expedite correlation, quickly narrowing the list of likely candidates using well-trained models. Eruptives from Alaska's Aleutian Arc-Alaska Peninsula and Wrangell volcanic field were used as a test environment for 11 supervised classification algorithms, trained on nearly 2000 electron probe microanalysis measurements of glass major oxides, representing 10 volcanic sources. Artificial neural networks and random forests were consistently among the top-performing learners (accuracy and kappa > 0.96). Their combination as an average ensemble effectively improves their performance. Using this combined model on tephras from Eklutna Lake, south-central Alaska, showed that predictions match traditional methods and can speed correlation. Although classifiers are useful tools, they should aid expert analysis, not replace it. The Eklutna Lake tephras are mostly from Redoubt Volcano. Besides tephras from known Holocene-active sources, Holocene tephra geochemically consistent with Pleistocene Emmons Lake Volcanic Center (Dawson tephra), but from a yet unknown source, is evident. These tephras are mostly anchored by a highly resolved varved chronology and represent new important regional stratigraphic markers.",
keywords = "Alaska, classification, glass geochemistry, machine learning, tephra",
author = "Bolton, {Matthew S.M.} and Jensen, {Britta J.L.} and Kristi Wallace and Nore Praet and David Fortin and Darrell Kaufman and {De Batist}, Marc",
note = "Funding Information: This research was funded in part by a Research Foundation – Flanders (FWO‐Vlaanderen) grant (G042812N) to M De Batist, an NSF award (1602106) to D. Kaufman and D. Fortin, a Natural Sciences and Engineering Research Council (NSERC) Discovery Grant to B. J. L. Jensen, and an NSERC Canada Graduate Scholarship‐Master's (CGS M) to M. S. M. Bolton. We thank three anonymous reviewers and Roger Denlinger (U.S. Geological Survey) for their insightful and constructive comments that greatly benefitted this paper. We also thank the numerous researchers who contributed to this work by putting in many hours in the field, lab, operating the microprobe, and entering data into databases. Without their hard work, glass compositional studies and comparisons such as this would be impossible. Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government. Funding Information: This research was funded in part by a Research Foundation – Flanders (FWO-Vlaanderen) grant (G042812N) to M De Batist, an NSF award (1602106) to D. Kaufman and D. Fortin, a Natural Sciences and Engineering Research Council (NSERC) Discovery Grant to B. J. L. Jensen, and an NSERC Canada Graduate Scholarship-Master's (CGS M) to M. S. M. Bolton. We thank three anonymous reviewers and Roger Denlinger (U.S. Geological Survey) for their insightful and constructive comments that greatly benefitted this paper. We also thank the numerous researchers who contributed to this work by putting in many hours in the field, lab, operating the microprobe, and entering data into databases. Without their hard work, glass compositional studies and comparisons such as this would be impossible. Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government. Publisher Copyright: Copyright {\textcopyright} 2019 John Wiley & Sons, Ltd.",
year = "2020",
month = jan,
day = "1",
doi = "10.1002/jqs.3170",
language = "English (US)",
volume = "35",
pages = "81--92",
journal = "Journal of Quaternary Science",
issn = "0267-8179",
publisher = "John Wiley and Sons Ltd",
number = "1-2",
}