石油物探2024，Vol.63Issue(4)：790-806,17.DOI:10.12431/issn.1000-1441.2024.63.04.008
基于多模态神经网络的微地震事件检测
Microseismic event detection based on multi-modal neural network
摘要
Abstract
A multimodal neural network-based microseismic event detection method is proposed to address the problem that the time series of effective microseismic signals has severe limitations.First,the multichannel time-domain mode with the target chan-nel as the axis symmetry is established using gather data correlation,and the S-domain modal characteristics are obtained by using time-frequency analysis for the target channel.Then,the neural network for microseismic event detection is designed by combining the time-domain mode and S-domain mode.Multimodal features are synthesized for training and learning to improve the accuracy of detection.Finally,method validation is performed through the analyses of synthetic low-SNR and small-amplitude data and actu-al oil-well microseismic events.The results showed that our method could detect low-SNR and weak microseismic signals effective-ly.Compared with SVM,CNN,and supervised machine learning,our method has improved anti-noise performance and accuracy.关键词
微地震/事件检测/拉普拉斯变换/多模态网络/时频谱/道集数据相关性Key words
microseismic/event detection/Laplace transform/multi-modal network/time-frequency spectrum/gather data correla-tion分类
天文与地球科学引用本文复制引用
张岩,刘小秋,王海潮,宋利伟,董宏丽..基于多模态神经网络的微地震事件检测[J].石油物探,2024,63(4):790-806,17.基金项目
东北石油大学特色科研团队项目"智慧油田信息处理创新团队"(2023TSTD-04)资助.This research is financially supported by the Northeast Petroleum University's Characteristic Research Team Project(Grant No.2023TSTD-04). （2023TSTD-04）
