Olivine in picrites from continental flood basalt provinces classified using machine learning
Picrites, dominantly composed of highly forsteritic olivine, can serve as important constraints on primary magma composition and eruption dynamic processes in global continental flood basalt (CFB) provinces. Picrites are commonly divided into high-Ti and low-Ti groups based on whole-rock TiO2 conten...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/163906 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-163906 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1639062022-12-21T07:30:58Z Olivine in picrites from continental flood basalt provinces classified using machine learning Cheng, Lilu Wang, Yu Yang, Zongfeng Earth Observatory of Singapore Science::Geology Olivine Machine Learning Picrites, dominantly composed of highly forsteritic olivine, can serve as important constraints on primary magma composition and eruption dynamic processes in global continental flood basalt (CFB) provinces. Picrites are commonly divided into high-Ti and low-Ti groups based on whole-rock TiO2 content or Ti/Y ratio. Here, we use an artificial neural network (ANN) to classify the individual olivine in picrites from global CFB provinces according to whether their parental magma is high-Ti or low-Ti to better understand the primary origin and magmatic processes. After training the ANN on 1000 olivine major element compositions data points, the network was able to differentiate chemical patterns for high-Ti and low-Ti olivine and classify olivine into correct types with an accuracy of >95%. Moreover, we find that two types of olivine mix in some single samples from Etendeka, Emeishan, and Karoo CFB provinces. Combining the results with chemical markers of source lithology, we suggest that the two types of olivine originate from two different sources and their olivine populations mixed during the ascent. This mixing then makes the spatial and temporal variation of picrites types in some CFB provinces unclear. Ministry of Education (MOE) National Research Foundation (NRF) This research was supported by the National Basic Research Program of China (973 Program NO. 2011CB808901) and the National Research Foundation of Singapore and the Singapore Ministry of Education under the Research Centres of Excellence initiative, and a National Research Foundation Singapore Investigatorship Award (NRF-NRFI2017-06). 2022-12-21T07:30:58Z 2022-12-21T07:30:58Z 2022 Journal Article Cheng, L., Wang, Y. & Yang, Z. (2022). Olivine in picrites from continental flood basalt provinces classified using machine learning. American Mineralogist, 107(6), 1045-1052. https://dx.doi.org/10.2138/am-2022-8083 0003-004X https://hdl.handle.net/10356/163906 10.2138/am-2022-8083 2-s2.0-85131182114 6 107 1045 1052 en NRF-NRFI2017-06 American Mineralogist © 2022 Mineralogical Society of America. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Science::Geology Olivine Machine Learning |
spellingShingle |
Science::Geology Olivine Machine Learning Cheng, Lilu Wang, Yu Yang, Zongfeng Olivine in picrites from continental flood basalt provinces classified using machine learning |
description |
Picrites, dominantly composed of highly forsteritic olivine, can serve as important constraints on primary magma composition and eruption dynamic processes in global continental flood basalt (CFB) provinces. Picrites are commonly divided into high-Ti and low-Ti groups based on whole-rock TiO2 content or Ti/Y ratio. Here, we use an artificial neural network (ANN) to classify the individual olivine in picrites from global CFB provinces according to whether their parental magma is high-Ti or low-Ti to better understand the primary origin and magmatic processes. After training the ANN on 1000 olivine major element compositions data points, the network was able to differentiate chemical patterns for high-Ti and low-Ti olivine and classify olivine into correct types with an accuracy of >95%. Moreover, we find that two types of olivine mix in some single samples from Etendeka, Emeishan, and Karoo CFB provinces. Combining the results with chemical markers of source lithology, we suggest that the two types of olivine originate from two different sources and their olivine populations mixed during the ascent. This mixing then makes the spatial and temporal variation of picrites types in some CFB provinces unclear. |
author2 |
Earth Observatory of Singapore |
author_facet |
Earth Observatory of Singapore Cheng, Lilu Wang, Yu Yang, Zongfeng |
format |
Article |
author |
Cheng, Lilu Wang, Yu Yang, Zongfeng |
author_sort |
Cheng, Lilu |
title |
Olivine in picrites from continental flood basalt provinces classified using machine learning |
title_short |
Olivine in picrites from continental flood basalt provinces classified using machine learning |
title_full |
Olivine in picrites from continental flood basalt provinces classified using machine learning |
title_fullStr |
Olivine in picrites from continental flood basalt provinces classified using machine learning |
title_full_unstemmed |
Olivine in picrites from continental flood basalt provinces classified using machine learning |
title_sort |
olivine in picrites from continental flood basalt provinces classified using machine learning |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/163906 |
_version_ |
1753801166574059520 |