A neural network application to assess magma diversity in the Etendeka igneous province, Namibia

IF 1.2 4区 地球科学 Q2 GEOLOGY South African Journal of Geology Pub Date : 2021-05-31 DOI:10.25131/SAJG.124.0034
T. Owen-Smith, R. Trumbull, K. Bauer, J. Keiding, T. Will
{"title":"A neural network application to assess magma diversity in the Etendeka igneous province, Namibia","authors":"T. Owen-Smith, R. Trumbull, K. Bauer, J. Keiding, T. Will","doi":"10.25131/SAJG.124.0034","DOIUrl":null,"url":null,"abstract":"\n The geochemical discrimination of different magma types in Large Igneous Provinces is conventionally based on a few, pre-selected variables that are regarded to have petrological meaning. An alternative approach explored in this study is to apply the neural network technique of self-organising maps (SOM) to identify inherent groupings in data without knowledge or assumptions (unsupervised learning). The dataset used in this study comprises whole-rock analyses from extrusive (lava) and intrusive (dykes, sills) mafic suites in the Etendeka province, Namibia, taken from published sources and augmented by 103 new chemical analyses of dykes. Six SOM-classified groups are identified, which are unevenly distributed among the extrusive and the intrusive rock suites. The lava samples are dominated by just three of the six SOM groups (95% of all samples) and one group is absent entirely, whereas all six groups are present in the intrusive suite and five of them each comprise more than 5% of the samples. The geographic distribution of SOM-grouped dykes is heterogeneous and groups that are under-represented in the lava suite occur preferentially in a region of the pre-Etendeka basement where few lavas are preserved. Thus, the difference in magma diversity between intrusive and extrusive suites may be partly an artefact of erosion, which implies that a proper assessment of magma diversity in this and other LIPs must include the intrusive components.\n The correspondence of our SOM groupings with magma types in the Etendeka province that were established from petrologically defined variables is reasonably good for most trace-element abundances and ratios. However, some of the SOM groups have a wide range of initial Sr–Nd isotope ratios and a poor correspondence with the established magma types. We conclude that the SOM approach is useful for sorting out large and complex geochemical datasets but the method gives all input variables equal weight, which may be problematic if they have different responses to processes in the system under study (e.g., partial melting, fractional crystallisation, degassing, alteration). It is no substitute for expert petrological knowledge in discriminating genetically distinct magma types in an application like the present one.","PeriodicalId":49494,"journal":{"name":"South African Journal of Geology","volume":" ","pages":""},"PeriodicalIF":1.2000,"publicationDate":"2021-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"South African Journal of Geology","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.25131/SAJG.124.0034","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOLOGY","Score":null,"Total":0}
引用次数: 3

Abstract

The geochemical discrimination of different magma types in Large Igneous Provinces is conventionally based on a few, pre-selected variables that are regarded to have petrological meaning. An alternative approach explored in this study is to apply the neural network technique of self-organising maps (SOM) to identify inherent groupings in data without knowledge or assumptions (unsupervised learning). The dataset used in this study comprises whole-rock analyses from extrusive (lava) and intrusive (dykes, sills) mafic suites in the Etendeka province, Namibia, taken from published sources and augmented by 103 new chemical analyses of dykes. Six SOM-classified groups are identified, which are unevenly distributed among the extrusive and the intrusive rock suites. The lava samples are dominated by just three of the six SOM groups (95% of all samples) and one group is absent entirely, whereas all six groups are present in the intrusive suite and five of them each comprise more than 5% of the samples. The geographic distribution of SOM-grouped dykes is heterogeneous and groups that are under-represented in the lava suite occur preferentially in a region of the pre-Etendeka basement where few lavas are preserved. Thus, the difference in magma diversity between intrusive and extrusive suites may be partly an artefact of erosion, which implies that a proper assessment of magma diversity in this and other LIPs must include the intrusive components. The correspondence of our SOM groupings with magma types in the Etendeka province that were established from petrologically defined variables is reasonably good for most trace-element abundances and ratios. However, some of the SOM groups have a wide range of initial Sr–Nd isotope ratios and a poor correspondence with the established magma types. We conclude that the SOM approach is useful for sorting out large and complex geochemical datasets but the method gives all input variables equal weight, which may be problematic if they have different responses to processes in the system under study (e.g., partial melting, fractional crystallisation, degassing, alteration). It is no substitute for expert petrological knowledge in discriminating genetically distinct magma types in an application like the present one.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
神经网络在评估纳米比亚埃滕德卡火成岩省岩浆多样性中的应用
大火成岩省不同岩浆类型的地球化学区分通常是基于几个预先选择的变量,这些变量被认为具有岩石学意义。本研究探索的另一种方法是应用自组织映射(SOM)的神经网络技术在没有知识或假设(无监督学习)的情况下识别数据中的固有分组。本研究中使用的数据集包括来自纳米比亚Etendeka省的挤出(熔岩)和侵入(岩脉,岩脉)基性套件的全岩分析,这些数据来自已发表的资料,并增加了103个新的岩脉化学分析。识别出6个som分类群,它们在挤压岩套和侵入岩套之间分布不均匀。熔岩样品仅由6个SOM组中的3个占主导地位(占所有样品的95%),其中一个组完全不存在,而所有6个组都存在于侵入套件中,其中5个组各占样品的5%以上。som组岩脉的地理分布是不均匀的,在熔岩套中代表性不足的岩脉群优先出现在前etendeka基底地区,那里保存的熔岩很少。因此,岩浆多样性在侵入套和挤压套之间的差异可能部分是侵蚀作用的产物,这意味着对这一套和其他第三系岩浆多样性的适当评估必须包括侵入成分。我们的SOM分组与Etendeka省的岩浆类型的对应关系是由岩石学定义的变量建立的,对于大多数微量元素的丰度和比率来说是相当好的。然而,某些SOM群的初始Sr-Nd同位素比值范围较宽,与已建立的岩浆类型的对应性较差。我们得出的结论是,SOM方法对于整理大型和复杂的地球化学数据集是有用的,但该方法给予所有输入变量相同的权重,如果它们对所研究系统中的过程(例如,部分熔化,分数结晶,脱气,蚀变)有不同的响应,则可能存在问题。在像现在这样的应用中,它不能代替岩石学专家的知识来区分不同的岩浆类型。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
3.60
自引率
5.60%
发文量
18
审稿时长
>12 weeks
期刊介绍: The South African Journal of Geology publishes scientific papers, notes, stratigraphic descriptions and discussions in the broadly defined fields of geoscience that are related directly or indirectly to the geology of Africa. Contributions relevant to former supercontinental entities such as Gondwana and Rodinia are also welcome as are topical studies on any geoscience-related discipline. Review papers are welcome as long as they represent original, new syntheses. Special issues are also encouraged but terms for these must be negotiated with the Editors.
期刊最新文献
The Greater Cederberg–False Bay Large Igneous Province in South Africa: A southern node of widespread magmatism associated with South Atlantic rifting Dissolution of synthetic diamonds to produce morphologies similar to natural diamonds: an experimental study The geomorphology and neotectonics of the Vaalputs Radioactive Waste Disposal Facility site, Namaqualand, South Africa: Palaeoseismological and geodynamic implications Petrogenesis of the Marginal Sill Phase and Lower Zone in the Eastern Limb of the Bushveld Complex: Incremental development of igneous layering and syn-magmatic emplacement of peridotite intrusions and sills O- and H-isotope record of Cape Town rainfall from 1996 to 2022: the effect of increasing temperature, and the ‘water crisis’ of 2015 to 2018
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1