Detachment of the Subducting Slab in Ancient Subduction Zones Discerned Using Machine Learning
Abstract Identification of complex geochemical signatures of basalts from various tectonic settings using trace elements contents is still challenging due to uncertainties in existing classification diagrams and machine‐learning attempts. To address this, we trained a machine‐learning model using a random forest classifier on trace element concentrations of a global basalt‐dataset, categorized by types of tectonic plate boundary—destructive or constructive—at which they formed. Achieving an accuracy exceeding 98%, the model efficiently extracts the distinctive characteristics from each basalt type. When applied to the Bangong‐Nujiang suture zone in central Tibet, the model reveals that the basalts exhibited features of both boundary types prior to 108–107 Ma before transitioning to solely destructive characteristics. This transition is likely to be caused by the detachment of a descending oceanic slab, aligning with existing geological evidence. This case study highlights the promising potential of machine learning models, trained on simplified basalt types, in more accurately tracing lithospheric evolution.
Authors
- Yunchuan Zeng (ORCID: https://orcid.org/0000-0002-9701-9693)
- Alexander R.L. Nichols (ORCID: https://orcid.org/0000-0002-8298-2882)
- Anlin Ma
- Feng Zi (ORCID: https://orcid.org/0000-0003-0455-4345)
- Quan Ou
- Jia Liao
- Sheng‐Ping Qian (ORCID: https://orcid.org/0000-0003-1750-6027)
- Zongying Huang (ORCID: https://orcid.org/0000-0003-0645-6597)
- Dan Zheng (ORCID: https://orcid.org/0000-0002-4310-8121)
- Z.‐Q. Hou (ORCID: https://orcid.org/0009-0009-5040-9158)
- Kun Wang (ORCID: https://orcid.org/0009-0006-7995-3796)
Institutions
- Hunan University of Science and Technology (CN)
- University of Canterbury (NZ)
- Chinese Academy of Sciences (CN)
- Ministry of Natural Resources (CN)
- China University of Mining and Technology (CN)
- China Geological Survey (CN)
- Guangzhou Institute of Geochemistry (CN)
- China University of Geosciences (Beijing) (CN)
- Chengdu University of Technology (CN)
- State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation (CN)
- Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou) (CN)
- Nanjing University (CN)
Publication Details
- Journal
- Journal of Geophysical Research Machine Learning and Computation
- Published
- 2024-12-01
- DOI
- https://doi.org/10.1029/2024jh000400
- Citations
- 1
- Primary Topic
- Geochemistry and Geologic Mapping
- Type
- article
- Field-Weighted Citation Impact
- 0.35
Funders
- National Natural Science Foundation of China
- Chengdu University of Technology
- Chengdu University
- Natural Science Foundation of Sichuan Province