机器学习在地幔地球化学研究中的应用  

Applications of machine learning in mantle geochemistry research

作　　者：张舟 夏群科 ZHANG Zhou;XIA Qun-ke(Key Laboratory of Geoscience Big Data and Deep Resource of Zhejiang Province,School of Earth Sciences,Zhejiang University,Hangzhou 310058,China)

机构地区：[1]浙江省地学大数据与地球深部资源重点实验室,浙江大学地球科学学院,杭州310058

出　　处：《矿物岩石地球化学通报》2023年第1期1-12,共12页Bulletin of Mineralogy, Petrology and Geochemistry

基　　金：中央高校基本科研业务费专项资金资助(K20210168)。

摘　　要：高温高压条件下的热力学平衡是开展地幔地球化学研究的重要基础。目前,对地幔条件下矿物和熔体的热力学平衡的认识还存在一些不足,即地幔地球化学的实验和天然样品数据(压强、温度和成分等)构成的高维度矩阵中离散点之间的关系还未被充分厘清。机器学习是挖掘数据的有效工具,通过回归、分类等算法,可以为地幔条件下的热力学平衡提供新认识。已开展的实例研究包括温压计、熔体中元素的溶解度、矿物的三价铁含量、判断地幔捕掳体是否发生交代作用、判断样品是否发生氢扩散作用,等等。本研究方向的发展还需要机器学习方法的普及、基础数据库正确率和数据质量的提高以及算法的改进。Thermodynamic equilibrium under high-pressure and high-temperature conditions are crucial for mantle geochemistry research. At present, there is still a lack of understanding of the thermodynamic equilibrium of minerals and melts under mantle conditions. The mantle geochemical data(pressure, temperature, and chemical compositions) are scattering points in high dimensional space. Machine learning is an effective approach to exploring the correlation of the scattering points in high space. Machine learning application includes geothermobarometer, elemental solubility in melts, ferric iron content in minerals, discrimination of mantle xenoliths with or without metasomatism, and discrimination of samples with or without hydrogen diffusion, etc. Development of this research direction requires a broader application of machine learning, enhancement of data accuracy rate in cyberinfrastructures, improvement of data quality, and modification of algorithms.

关 键 词：机器学习 热力学 地幔地球化学 

分 类 号：P591[天文地球—地球化学] P595[天文地球—地质学] P599