Machine-learning techniques for geochemical discrimination of 2011 Tohoku tsunami deposits

Abstract

Geochemical discrimination has recently been recognised as a potentially useful proxy for identifying tsunami deposits in addition to classical proxies such as sedimentological and micropalaeontological evidence. However, difficulties remain because it is unclear which elements best discriminate between tsunami and non-tsunami deposits. Herein, we propose a mathematical methodology for the geochemical discrimination of tsunami deposits using machine-learning techniques. The proposed method can determine the appropriate combinations of elements and the precise discrimination plane that best discerns tsunami deposits from non-tsunami deposits in high-dimensional compositional space through the use of data sets of bulk composition that have been categorised as tsunami or non-tsunami sediments. We applied this method to the 2011 Tohoku tsunami and to background marine sedimentary rocks. After an exhaustive search of all 262,144 (= 218) combinations of the 18 analysed elements, we observed several tens of combinations with discrimination rates higher than 99.0%. The analytical results show that elements such as Ca and several heavy-metal elements are important for discriminating tsunami deposits from marine sedimentary rocks. These elements are considered to reflect the formation mechanism and origin of the tsunami deposits. The proposed methodology has the potential to aid in the identification of past tsunamis by using other tsunami proxies.

Involvement of Slab‐Derived Fluid in the Generation of Cenozoic Basalts in Northeast China Inferred From Machine Learning

“…Machine learning methods such as random forest (RF), sparse multinomial regression, support vector machine, and deep neural network (DNN) have started to find wide applications in Earth sciences (Kuwatani et al, 2014;Petrelli & Perugini, 2016;Rouet-Leduc et al, 2019;Ueki et al, 2017;Zhu et al, 2017). In this study, we apply supervised machine learning algorithms, RF, and DNN, to predict the origin of Cenozoic basalts in Northeast China.…”

Preface to the Special Issue on ^|^ldquo;Geochemistry and Environmental Science of Tsunami Deposits^|^rdquo;^|^mdash;I

“…However, we have to take one more step from the current reconstruction and recovery stages to a scientific consideration of tsunami deposits. Recently, Kuwatani et al （2014） proposed a novel geochemical discrimination diagram of tsunami deposits characterizing them in terms of geochemistry. We would be gratified if this special issue provides an opportunity to take this research further.…”

Classification of geochemical data based on multivariate statistical analyses: Complementary roles of cluster, principal component, and independent component analyses

“…These include linear regression, cluster analysis, discriminant analysis, principal component analysis, factor analysis, and independent component analysis: e.g., application to various petrological problems [ Le Maitre , ]; identification of mantle geochemical structures [ Zindler et al ., ; Allègre et al ., ; Hart et al ., ; White and Duncan , ; Iwamori and Albarède , ; Stracke , ]; classification and source identification of sediment [ Pisias et al ., ; Yasukawa et al ., ] or volcanic rocks [ Brandmeier and Wörner , ]; and rock‐tectonic setting association [ Agrawal et al ., ; Snow , ; Vermeesch , ; Verma et al ., ]. Additionally, advanced methods of supervised machine learning have been applied recently to identify Tsunami deposits [ Kuwatani et al ., ] and tectonic discrimination of igneous rocks based on PetDB and GEOROC databases [ Petrelli and Perugini , ].…”