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

Abstract

The origin and involvement of fluid in the generation of Cenozoic basalts in Northeast China are still under debate. Here we apply the machine learning methods of random forest and deep neural network to train models using data sets of global island arc and ocean island basalts. The trained models predict that most Cenozoic basalts in Northeast China are influenced by fluid and that the fluid activity decreases from east to west. The boundary defined by fluid activity coincides with the westernmost edge of the present‐day stagnant Pacific slab determined by seismic tomography and with the geochemical boundary defined by magnesium isotopes. These observations support the view that the fluid involved in the generation of the basalts is controlled by the stagnant Pacific slab instead of driven by the plume induced by the sinking Izanagi Plate.

New Insights Into Potassic Intraplate Volcanism in Northeast China From Joint Tomography of Ambient Noise and Teleseismic Surface Waves

“…The background geodynamics of Northeast China since the late Mesozoic are dominated by convection within a big mantle wedge that is linked to the deep subduction and stagnation of the paleo‐Pacific plate (Wu et al., 2011). The widespread Cenozoic intraplate volcanism there is simultaneously interpreted as one of the manifestations that is tied to these processes (e.g., Liu et al., 2001; Zhao et al., 2019). Recent geochemical analyses on potassic basalts from the WEK volcanic belt have also postulated material involvement from the stagnant slab in the mantle transition zone (Tian et al., 2016; Wang et al., 2017).…”

A Test of the Hypothesis That Syn‐Collisional Felsic Magmatism Contributes to Continental Crustal Growth Via Deep Learning Modeling and Principal Component Analysis of Big Geochemical Datasets

“…That is to say that what features extracted by the classifier and/or regressor may have played a role in the machine learning task is unknown. In this situation, white‐box model (i.e., random forest) is normally simultaneously deployed to aid in interpretation (e.g., Zhao et al., 2019). In addition to this, (multivariate) statistical analysis like principal component analysis can be of great help to understand machine learning modeling as well (e.g., X. Lin et al., 2020).…”

Machine Learning for Source Identification of Dust on the Chinese Loess Plateau

“…PCA, which highlights inter-group differences and within-group similarities in a data set, is a powerful method for process discovery and pattern identification (Zhao et al, 2019). It discovers new linear combinations of the variables (elements) based on measures of association (correlation).…”

“…Machine learning allowing computers to handle new situations via analysis, self-training, observation, and experience has been successfully applied in the geosciences (Bergen et al, 2019). Zhao et al (2019) use random forest and deep neural network to predict the origin of Cenozoic basalts in Northeast China. Mousavi and Beroza (2020) design a regressor composed of convolutional and recurrent neural networks to estimate the earthquake magnitude.…”