微地震初至精确拾取是目前微地震监测关键环节之一，传统的人工拾取方法耗时长、效率低，在实际应用中容易导致无法及时预警等问题。近年来，基于深度学习的长短期记忆网络模型(LSTM)常用于微地震初至拾取，但在低信噪比环境下拾取准确率较低，且忽视了微地震数据中相邻道初至之间的关联性。针对上述问题，将微地震初至发生前、后看作是图像二分类问题，提出了一种应用图像语义分割网络的微地震事件识别和初至自动拾取方法。应用在矿井中采集的实际微地震数据进行实验，结果表明，对包含岩石破裂、工程爆破等多类型微地震事件，该方法的识别准确率较现有的深度学习方法明显提高，平均拾取误差大幅降低，特别是低信噪比数据的平均拾取误差远小于LSTM法，因而具有良好的实际工程应用价值。
Abstract
Precise picking of microseismic first breaks is one of the key aspects of microseismic monitoring. The traditional manual pickup method is time-consuming and inefficient, and it is likely to lead to problems such as failure to provide timely war-nings in practical applications. In recent years, the long short-term memory (LSTM) network model based on deep learning has been commonly used for microseismic first break picking, but the picking accuracy is low in a low signal-to-noise ratio (SNR) environment, and the correlation between first arrivals of adjacent traces is neglected. To address the above problems, we propose a microseismic event recognition and automatic first break pickup method based on the image semantic segmentation network (D-LinkNet), which treats microseismic first breaks as a binary image classification problem. Experiments using actual microseismic data acquired in mines are conducted, and the experimental results reveal that the recognition accuracy of the method is significantly improved compared with that of the existing deep learning methods for multiple types of microseismic events including rock rupture and engineering blasting, and the average pickup error is significantly reduced; in particular, the average pickup error of low SNR data is much smaller than that of the LSTM method. Thus, the proposed method has good value for practical engineering applications.
关键词
微地震监测 /
微地震初至 /
拾取 /
图像语义分割 /
长短期记忆网络模型(LSTM)
{{custom_keyword}} /
Key words
microseismic monitoring /
first break /
picking /
image semantic segmentation network (D-LinkNet) /
long short-term memory network (LSTM)
{{custom_keyword}} /
中图分类号：
P631
{{custom_clc.code}}
({{custom_clc.text}})
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 柳云龙,田有,冯晅,等. 微震技术与应用研究综述[J]. 地球物理学进展,2013,28(4):1801-1808.
LIU Yunlong,TIAN You,FENG Xuan,et al. Review of microseism technology and its application[J]. Progress in Geophysics,2013,28(4):1801-1808.
[2] 宋维琪,冯超. 微地震有效事件自动识别与定位方法[J]. 石油地球物理勘探,2013,48(2):283-288.
SONG Weiqi,FENG Chao. Automatic recognition and location method of effective microseismic events[J]. Oil Geophysical Prospecting,2013,48(2):283-288.
[3] 曾志毅,张建中. 利用微地震记录互相关成像的震源定位方法[J]. 石油地球物理勘探,2020,55(2):360-372,388.
ZENG Zhiyi,ZHANG Jianzhong. Source location method using microseismic record cross-correlation imaging[J]. Oil Geophysical Prospecting,2020,55(2):360-372,388.
[4] ALLEN R V. Automatic earthquake recognition and timing from single traces[J]. Bulletin of the Seismological Society of America,1978,68(5):1521-1532.
[5] TAKANAMI T,KITAGAWA G. Estimation of the arrival times of seismic waves by multivariate time series model[J]. Annals of the Institute of Statistical Mathematics,1991,43(3):407-433.
[6] 高煜,胡宾鑫,朱峰,等. 微震初至波到时自动拾取研究[J]. 工矿自动化,2020,46(12):106-110.
GAO Yu,HU Binxin,ZHU Feng,et al. Research on automatic picking of microseismic first arrival[J]. Industry and Mine Automation,2020,46(12):106-110.
[7] ZHENG J,LU J R,PENG S Q,et al. An automatic microseismic or acoustic emission arrival identification scheme with deep recurrent neural networks[J]. Geo-physical Journal International,2018,212(2):1389-1397.
[8] 张全敏. 基于深度学习的微震事件检测及波形初至拾取方法研究[D]. 四川绵阳:西南科技大学,2021.
[9] 喻志超,谭玉阳,翟尚,等. 基于波形相似特征的微地震事件初至拾取及全局校正[J]. 地球物理学报,2019,62(12):4782-4793.
YU Zhichao,TAN Yuyang,ZHAI Shang,et al. Arrival picking and global refinement for microseismic events based on waveform similarity[J]. Chinese Journal of Geophysics,2019,62(12):4782-4793.
[10] 陈德武,杨午阳,魏新建,等. 基于混合网络U-SegNet的地震初至自动拾取[J]. 石油地球物理勘探,2020,55(6):1188-1201.
CHEN Dewu,YANG Wuyang,WEI Xinjian,et al. Automatic picking of seismic first arrivals based on hybrid network U-SegNet[J]. Oil Geophysical Prospecting,2020,55(6):1188-1201.
[11] REN S Q,HE K M,GIRSHICK R,et al. Faster R-CNN:towards real-time object detection with region proposal networks[C]. Proceedings of the 28th International Conference on Neural Information Processing Systems,2015，91-99.
[12] CHEN Z Y,WU R H,LIN Y Y,et al. Plant disease recognition model based on improved YOLOv5[J]. Agronomy,2022,12(2)：doi:10.3390/agronomy- 12020365.
[13] 南晓虎,丁雷. 深度学习的典型目标检测算法综述[J]. 计算机应用研究,2020,37(增刊2):15-21.
NAN Xiaohu,DING Lei. Overview of typical target detection algorithms for deep learning[J]. Application Research of Computers,2020,37(S2):15-21.
[14] SHELHAMER E,LONG J,DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[15] RONNEBERGER O,FISCHER P,BROX T. U-Net:convolutional networks for biomedical image segmentation[C]. Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015,2015,234-241.
[16] ZHOU L C,ZHANG C,WU M. D-LinkNet:LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW),2018,182-186.
[17] ZHAO Z,GROSS L,ZHOU Y,et al. Automatic microseismic event detection using deep learning:a classification is detection method[C]. Extended Abstracts of 81st EAGE Conference and Exhibition,2019,1-5.
[18] 刘晗,张建中. 微震信号自动检测的STA/LTA算法及其改进分析[J]. 地球物理学进展,2014,29(4):1708-1714.
LIU Han,ZHANG Jianzhong. STA/LTA algorithm for automatic detection of microseismic signals and its improved analysis[J]. Progress in Geophysics,2014,29(4):1708-1714.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
本项研究受国家自然科学基金项目“基于深度学习的青藏高原东缘深部电性结构模型及其动力学特征”(41930112)资助。
{{custom_fund}}
PDF(3566 KB)
