Shuzhao Wu , Changfeng Jing , Sheng Yao , Tianyi Zhang , Gaoran Xu , Shuhui Gong , Sensen Wu , Zhenhong Du , KunFeng Qiu
{"title":"Precise discrimination of basalt tectonic settings via dual-stream model with geochemical element matrix and series learning","authors":"Shuzhao Wu , Changfeng Jing , Sheng Yao , Tianyi Zhang , Gaoran Xu , Shuhui Gong , Sensen Wu , Zhenhong Du , KunFeng Qiu","doi":"10.1016/j.chemgeo.2025.122746","DOIUrl":null,"url":null,"abstract":"<div><div>Precise discrimination of basalt tectonic settings serves as a crucial methodological approach for providing insights into Earth's history. To address the limitations of traditional discrimination methods, which include high subjectivity due to reliance on expert experience and restricted precision resulting from simplistic comparative analysis of geochemical elements, we developed an innovative discrimination model-the Element Matrix and Series Parallel Network (EMSPN). The model enhances the capacity of tectonic setting discrimination by integrating the correlation characteristics between geochemical elements and the sequential features of element reactivity, thereby obtaining more comprehensive lithogenetic information. Based on >39,000 geochemical analyses of basalts from 9 typical tectonic settings after the Archaean period, we conducted application demonstrations through preprocessing operations, including feature engineering, missing value imputation, and category balancing. The proposed model demonstrated superior performance across multiple evaluation methods, achieving an overall discrimination accuracy of 88 %. This study compared the proposed model with four traditional machine learning models as baseline methods, and the results showed that the model outperformed other traditional machine learning models in overall discrimination accuracy across 9 tectonic settings. Additionally, in ablation experiments, by systematically removing key components of the EMSPN, the results validated the model design's rationality and confirmed each module's importance in information extraction and feature learning. Using the SHapley Additive exPlanations (SHAP) method, we analyzed and discussed the importance of different elements in discrimination results and the geochemical characteristics across various tectonic settings. When applied to controversial Archaean basalt samples, the results confirm the conclusions from traditional geochemical analysis methods, demonstrating the model's geological reliability and practical significance. This research provides a reliable technical approach for the field of lithogeochemistry and retrieves geodynamic information through tectonic setting discrimination, contributing to more accurate reconstruction of Earth's tectonic history.</div></div>","PeriodicalId":9847,"journal":{"name":"Chemical Geology","volume":"682 ","pages":"Article 122746"},"PeriodicalIF":3.6000,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chemical Geology","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0009254125001366","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GEOCHEMISTRY & GEOPHYSICS","Score":null,"Total":0}
引用次数: 0
Abstract
Precise discrimination of basalt tectonic settings serves as a crucial methodological approach for providing insights into Earth's history. To address the limitations of traditional discrimination methods, which include high subjectivity due to reliance on expert experience and restricted precision resulting from simplistic comparative analysis of geochemical elements, we developed an innovative discrimination model-the Element Matrix and Series Parallel Network (EMSPN). The model enhances the capacity of tectonic setting discrimination by integrating the correlation characteristics between geochemical elements and the sequential features of element reactivity, thereby obtaining more comprehensive lithogenetic information. Based on >39,000 geochemical analyses of basalts from 9 typical tectonic settings after the Archaean period, we conducted application demonstrations through preprocessing operations, including feature engineering, missing value imputation, and category balancing. The proposed model demonstrated superior performance across multiple evaluation methods, achieving an overall discrimination accuracy of 88 %. This study compared the proposed model with four traditional machine learning models as baseline methods, and the results showed that the model outperformed other traditional machine learning models in overall discrimination accuracy across 9 tectonic settings. Additionally, in ablation experiments, by systematically removing key components of the EMSPN, the results validated the model design's rationality and confirmed each module's importance in information extraction and feature learning. Using the SHapley Additive exPlanations (SHAP) method, we analyzed and discussed the importance of different elements in discrimination results and the geochemical characteristics across various tectonic settings. When applied to controversial Archaean basalt samples, the results confirm the conclusions from traditional geochemical analysis methods, demonstrating the model's geological reliability and practical significance. This research provides a reliable technical approach for the field of lithogeochemistry and retrieves geodynamic information through tectonic setting discrimination, contributing to more accurate reconstruction of Earth's tectonic history.
期刊介绍:
Chemical Geology is an international journal that publishes original research papers on isotopic and elemental geochemistry, geochronology and cosmochemistry.
The Journal focuses on chemical processes in igneous, metamorphic, and sedimentary petrology, low- and high-temperature aqueous solutions, biogeochemistry, the environment and cosmochemistry.
Papers that are field, experimentally, or computationally based are appropriate if they are of broad international interest. The Journal generally does not publish papers that are primarily of regional or local interest, or which are primarily focused on remediation and applied geochemistry.
The Journal also welcomes innovative papers dealing with significant analytical advances that are of wide interest in the community and extend significantly beyond the scope of what would be included in the methods section of a standard research paper.