Explainable machine learning for labquake prediction using catalog-driven features

被引:12
|
作者
Karimpouli, Sadegh [1 ]
Caus, Danu [2 ,3 ,4 ]
Grover, Harsh [2 ,3 ,4 ]
Martinez-Garzon, Patricia [1 ]
Bohnhoff, Marco [1 ,5 ]
Beroza, Gregory C. [6 ]
Dresen, Georg [1 ,7 ]
Goebel, Thomas [8 ]
Weigel, Tobias [2 ,3 ,4 ]
Kwiatek, Grzegorz [1 ]
机构
[1] GFZ German Res Ctr Geosci, Helmholtz Ctr Potsdam, Potsdam, Germany
[2] DKRZ German Climate Comp Ctr, Hamburg, Germany
[3] Helmholtz Ctr Hereon, Geesthacht, Germany
[4] Helmholtz Forschungszentrum, Geesthacht, Germany
[5] Free Univ Berlin, Dept Earth Sci, Berlin, Germany
[6] Stanford Univ, Dept Geophys, Stanford, CA USA
[7] Univ Potsdam, Inst Earth & Environm Sci, Potsdam, Germany
[8] Univ Memphis, Ctr Earthquake Res & Informat, Memphis, TN 38152 USA
基金
欧洲研究理事会;
关键词
labquake prediction; explainable ML; catalog-driven features; time to failure; B-VALUE; STRAIN-RATE; EARTHQUAKES; SEISMICITY; MAGNITUDE; EVOLUTION; INVERSION; NETWORKS; FRICTION; INSIGHTS;
D O I
10.1016/j.epsl.2023.118383
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Recently, Machine learning (ML) has been widely utilized for laboratory earthquake (labquake) prediction using various types of data. This study pioneers in time to failure (TTF) prediction based on ML using acoustic emission (AE) records from three laboratory stick-slip experiments performed on Westerly granite samples with naturally fractured rough faults, more similar to the heterogeneous fault structures in the nature. 47 catalog-driven seismo-mechanical and statistical features are extracted introducing some new features based on focal mechanism. A regression voting ensemble of Long-Short Term Memory (LSTM) networks predicts TTF with a coefficient of determination (R2) of 70% on the test dataset. Feature importance analysis revealed that AE rate, correlation integral, event proximity, and focal mechanism-based features are the most important features for TTF prediction. Results reveal that the network uses all information among the features for prediction, including general trends in high correlated features as well as fine details about local variations and fault evolution involved in low correlated features. Therefore, some highly correlated and physically meaningful features may be considered less important for TTF prediction due to their correlation with other important features. Our study provides a ground for applying catalog-driven to constrain TTF of complex heterogeneous rough faults, which is capable to be developed for real application.(c) 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC license (http://creativecommons .org /licenses /by-nc /4 .0/).
引用
收藏
页数:11
相关论文
共 50 条
  • [31] Nondestructive Prediction of Eggshell Thickness Using NIR Spectroscopy and Machine Learning with Explainable AI
    Ahmed, Md Wadud
    Alam, Sreezan
    Khaliduzzaman, Alin
    Emmert, Jason Lee
    Kamruzzaman, Mohammed
    ACS FOOD SCIENCE & TECHNOLOGY, 2025, 5 (02): : 822 - 832
  • [32] Explainable Heart Disease Prediction Using Ensemble-Quantum Machine Learning Approach
    Abdulsalam, Ghada
    Meshoul, Souham
    Shaiba, Hadil
    INTELLIGENT AUTOMATION AND SOFT COMPUTING, 2023, 36 (01): : 761 - 779
  • [33] Prediction of caregiver quality of life in amyotrophic lateral sclerosis using explainable machine learning
    Anna Markella Antoniadi
    Miriam Galvin
    Mark Heverin
    Orla Hardiman
    Catherine Mooney
    Scientific Reports, 11
  • [34] Accurate prediction of concrete compressive strength based on explainable features using deep learning
    Zeng, Ziyue
    Zhu, Zheyu
    Yao, Wu
    Wang, Zhongping
    Wang, Changying
    Wei, Yongqi
    Wei, Zhenhua
    Guan, Xingquan
    CONSTRUCTION AND BUILDING MATERIALS, 2022, 329
  • [35] Prediction of caregiver quality of life in amyotrophic lateral sclerosis using explainable machine learning
    Antoniadi, Anna Markella
    Galvin, Miriam
    Heverin, Mark
    Hardiman, Orla
    Mooney, Catherine
    SCIENTIFIC REPORTS, 2021, 11 (01)
  • [36] In Silico Prediction of Chemical Acute Dermal Toxicity Using Explainable Machine Learning Methods
    Lou, Shang
    Yu, Zhuohang
    Huang, Zejun
    Wang, Haoqiang
    Pan, Fei
    Li, Weihua
    Liu, Guixia
    Tang, Yun
    CHEMICAL RESEARCH IN TOXICOLOGY, 2024, 37 (03) : 513 - 524
  • [37] Enhancing Fall Risk prediction In Chinese Older Adults Using Explainable Machine Learning
    Gu, Linda
    Li, Ming
    Shao, Jianchong
    Wang, Xing
    Zhang, Shaoliang
    MEDICINE & SCIENCE IN SPORTS & EXERCISE, 2024, 56 (10) : 106 - 107
  • [38] Explainable machine learning models for corn yield prediction using UAV multispectral data☆
    Kumar, Chandan
    Dhillon, Jagman
    Huang, Yanbo
    Reddy, Krishna
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2025, 231
  • [39] Explainable Remaining Tool Life Prediction for Individualized Production Using Automated Machine Learning
    Krupp, Lukas
    Wiede, Christian
    Friedhoff, Joachim
    Grabmaier, Anton
    SENSORS, 2023, 23 (20)
  • [40] Risk Prediction of Diabetic Foot Amputation Using Machine Learning and Explainable Artificial Intelligence
    Oei, Chien Wei
    Chan, Yam Meng
    Zhang, Xiaojin
    Leo, Kee Hao
    Yong, Enming
    Chong, Rhan Chaen
    Hong, Qiantai
    Zhang, Li
    Pan, Ying
    Tan, Glenn Wei Leong
    Mak, Malcolm Han Wen
    JOURNAL OF DIABETES SCIENCE AND TECHNOLOGY, 2024,