PDF Download HTML

[1]ZHAO Xiaoyan,JIANG Haikun,MENG Lingyuan,et al.Research on the Importance of Feature Parameters in Seismic Sequence Type Determination in Sichuan-Yannan Region Based on Decision Tree[J].Journal of Seismological Research,2024,47(03):321-335.[doi:10.20015/j.cnki.ISSN1000-0666.2024.0039 ]

Copy

Research on the Importance of Feature Parameters in Seismic Sequence Type Determination in Sichuan-Yannan Region Based on Decision Tree

Journal of Seismological Research[ISSN 1000-0666/CN 53-1062/P] Volume: 47 Number of periods: 2024 03 Page number: 321-335 Column: 人工智能 Public date: 2024-05-01

Title:: Research on the Importance of Feature Parameters in Seismic Sequence Type Determination in Sichuan-Yannan Region Based on Decision Tree

Author(s):: ZHAO Xiaoyan¹; JIANG Haikun²; MENG Lingyuan²; SU Youjin¹; HE Suge¹; (1.Yunnan Earthquake Agency,Kunming 650224,Yunnan,China;2.China Earthquake Networks Center,Beijing 100045,China)

Keywords:: earthquake sequence type; machine learning; characteristic parameters; decision tree

CLC:: P315.72

DOI:: 10.20015/j.cnki.ISSN1000-0666.2024.0039

Abstract:: Based on the catalog of 225 earthquakes with magnitude 5 or above,the catalog of earthquake sequences,and the focal mechanism of the historical earthquakes in Sichuan-Yunnan region from 1966 to 2021,and referring to the previous research and practice on the estimation of the tendency of the aftershock activity,10 sample datasets for the judging features of the earthquake sequence types have been constructed.According to the earthquake sequences types—swarm type,mainshock-aftershock type,as well isolated type—three labels have been made.After processing the imbalanced state and the missing state of the feature parameters,a decision tree model was used to study and analyze the importance of feature parameters.The results showed that there were differences in the importance categories of the feature parameters in different periods.As the sequence data increased,sequence type judgement relied more on dynamic sequence data; the parameters related to the main shocks' focal mechanism and the main shocks' parameters had a high contribution rate to the sequence classification,while the contribution rate of sequence parameters was extremely low.In overall,the results provided by the model are consistent with the actual empirical prediction methods.The above results can provide some ideas for the preliminary screening,exclusion,and selection of the complex and numerous feature parameters.

References:: 毕金孟,蒋长胜,来贵娟.2022a.全球部分强震的序列参数分布特征[J].地震,42(1):33-53.
Bi J M,Jiang C S,Lai G J.2022a.The numerical characteristics of sequence parameters of global strong earthquakes[J].Earthquake,42(1):33-53.(in Chinese)
毕金孟,蒋长胜,来贵娟,等.2022b.中国大陆强震的早期余震概率预测效能评估与制约因素[J].地球物理学报,65(7):2532-2545.
Bi J M,Jiang C S,Lai G J,et al.2022b.Effectiveness evaluation and constraints of early aftershock probability forecasting for strong earthquakes in continental China[J].Chinese Journal of Geophysics,65(7):2532-2545.(in Chinese)
毕金孟,蒋长胜.2019.华北地区地震序列参数的分布特征[J].地球物理学报,62(11):4300-4312.
Bi J M,Jiang C S.2019.Distribution characteristics of earthquake sequence parameters in North China[J].Chinese Journal of Geophysics,62(11):4300-4312.(in Chinese)
崔子健,李志雄,陈章立,等.2012.判别小震群序列类型的新方法研究——谱振幅相关分析法[J].地球物理学报,55(5):1718-1724.
Cui Z J,Li Z X,Chen Z L,et al.2012.A study on the new method for determining small earthquake sequence type—Correlation analysis of spectral amplitude[J].Chinese Journal of Geophysics,55(5):1718-1724.(in Chinese)
皇甫岗,秦嘉政,李忠华,等.2007.云南地震类型分区特征研究[J].地震研究,29(2):142-150.
Huangfu G,Qin J Z,Li Z H,et al.2007.Subarea characteristics of earthquake types in Yunnan[J].Journal of Seismological Research,29(2):142-150.(in Chinese)
黄浩,付虹.2014.2008年以来滇西地区地震序列的谱振幅相关系数变化特征[J].地震学报,36(4):631-639.
Huang H,Fu H.2014.Characteristics of the correlation coefficient of spectral amplitude of earthquake sequences in western Yunnan region since 2008[J].Acta Seismologica Sinica,36(4):631-639.(in Chinese)
蒋长胜,吴忠良,庄建仓.2013.地震的“序列归属”问题与 ETAS模型——以唐山序列为例[J].地球物理学报,56(9):2971-2981.
Jiang C S,Wu Z L,Zhuang J C.2013.ETAS model applied to the Earthquake-Sequence Association(ESA)problem:the Tangshan sequence[J].Chinese Journal of Geophysics,56(9):2971-2981.(in Chinese)
蒋海昆,代磊,侯海峰,等.2006a.余震序列性质判定单参数判据的统计研究[J].地震,26(3):17-25.
Jiang H K,Dai L,Hong H F,et al.2006a.Statistic study on the criterion index for classification of aftershock sequences[J].Earthquake,26(3):17-25.(in Chinese)
蒋海昆,李永莉,曲延军,等.2006b.中国大陆中强地震序列类型的空间分布特征[J].地震学报,28(4):389-398.
Jiang H K,Li Y L,Qu Y J,et al.2006b.Spatial distribution features of sequence types of moderate and strong earthquakes in Chinese Mainland[J].Acta Seismologica Sinica,28(4):389-398.(in Chinese)
蒋海昆,曲延军,李永莉,等.2006c.中国大陆中强地震余震序列的部分统计特征[J].地球物理学报,49(4):1110-1117.
Jiang H K,Qu Y J,Li Y L,et al.2006c.Some statistic features of aftershock sequences in Chinese mainland[J].Chinese Journal of Geophysics,49(4):1110-1117.(in Chinese)
蒋海昆,王锦红.2023.适用于机器学习的地震序列类型判定特征重要性讨论[J].地震研究,46(2):155-172.
Jiang H K,Wang J H.2023.Discussion on the importance of the features for the judgement of earthquake sequence types applicable to machine learning[J].Journal of Seismological Research,46(2):155-172.(in Chinese)
蒋海昆,杨马陵,付虹,等.2015.震后趋势判定参考指南[M].北京:地震出版社.
Jiang H K,Yang M L,Fu H,et al.2015.Reference Guide for Earthquake Trend Determination[M].Beijing:Seismological Press.(in Chinese)
蒋海昆,郑建常,代磊,等.2007a.中国大陆余震序列类型的综合判定[J].地震,27(1):17-25.
Jiang H K,Zheng J C,Dai L,et al.2007a.Synthetical judgment of types of aftershock sequences in Chinese Mainland[J].Earthquake,27(1):17-25.(in Chinese)
蒋海昆,郑建常,吴琼,等.2007b.中国大陆中强以上地震余震分布尺度的统计特征[J].地震学报,29(2):151-164.
Jiang H K,Zheng J C,Wu Q,et al.2007b.Statistical features of aftershock distribution size for moderate and large earthquakes in Chinese Mainland[J].Acta Seismologica Sinica,29(2):151-164.(in Chinese)
蒋海昆,郑建常,吴琼,等.2007c.传染型余震序列模型震后早期参数特征及其地震学意义[J].地球物理学报,50(6):1778-1786.
Jiang H K,Zheng J C,Wu Q,et al.2007.Earlier statistical features of ETAS model parameters and their seismological meanings[J].J Geophys,50(6):1778～1786.(in Chinese)
李忠华,苏有锦,蔡明军,等.2000.云南地区地震序列的p值和b值变化特征[J].地震研究,20(4):74-78.
Li Z H,Su Y J,Cai M J,et al.2000.Characteristics of P value and b value of earthquake sequences in Yunnan region[J].Journal of Seismological Research,20(4):74-78.(in Chinese)
刘瑞丰,陈运泰,任枭,等.2015.震级的测定[M].北京:地震出版社.
Liu R F,Chen Y T,Ren X,et al.2015.Determination of earthquake magnitude[M].Beijing:Seismological Press.(in Chinese)
刘正荣,孔绍麟.1986.地震频度衰减与地震预报[J].地震研究,9(1):6-8.
Liu Z R,Kong S L.1986.Earthquake frequency attenuation and earthquake prediction[J].Journal of Seismological Research,9(1):6-8.(in Chinese)
刘珠妹,蒋海昆,李盛乐,等.2019.基于震例类比的震后趋势早期判定技术系统建设[J].中国地震,35(4):602-615.
Liu Z M,Jiang H K,Li S L,et al.2019.Aftershock analysis and forecasting system construction based on seismic analogy[J].Earthquake Research in China,35(4):602-615.(in Chinese)
祁玉萍,龙锋,林圣杰,等.2021.南北地震带中段及周边中强地震序列类型的特征[J].地震地质,43(1):177-196.
Qi Y P,Long F,Lin S J,et al.2021.A study on the earthquake sequence type in the middle section of the north-south seismic belt and its surrounding regions[J].Seismology and Geology,43(1):177-196.(in Chinese)
史翔宇.2021.基于机器学习回归算法的地震预测研究及其在中国地震科学实验场的应用[D].北京:中国地震局地震预测研究所.
Shi X Y.2021.Research on earthquake prediction based on machine learning regression algorithm and its application in China Seismic Experimental Site[D].Beijing:Institute of Earthquake Prediction,China Earthquake Administration.(in Chinese)
宋金,杨马陵,吴时平,等.2013.基于序列参数的水库地震类型综合判定研究[J].中国地震,29(4):462-471.
Song J,Yang M L,Wu S P,et al.2013.Synthesis on the types of reservoir earthquake sequences based on sequence parameters[J].Earthquake Research in China,29(4):462-471.(in Chinese)
苏有锦,李忠华,赵小艳,等.2014.全球7级以上地震序列研究[M].昆明:云南大学出版社.
Su Y J,Li Z H,Zhao X Y,et al.2014.Research on global earthquake sequences with magnitudes 7 and above[M].Kunming:Yunnan University Press.(in Chinese)
苏有锦,刘祖荫,蔡明军,等.1999.云南地区强震分布的深部地球介质背景[J].地震学报,21(3):313-332.
Su Y J,Liu Z Y,Cai M J,et al.1999.Deep Earth Medium Background of Strong Earthquake Distribution in Yunnan Region[J].Acta Seismologica Sinica,21(3):313-332.(in Chinese)
王亚文,蒋长胜.2017.南北地震带地震台网监测能力评估的不同方法比较研究[J].地震学报,39(3):315-329.
Wang Y W,Jiang C S.2017.Comparison among different methods for assessing monitoring capability of seismic station in North-South Seismic Belt[J].Acta Seismologica Sinica,39(3):315-329.(in Chinese)
隗永刚,蒋长胜.2021.人工智能技术在地震减灾应用中的研究进展[J].地球物理学进展,36(2):516-524.
Wei Y G,Jiang C S.2021.Research progress of artificial intelligence technology in the application of earthquake disaster reduction[J].Progress in Geophysics,36(2):516-524.(in Chinese)
吴开统,焦远碧,吕培苓,等.1990.地震序列概论[M].北京:北京大学出版社.
Wu K T,Jiao Y B,Lyu P L,et al.1990.Introduction to Earthquake Sequences[M].Beijing:Beijing University Press.(in Chinese)
周翠英,张宇霞,王红卫.1996.以模式识别方法提取地震序列早期判断的综合指标[J].地震学报,18(1):118-124.
Zhou C Y,Zhang Y X,Wang H W.1996.Extracting comprehensive indicators for early judgment of earthquake sequences using pattern recognition methods[J].Acta Seismologica Sinica,18(1):118-124.(in Chinese)
Asencio-Cortés G,Martínez-Álvarez F,Morales-Esteban A,et al 2016.A sensitivity study of seismicity indicators in supervised learning to improve earthquake prediction[J].Knowledge-Based Systems,101:15-30.
Asencio-Cortés G,Morales-Esteban A,Shang X,et al. 2018. Earthquake prediction in California using regression algorithms and cloud-based big data infrastructure[J].Computers & Geosciences,115:198～210.
Asim K M,Moustafa S S R,Niaz I A,et al. 2020.Seismicity analysis and machine learning models for short-term low magnitude seismic activity predictions in Cyprus[J].Soil Dynamics and Earthquake Engineering,130:105932.
Ben-Zion Y,Lyakhovsky V.2006.Analysis of aftershocks in a lithospheric model with seismogenic zone governed by damage rheology[J].Geophys J Int,165:197-210.
Ben-Zion Y,Rice J R.1993.Earthquake failure sequences along a cellular fault zone in a three-dimensional elastic Solid containing asperity and nonasperity regions[J].J Geophys Res,B8:14109-14131.
Corbi F,Sandri L,Bedford J,et al. 2019.Machine learning can predict the timing and size of analog earthquakes[J].Geophysical Research Letters,46(3):1303-1311.
DeVries P M R,Viegas F,Wattenberg M,et al.2018.Deep learning of aftershock patterns following large earthquakes[J].Nature,560(7720):632-634.
Gulia L,Wiemer S.2019.Real-time discrimination of earthquake foreshocks and aftershocks[J].Nature,574(7777):193-199.
Hulbert C,Rouet-Leduc B,Johnson P A,et al 2019.Similarity of fast and slow earthquakes illuminated by machine learning[J].Nature Geoscience,12(1):69-74.
Iwata T.2008.Low detection capability of global earthquakes after the occurrence of large earthquakes:Investigation of the Harvard CMT catalogue[J].Geophysical Journal International,174(3):849-856.
Jordan T H,Chen Y T,Gasparini P,et al. 2011.Operational earthquake forecasting:State of knowledge and guidelines for utilization[J].Annals of Geophysics,54(4):315-391.
Liu Z,Jiang H,Li S.2023.Implementation and verification of a real time system for automatic aftershock forecasting in China[J].Earth Science Informatics,16:1891-1907.
Martínez-Álvarez F,Reyes J,Morales-Esteban A,et al. 2013.Determining the best set of seismicity indicators to predict earthquakes.Two case studies:Chile and the Iberian Peninsula[J].Knowledge-Based Systems,50:198-210.
Panakkat A,Adeli H.2007.Neural network models for earthquake magnitude prediction using multiple seismicity indicators[J].International Journal of Neural Systems,17(1):13-33.
U.S.Geological Survey.2017.Advanced national seismic system—Current status,development opportunities,and priorities for 2017-2027(ver.1.1)[R//OL].Reston,VA,USA,2017-07-18[2023-07-10].https://pubs.usgs.gov/publication/cir1429.

Similar References:

Memo

Last Update: 2024-05-01