Discriminating Tectonic Setting of Igneous Rocks Using Biotite Major Element chemistry−A Machine Learning Approach

Abstract

Mineral chemistry is a widely used tool for identifying the tectonic setting of igneous rocks and for constraining past geodynamic environments. The major-trace element and isotopic composition of several minerals such as pyroxene, olivine, spinel, amphibole, chromite, and rutile have been extensively used for this purpose (e.g.,

Machine Learning Guided Strategies to Develop High Efficiency Indoor Perovskite Solar Cells

“…[ 22 ] It estimates the influence of each feature on the model predictions and the quantification of individual feature's contribution, grounded in cooperative game theory, represented by its SHAP value. [ 23 ] To better understand the intricate relationship between features (Δ H , Δ L , bandgap, illuminance value, and light source type) and the performance prediction parameters ( V OC , J SC , FF, and PCE), we employed density scatter plots representing Shapley values ( Figure ; Figure S4, Supporting Information for DTR and XGBoost model, respectively). In the context of our regression problem's feature importance bar plot, the features are ordered by their descending mean SHAP value or importance, with the most important features appearing first.…”

Machine Learning Developments and Applications in Solid‐Earth Geosciences: Fad or Future?

“…These are the problems that do not have existing accepted solutions, rely heavily on judgments of highly experienced experts, yet could lead to the most profound scientific insights if investigated properly. A few studies explore the promise of ML in multi‐disciplinary data integration for predicting drought behavior in the Colorado River Basin based on various Earth System Models (Talsma et al., 2022), for predicting sea surface variabilities in the South China Sea (Shao et al., 2021), for geothermal heat flow prediction from multiple geophysical and geological datasets (Lösing & Ebbing, 2021), for identifying volcano's transition from non‐eruptive to eruptive states (Manley et al., 2021), for understanding the geodynamic history using geochemical data (Jorgenson et al., 2022; X. Lin et al., 2022; X. Li & Zhang, 2022; Saha et al., 2021; Thomson et al., 2021; Y. Wang et al., 2021), and for characterizing geodetic signals by their sources (Hu et al., 2021). Albert (2022) uses an unsupervised deep NN structure to predict future atmospheric structures from past measurements to enable infrasound propagation modeling.…”

“…Lin et al, 2022;X. Li & Zhang, 2022;Saha et al, 2021;Thomson et al, 2021;, and for characterizing geodetic signals by their sources (Hu et al, 2021). Albert (2022) uses an unsupervised deep NN structure to predict future atmospheric structures from past measurements to enable infrasound propagation modeling.…”

Discrimination of Quartz Genesis Based on Explainable Machine Learning

“…In recent times, the progress in artificial intelligence has resulted in an increasing prevalence of machine learning techniques in geological research, particularly in the field of tectonic environment identification [19][20][21][22]. Research indicates that machine-learning algorithms exhibit good performance in feature analysis of rock samples from various tectonic environments [23,24]. However, these algorithms have limitations in recognizing ore deposits, including challenges in visualizing classification results and interpreting the models [25].…”

“…Random forest [31], XGBoost, and LightGBMbased quartz classifiers were designed to distinguish quartz samples from eight types of ore deposits, including epithermal, greisen, Carlin, porphyry, pegmatite, skarn, orogenic, and granite. All three methods were successfully applied to classify tectonic environments of rock samples [20,[22][23][24]32,33]. We employ the Shapley Additive Explanations (SHAP) [34] technique to interpret the quartz classification model.…”