[1]晏绮云,沈 平,王振南,等.基于深度学习的湖南地区地震事件检测与定位[J].华南地震,2026,46(03):51-57.[doi:10.13512/j.hndz.2026.03.08]
 YAN Qiyun,SHEN Ping,WANG Zhennan,et al.Earthquake Detection and Location in Hunan Region Based on Deep Learning[J].,2026,46(03):51-57.[doi:10.13512/j.hndz.2026.03.08]
点击复制

基于深度学习的湖南地区地震事件检测与定位()

华南地震[ISSN:1006-6977/CN:61-1281/TN]

卷:
46
期数:
2026年03期
页码:
51-57
栏目:
东南沿海地震带地震构造与危险性研究专栏
出版日期:
2026-05-18

文章信息/Info

Title:
Earthquake Detection and Location in Hunan Region Based on Deep Learning
文章编号:
1001-8662(2026)03-0051-07
作者:
晏绮云沈 平王振南佘旭明黄毓森
湖南省地震局,长沙 410004
Author(s):
YAN QiyunSHEN PingWANG ZhennanSHE XumingHUANG Yusen
Hunan Earthquake Agency , Changsha 410004, China
关键词:
湖南地区深度学习地震检测双差定位
Keywords:
Hunan regionDeep learningEarthquake detectionDouble-difference relocation
分类号:
P315
DOI:
10.13512/j.hndz.2026.03.08
文献标志码:
A
摘要:
基于LOC-FLOW深度学习地震检测与定位的自动工作流程,对湖南地震台网2011—2024年的连续波形进行系统处理,通过震相自动拾取、震相关联、绝对定位和人工复核后,共识别出2831个地震事件,约为人工编目事件的4.3倍,最小完整性震级降低至ML1.5,显著提升了微震检测能力。利用双差定位对1644个事件进行了精定位,部分事件集中沿已知断裂分布,部分事件可能与水库蓄水活动有关。为进一步认识湖南地区地震活动特征、发震成因和地震危险性评估提供了基础数据支撑。
Abstract:
Based on the automated workflow of LOC-FLOW deep learning for earthquake detection and location, this study systematically processed continuous waveform data recorded by the Hunan Seismic Network from 2011 to 2024. Through automatic phase picking,phase association,absolute positioning and manual verification,a total of 2831 seismic events were identified, which was approximately 4.3 times the number of manually cataloged events. The minimum complete magnitude was reduced to ML1.5, significantly enhancing microseismic detection capability. 1644 events were precisely relocated using the double-difference relocation method. The results indicate that some events are concentrated along known faults,while others may be associated with reservoir impoundment activities. This study provides fundamental data support for further understanding the characteristics of seismic activity,seismogenic mechanisms,and seismic hazard assessment in the Hunan region.

参考文献/References:

[1]徐伟进,高孟潭.中国大陆及周缘地震目录完整性统计分析[J].地球物理学报,2014,57(9):2802-2812.
[2] Stevenson P R. Microearthquakes at Flathead Lake,Montana:A study using automatic earthquake processing[J]. Bulletin of the Seismological Society of America,1976,66(1):61-80.
[3] Gibbsons S J,Ringdal F. The detection of low magnitude seis‐mic events using array-based waveform correlation[J]. Geo‐physical Journal International,2006,165(1):149-166.
[4] Zhang M,Wen L X. An effective method for small event de‐tection:Match and locate(M&L)[J]. Geophysical Journal In‐ternational,2015,200(3):1523-1537.
[5] Huang Y,Zhang S,Lv Y,et al. Earthquake detection in the Ji‐angsu region,China using graphics-processing-unit-based Match & Locate and rapid earthquake association and loca‐tion[J]. Earthquake Science,2020,33(1):23-33.
[6]张雅楠,李红谊,张盛中,等.上海及邻区微震检测与定位[J].地球物理学报,2023,66(3):1113-1124.
[7]汤兰荣,曾新福,许志山,等.寻乌及邻区遗漏地震检测及目录完整性分析[J].华南地震,2024,44(2):1-7.
[8] Zhu W,Beroza G C. PhaseNet:A deep-neural-network-based seismic arrival-time picking method[J]. Geophysical Journal International,2019,216(1):261-273.
[9] Mousavi S M,Ellsworth W L,Zhu W,et al. Earthquake trans‐former—an attentive deep-learning model for simultaneous earthquake detection and phase picking[J]. Nature Communi‐cations,2020,11(1):3952.
[10] Münchmeyer J,Woollam J,Rietbrock A,et al. Which picker fits my data? A quantitative evaluation of deep learning based seismic pickers[J]. Journal of Geophysical Research:Solid Earth,2022,127(1):e2021JB023499.
[11]苏金波,刘敏,张云鹏,等.基于深度学习构建2021年5月21日云南漾濞MS6.4地震序列高分辨率地震目录[J].地球物理学报,2021,64(8):2647-2656.
[12]赵明,唐淋,陈石,等.基于深度学习到时拾取自动构建长宁地震前震目录[J].地球物理学报,2021,64(1):54-66.
[13]郭慧丽,常利军,鲁来玉,等.基于深度学习震相拾取和密集台阵数据构建青海玛多MS7.4地震震源区高分辨率地震目录[J].地球物理学报,2022,65(5):1628-1643.
[14]孙海霞,赵桂儒,林向东,等.基于深度学习的PhaseNet方法在北京地区历史地震中的初步应用[J].华南地震, 2024,44(S1):127-128.
[15]戴宗辉,曲均浩,徐宁,等.2023年微山震群震源区三维速度结构与发震构造[J].地震地质,2025,47(6):1649-1666.
[16]戴宗辉,郑建常,周连庆,等.基于深度学习的山东平原MS5.5地震余震检测及发震构造研究[J].地球物理学报, 2025,68(3):925-937.
[17]文玺翔,沈旭章,周启明.基于机器学习和短周期密集台阵资料研究北流地震余震特[J].地球物理学报,2022,65 (9):3297-3308.
[18]支龙祥,赵旭.基于深度学习单台定位2025年西藏定日M6.8地震早期余震[J].地震地质,2025,47(3):820-834.
[19] Zhang M,Liu M,Feng T,et al. LOC-FLOW:An end-to-end machine-learning-based high-precision earthquake location workflow[J]. Seismological Research Letters,2022,93(5):2426-2438.
[20] Zhang M,Ellsworth W L,Beroza G C. Rapid earthquake as‐sociation and location[J]. Seismological Research Letters, 2019,90(6):2276-2284.
[21] Klein F W. User's guide to HYPOINVERSE-2000,a for‐tran program to solve for earthquake locations and magni‐tudes:USGS Open-File Report,2002-171[R]. Reston,Vir‐ginia:USGS,2002.
[22] Waldhauser F,Ellsworth W L. A double-difference earth‐quake location algorithm:Method and application to the northern Hayward fault,California[J]. Bulletin of the Seis‐mological Society of America,2000,90(6):1353-1368.
[23] Hu J,Sun W,Liu C,et al. Seismological reference earth model in South China(SREM-SC):Crust and uppermost mantle[J]. Frontiers in Earth Science,2023(10):1080307.

相似文献/References:

[1]张燕明,张红才,陈惠芳,等.实时智能地震处理系统在2013年福建仙游ML5.0地震序列中的应用研究[J].华南地震,2023,(04):64.[doi:10.13512/j.hndz.2023.04.09]
 ZHANG Yanming,ZHANG Hongcai,CHEN Huifang,et al.Application of Real-time Intelligent Seismic Processor in Xianyou ML5.0 Earthquake Sequence in Fujian Province in 2013[J].,2023,(03):64.[doi:10.13512/j.hndz.2023.04.09]
[2]梁 明,刘 军,洪玉清,等.地震自动编目处理系统在2023年广东河源M4.3地震序列中的应用[J].华南地震,2023,(04):119.[doi:10.13512/j.hndz.2023.04.15]
 LIANG Ming,LIU Jun,Hong Yuqing,et al.Application of Seismic Automatic Cataloguing Processing System in Heyuan M4.3 Earthquake Sequence in Guangdong in 2023[J].,2023,(03):119.[doi:10.13512/j.hndz.2023.04.15]
[3]徐晓桐,陈吉锋,李东平,等.基于多头自注意力机制的CNN地震舆情分析模型研究[J].华南地震,2024,(04):21.[doi:10.13512/j.hndz.2024.04.03]
 XU Xiaotong,CHEN Jifeng,LI Dongping,et al.CNN Earthquake Public Opioion Analysis Model Based on Multi-Head Self-Attention Mechanism[J].,2024,(03):21.[doi:10.13512/j.hndz.2024.04.03]
[4]郑建常.基于AlexNet 卷积神经网络的地震预测初步研究[J].华南地震,2024,(增刊):21.[doi:10.13512/j.hndz.2024.S1.09]
 ZHENG Jianchang.A Preliminary Study of Earthquake Prediction Based on AlexNet[J].,2024,(03):21.[doi:10.13512/j.hndz.2024.S1.09]
[5]王淑辉,马 莉,王晓睿,等.深度学习大强煤矿台阵数据的研究[J].华南地震,2024,(增刊):136.[doi:10.13512/j.hndz.2024.S1.50]
 WANG Shuhui,MA li,WANG Xiaorui,et al.Research on Daqiang Coal Mine Array Data Based on Deep Learning[J].,2024,(03):136.[doi:10.13512/j.hndz.2024.S1.50]
[6]李金湘,廖家乐,宿文姬.基于SMOTETomek和机器学习的粤东山区边坡崩滑地质灾害危险性评价研究[J].华南地震,2025,(02):50.[doi:10.13512/j.hndz.2025.02.07]
 LI Jinxiang,LIAO Jiale,SU Wenji.Risk Assessment of Slope Collapse Hazards in Mountainous Areas of Eastern Guangdong Based on SMOTETomek and Machine Learning[J].,2025,(03):50.[doi:10.13512/j.hndz.2025.02.07]
[7]陈 龙,葛 澄,戴颖超,等.基于深度学习的高分辨率遥感影像滑坡体识别方法研究[J].华南地震,2025,(02):66.[doi:10.13512/j.hndz.2025.02.09]
 CHEN Long,GE Cheng,DAI Yingchao,et al.Research on Landslide Detection in High-Resolution Remote Sensing Image Based on Deep Learning[J].,2025,(03):66.[doi:10.13512/j.hndz.2025.02.09]

备注/Memo

备注/Memo:
收稿日期:2025-11-30
基金项目:中国地震局地震监测预报预警工作任务(CEA-JCYJ-202501053)
作者简介:晏绮云(1989-),女,工程师,主要从事地震监测预报研究。E-mail:610490235@qq.com
更新日期/Last Update: 2026-05-20