基于迁移学习的岩石边坡微地震事件检测算法  

A landslide microseismicity detection method based on transfer learning

作　　者：蔡育埼 于子叶 CAI Yuqi;YU Ziye(Institute of Geophysics,China Earthquake Administration,Beijing 100081,China)

机构地区：[1]中国地震局地球物理研究所,中国北京100081

出　　处：《地震地磁观测与研究》2024年第2期20-27,共8页Seismological and Geomagnetic Observation and Research

基　　金：基于深度神经网络的体波面波联合反演算法,中央级公益性科研院所基本科研业务费(项目编号:DQJB23R31)。

摘　　要：基于迁移学习,设计一套岩石边坡微地震事件检测算法流程,用于自动化处理岩石边坡数据。基于海量人工标注的天然地震数据进行训练,得到深度学习预训练模型,并利用少量人工标注的微地震数据进行微调,使得模型可以适用于滑坡体微地震数据。采用实际标注数据进行测试,结果表明,基于迁移学习模型的查准率和查全率分别可达0.884和0.91。分析认为,在迁移学习流程中,深度学习模型减少了对于标注数据的依赖,同时可以仅经少量迭代即可得到鲁棒的、高精度结果。该模型部分程序是开源的,可以将其迁移到更多区域的微地震事件检测工作中。In this article,we introduce a transfer learning-based landslide microseismicity detection model,which can automatically pick up microseismicity occurring on the slopes in more accurate means.The deep learning model is first trained using a huge amount of manually labeled seismic events to obtain a well pre-trained model,then,the pre-trained model is fine-tuned by a small number of manually labeled microseismic events that have occurred on the slope to account for landslide microseismicity detection.The results suggest that our model achieves a rate of 0.884 and 0.91 in recall and precision test using unknown events that occurred on the slope,respectively.The proposed transfer learning-based training procedure not only significantly reduces the demand on the labeled training data on the slope,but also achieves a more robust and accurate model using a small number of integrations when applied to slopes.We open source the main function of the model,which can also be applied to other slopes.

关 键 词：迁移学习 微地震事件检测 深度学习 边坡 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]