基于树的日本和印度尼西亚位移率和变形模式特征异常检测

IF 2.8 4区 地球科学 Q2 GEOCHEMISTRY & GEOPHYSICS
Adi Wibowo , Satriawan Rasyid Purnama , Cecep Pratama , Leni Sophia Heliani , David P. Sahara , Sidik Tri Wibowo
{"title":"基于树的日本和印度尼西亚位移率和变形模式特征异常检测","authors":"Adi Wibowo ,&nbsp;Satriawan Rasyid Purnama ,&nbsp;Cecep Pratama ,&nbsp;Leni Sophia Heliani ,&nbsp;David P. Sahara ,&nbsp;Sidik Tri Wibowo","doi":"10.1016/j.geog.2022.07.003","DOIUrl":null,"url":null,"abstract":"<div><p>Research on strain anomalies and large earthquakes based on temporal and spatial crustal activities has been rapidly growing due to data availability, especially in Japan and Indonesia. However, many research works used local-scale case studies that focused on a specific earthquake characteristic using knowledge-driven techniques, such as crustal deformation analysis. In this study, a data-driven-based analysis is used to detect anomalies using displacement rates and deformation pattern features extracted from daily global navigation satellite system (GNSS) data using a machine learning algorithm. The GNSS data with 188 and 1181 continuously operating reference stations from Indonesia and Japan, respectively, are used to identify the anomaly of recent major earthquakes in the last two decades. Feature displacement rates and deformation patterns are processed in several window times with 2560 experiment scenarios to produce the best detection using tree-based algorithms. Tree-based algorithms with a single estimator (decision tree), ensemble bagging (bagging, random forest and Extra Trees), and ensemble boosting (AdaBoost, gradient boosting, LGBM, and XGB) are applied in the study. The experiment test using real-time scenario GNSSdailydatareveals high F1-scores and accuracy for anomaly detection using slope windowing 365 and 730 days of 91-day displacement rates and then 7-day deformation pattern features in tree-based algorithms. The results show the potential for medium-term anomaly detection using GNSS data without the need for multiple vulnerability assessments.</p></div>","PeriodicalId":46398,"journal":{"name":"Geodesy and Geodynamics","volume":"14 2","pages":"Pages 150-162"},"PeriodicalIF":2.8000,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Anomaly detection on displacement rates and deformation pattern features using tree-based algorithm in Japan and Indonesia\",\"authors\":\"Adi Wibowo ,&nbsp;Satriawan Rasyid Purnama ,&nbsp;Cecep Pratama ,&nbsp;Leni Sophia Heliani ,&nbsp;David P. Sahara ,&nbsp;Sidik Tri Wibowo\",\"doi\":\"10.1016/j.geog.2022.07.003\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Research on strain anomalies and large earthquakes based on temporal and spatial crustal activities has been rapidly growing due to data availability, especially in Japan and Indonesia. However, many research works used local-scale case studies that focused on a specific earthquake characteristic using knowledge-driven techniques, such as crustal deformation analysis. In this study, a data-driven-based analysis is used to detect anomalies using displacement rates and deformation pattern features extracted from daily global navigation satellite system (GNSS) data using a machine learning algorithm. The GNSS data with 188 and 1181 continuously operating reference stations from Indonesia and Japan, respectively, are used to identify the anomaly of recent major earthquakes in the last two decades. Feature displacement rates and deformation patterns are processed in several window times with 2560 experiment scenarios to produce the best detection using tree-based algorithms. Tree-based algorithms with a single estimator (decision tree), ensemble bagging (bagging, random forest and Extra Trees), and ensemble boosting (AdaBoost, gradient boosting, LGBM, and XGB) are applied in the study. The experiment test using real-time scenario GNSSdailydatareveals high F1-scores and accuracy for anomaly detection using slope windowing 365 and 730 days of 91-day displacement rates and then 7-day deformation pattern features in tree-based algorithms. The results show the potential for medium-term anomaly detection using GNSS data without the need for multiple vulnerability assessments.</p></div>\",\"PeriodicalId\":46398,\"journal\":{\"name\":\"Geodesy and Geodynamics\",\"volume\":\"14 2\",\"pages\":\"Pages 150-162\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2023-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Geodesy and Geodynamics\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1674984722000702\",\"RegionNum\":4,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"GEOCHEMISTRY & GEOPHYSICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Geodesy and Geodynamics","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1674984722000702","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOCHEMISTRY & GEOPHYSICS","Score":null,"Total":0}
引用次数: 1

摘要

基于时空地壳活动的应变异常和大地震研究由于数据的可用性而迅速发展,特别是在日本和印度尼西亚。然而,许多研究工作使用了局部尺度的案例研究,这些案例研究使用知识驱动的技术,例如地壳变形分析,专注于特定的地震特征。在本研究中,使用基于数据驱动的分析,利用机器学习算法从每日全球导航卫星系统(GNSS)数据中提取的位移率和变形模式特征来检测异常。利用印度尼西亚和日本的188个连续运行参考站和1181个连续运行参考站的GNSS数据,对近20年来的大地震进行了异常识别。在2560个实验场景下,在多个窗口时间内处理特征位移率和变形模式,以使用基于树的算法产生最佳检测。研究中应用了基于树的单估计器(决策树)、集成bagging (bagging、random forest和Extra Trees)和集成boosting (AdaBoost、梯度boosting、LGBM和XGB)算法。利用实时场景gnssdaily数据进行的实验测试表明,在基于树的算法中,基于91天位移率和7天变形模式特征的斜率窗分别为365天和730天,可以获得较高的f1分和精度。结果表明,使用GNSS数据进行中期异常检测的潜力,而无需进行多次漏洞评估。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Anomaly detection on displacement rates and deformation pattern features using tree-based algorithm in Japan and Indonesia

Research on strain anomalies and large earthquakes based on temporal and spatial crustal activities has been rapidly growing due to data availability, especially in Japan and Indonesia. However, many research works used local-scale case studies that focused on a specific earthquake characteristic using knowledge-driven techniques, such as crustal deformation analysis. In this study, a data-driven-based analysis is used to detect anomalies using displacement rates and deformation pattern features extracted from daily global navigation satellite system (GNSS) data using a machine learning algorithm. The GNSS data with 188 and 1181 continuously operating reference stations from Indonesia and Japan, respectively, are used to identify the anomaly of recent major earthquakes in the last two decades. Feature displacement rates and deformation patterns are processed in several window times with 2560 experiment scenarios to produce the best detection using tree-based algorithms. Tree-based algorithms with a single estimator (decision tree), ensemble bagging (bagging, random forest and Extra Trees), and ensemble boosting (AdaBoost, gradient boosting, LGBM, and XGB) are applied in the study. The experiment test using real-time scenario GNSSdailydatareveals high F1-scores and accuracy for anomaly detection using slope windowing 365 and 730 days of 91-day displacement rates and then 7-day deformation pattern features in tree-based algorithms. The results show the potential for medium-term anomaly detection using GNSS data without the need for multiple vulnerability assessments.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Geodesy and Geodynamics
Geodesy and Geodynamics GEOCHEMISTRY & GEOPHYSICS-
CiteScore
4.40
自引率
4.20%
发文量
566
审稿时长
69 days
期刊介绍: Geodesy and Geodynamics launched in October, 2010, and is a bimonthly publication. It is sponsored jointly by Institute of Seismology, China Earthquake Administration, Science Press, and another six agencies. It is an international journal with a Chinese heart. Geodesy and Geodynamics is committed to the publication of quality scientific papers in English in the fields of geodesy and geodynamics from authors around the world. Its aim is to promote a combination between Geodesy and Geodynamics, deepen the application of Geodesy in the field of Geoscience and quicken worldwide fellows'' understanding on scientific research activity in China. It mainly publishes newest research achievements in the field of Geodesy, Geodynamics, Science of Disaster and so on. Aims and Scope: new theories and methods of geodesy; new results of monitoring and studying crustal movement and deformation by using geodetic theories and methods; new ways and achievements in earthquake-prediction investigation by using geodetic theories and methods; new results of crustal movement and deformation studies by using other geologic, hydrological, and geophysical theories and methods; new results of satellite gravity measurements; new development and results of space-to-ground observation technology.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信