A Machine Learning Based‐Approach to Predict the Water Content of Mid‐Ocean Ridge Basalts
Abstract Water is critical in the evolution of the mantle due to its strong influence on the physicochemical properties of mantle rocks. Mid‐ocean ridge basalts (MORBs) are commonly used to study the compositional characteristics of the convecting upper mantle. However, there remains abundant sample...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-07-01
|
| Series: | Geochemistry, Geophysics, Geosystems |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023GC010984 |
| _version_ | 1797637924444962816 |
|---|---|
| author | Jingjun Zhou Jia Liu Qunke Xia Cheng Su Takeshi Kuritani Eero Hanski |
| author_facet | Jingjun Zhou Jia Liu Qunke Xia Cheng Su Takeshi Kuritani Eero Hanski |
| author_sort | Jingjun Zhou |
| collection | DOAJ |
| description | Abstract Water is critical in the evolution of the mantle due to its strong influence on the physicochemical properties of mantle rocks. Mid‐ocean ridge basalts (MORBs) are commonly used to study the compositional characteristics of the convecting upper mantle. However, there remains abundant samples in the global MORB data sets without direct measurements of water contents. The commonly observed good correlation between H2O and other incompatible trace components, such as Ce, has been applied to quantify water contents of MORBs. However, this approach assumes constant H2O/Ce in the target samples, which is not always true as the H2O/Ce ratios of MORBs could be rather heterogeneous even in some short ridge segments. Utilizing the present compositional data of global MORB glasses with measured water contents (n = 1,467), we construct a Random Forest Regression model based on machine learning, which can predict water concentrations of samples based on selected major and trace element data, without assuming a ratio between H2O and other trace elements. This model allows us to precisely recover water contents for MORBs with comparable accuracy with traditional analytical methods. The predicted results of MORB glasses from this model (n = 1,931) expand the water content database of global MORBs and indicate a broad existence of high‐H2O MORBs. This new approach allows us to investigate the water content of MORBs from some ridges lacking previous water content measurements (e.g., the Chile Ridge and the Pacific‐Antarctic Ridge) and infer changes in the water content of MORB sources through applying the model to transform fault samples. |
| first_indexed | 2024-03-11T12:55:13Z |
| format | Article |
| id | doaj.art-15d7e5e2fbbc41649aee5b37327ee746 |
| institution | Directory Open Access Journal |
| issn | 1525-2027 |
| language | English |
| last_indexed | 2024-03-11T12:55:13Z |
| publishDate | 2023-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | Geochemistry, Geophysics, Geosystems |
| spelling | doaj.art-15d7e5e2fbbc41649aee5b37327ee7462023-11-03T17:01:15ZengWileyGeochemistry, Geophysics, Geosystems1525-20272023-07-01247n/an/a10.1029/2023GC010984A Machine Learning Based‐Approach to Predict the Water Content of Mid‐Ocean Ridge BasaltsJingjun Zhou0Jia Liu1Qunke Xia2Cheng Su3Takeshi Kuritani4Eero Hanski5Key Laboratory of Geoscience Big Data and Deep Resource of Zhejiang Province School of Earth Sciences Zhejiang University Hangzhou ChinaKey Laboratory of Geoscience Big Data and Deep Resource of Zhejiang Province School of Earth Sciences Zhejiang University Hangzhou ChinaKey Laboratory of Geoscience Big Data and Deep Resource of Zhejiang Province School of Earth Sciences Zhejiang University Hangzhou ChinaKey Laboratory of Geoscience Big Data and Deep Resource of Zhejiang Province School of Earth Sciences Zhejiang University Hangzhou ChinaGraduate School of Science Hokkaido University Sapporo JapanOulu Mining School University of Oulu Oulu FinlandAbstract Water is critical in the evolution of the mantle due to its strong influence on the physicochemical properties of mantle rocks. Mid‐ocean ridge basalts (MORBs) are commonly used to study the compositional characteristics of the convecting upper mantle. However, there remains abundant samples in the global MORB data sets without direct measurements of water contents. The commonly observed good correlation between H2O and other incompatible trace components, such as Ce, has been applied to quantify water contents of MORBs. However, this approach assumes constant H2O/Ce in the target samples, which is not always true as the H2O/Ce ratios of MORBs could be rather heterogeneous even in some short ridge segments. Utilizing the present compositional data of global MORB glasses with measured water contents (n = 1,467), we construct a Random Forest Regression model based on machine learning, which can predict water concentrations of samples based on selected major and trace element data, without assuming a ratio between H2O and other trace elements. This model allows us to precisely recover water contents for MORBs with comparable accuracy with traditional analytical methods. The predicted results of MORB glasses from this model (n = 1,931) expand the water content database of global MORBs and indicate a broad existence of high‐H2O MORBs. This new approach allows us to investigate the water content of MORBs from some ridges lacking previous water content measurements (e.g., the Chile Ridge and the Pacific‐Antarctic Ridge) and infer changes in the water content of MORB sources through applying the model to transform fault samples.https://doi.org/10.1029/2023GC010984machine learningMORBwater |
| spellingShingle | Jingjun Zhou Jia Liu Qunke Xia Cheng Su Takeshi Kuritani Eero Hanski A Machine Learning Based‐Approach to Predict the Water Content of Mid‐Ocean Ridge Basalts Geochemistry, Geophysics, Geosystems machine learning MORB water |
| title | A Machine Learning Based‐Approach to Predict the Water Content of Mid‐Ocean Ridge Basalts |
| title_full | A Machine Learning Based‐Approach to Predict the Water Content of Mid‐Ocean Ridge Basalts |
| title_fullStr | A Machine Learning Based‐Approach to Predict the Water Content of Mid‐Ocean Ridge Basalts |
| title_full_unstemmed | A Machine Learning Based‐Approach to Predict the Water Content of Mid‐Ocean Ridge Basalts |
| title_short | A Machine Learning Based‐Approach to Predict the Water Content of Mid‐Ocean Ridge Basalts |
| title_sort | machine learning based approach to predict the water content of mid ocean ridge basalts |
| topic | machine learning MORB water |
| url | https://doi.org/10.1029/2023GC010984 |
| work_keys_str_mv | AT jingjunzhou amachinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts AT jialiu amachinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts AT qunkexia amachinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts AT chengsu amachinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts AT takeshikuritani amachinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts AT eerohanski amachinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts AT jingjunzhou machinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts AT jialiu machinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts AT qunkexia machinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts AT chengsu machinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts AT takeshikuritani machinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts AT eerohanski machinelearningbasedapproachtopredictthewatercontentofmidoceanridgebasalts |