Optimized gradient boosting models and reliability analysis for rock stiffness C13

IF 2.2 3区 地球科学 Q2 GEOSCIENCES, MULTIDISCIPLINARY Journal of Applied Geophysics Pub Date : 2024-09-11 DOI:10.1016/j.jappgeo.2024.105519
Tuan Nguyen-Sy
{"title":"Optimized gradient boosting models and reliability analysis for rock stiffness C13","authors":"Tuan Nguyen-Sy","doi":"10.1016/j.jappgeo.2024.105519","DOIUrl":null,"url":null,"abstract":"<div><p>The Extreme gradient boosting algorithm XGBoost has been confirmed to be an accurate method for predicting rock stiffnesses and anisotropic parameters from basic input features such as rock porosity, density, vertical compression stress, pore pressure and burial depth (Nguyen-Sy, T., To, Q.D., Vu, M.N., Nguyen, T.D. and Nguyen, T.T., 2020. Study the elastic properties and the anisotropy of rocks using different machine learning methods. Geophysical Prospecting, 68(8), 2557–2578). This study has the following contributions: reducing the R2-error score (that is, 1-R2) by 35 %, RMSE by 21 % and MAE by 16 % comparing to the previous study by considering an advanced CatXG hybrid boosting model in combination with the optimizer Optuna for predicting <span><math><msub><mi>C</mi><mn>13</mn></msub></math></span> (the most difficult stiffness to accurately predict); 2-conduct a reliability analysis for the predicted stiffness <span><math><msub><mi>C</mi><mn>13</mn></msub></math></span> with respect to the randomness of the input features. We also discuss the use of <span><math><msub><mi>C</mi><mn>11</mn></msub></math></span> or <span><math><msub><mi>C</mi><mn>33</mn></msub></math></span> as additional input features for accurately predicting <span><math><msub><mi>C</mi><mn>13</mn></msub></math></span> as well as the prediction of the related anisotropic parameter <span><math><mi>δ</mi></math></span>. This significant improvement of predicted stiffness <span><math><msub><mi>C</mi><mn>13</mn></msub></math></span> is extremely important because it encourages petrophysical engineers to use machine learning for predicting the elastic stiffnesses of rocks.</p></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"230 ","pages":"Article 105519"},"PeriodicalIF":2.2000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Applied Geophysics","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0926985124002350","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

The Extreme gradient boosting algorithm XGBoost has been confirmed to be an accurate method for predicting rock stiffnesses and anisotropic parameters from basic input features such as rock porosity, density, vertical compression stress, pore pressure and burial depth (Nguyen-Sy, T., To, Q.D., Vu, M.N., Nguyen, T.D. and Nguyen, T.T., 2020. Study the elastic properties and the anisotropy of rocks using different machine learning methods. Geophysical Prospecting, 68(8), 2557–2578). This study has the following contributions: reducing the R2-error score (that is, 1-R2) by 35 %, RMSE by 21 % and MAE by 16 % comparing to the previous study by considering an advanced CatXG hybrid boosting model in combination with the optimizer Optuna for predicting C13 (the most difficult stiffness to accurately predict); 2-conduct a reliability analysis for the predicted stiffness C13 with respect to the randomness of the input features. We also discuss the use of C11 or C33 as additional input features for accurately predicting C13 as well as the prediction of the related anisotropic parameter δ. This significant improvement of predicted stiffness C13 is extremely important because it encourages petrophysical engineers to use machine learning for predicting the elastic stiffnesses of rocks.

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
岩石刚度 C13 的优化梯度提升模型和可靠性分析
Extreme gradient boosting algorithm XGBoost 已被证实是根据岩石孔隙度、密度、垂直压缩应力、孔隙压力和埋深等基本输入特征预测岩石刚度和各向异性参数的精确方法(Nguyen-Sy, T., To, Q.D., Vu, M.N., Nguyen, T.D. and Nguyen, T.T., 2020.使用不同的机器学习方法研究岩石的弹性特性和各向异性。地球物理勘探,68(8),2557-2578)。本研究的贡献如下:1.通过将先进的 CatXG 混合提升模型与优化器 Optuna 结合用于预测 C13(最难准确预测的刚度),与之前的研究相比,R2-误差分值(即 1-R2)降低了 35%,RMSE 降低了 21%,MAE 降低了 16%;2.针对输入特征的随机性,对预测的刚度 C13 进行了可靠性分析。我们还讨论了使用 C11 或 C33 作为额外输入特征来准确预测 C13 以及预测相关各向异性参数 δ 的问题。
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
Journal of Applied Geophysics
Journal of Applied Geophysics 地学-地球科学综合
CiteScore
3.60
自引率
10.00%
发文量
274
审稿时长
4 months
期刊介绍: The Journal of Applied Geophysics with its key objective of responding to pertinent and timely needs, places particular emphasis on methodological developments and innovative applications of geophysical techniques for addressing environmental, engineering, and hydrological problems. Related topical research in exploration geophysics and in soil and rock physics is also covered by the Journal of Applied Geophysics.
期刊最新文献
Magnetic diagnosis model for heavy metal pollution in beach sediments of Qingdao, China An improved goal-oriented adaptive finite-element method for 3-D direct current resistivity anisotropic forward modeling using nested tetrahedra Deep learning-based geophysical joint inversion using partial channel drop method Advanced predictive modelling of electrical resistivity for geotechnical and geo-environmental applications using machine learning techniques Editorial Board
×
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