北京大学学报（自然科学版）2025，Vol.61Issue(3)：487-500,14.DOI:10.13209/j.0479-8023.2025.018
基于卷积神经网络和双向长短期记忆网络的微地震记录去噪方法
Micro-earthquake Recording Denoising Method Based on Convolutional Neural and Bidirectional Long Short-term Memory Network
摘要
Abstract
This paper proposes a deep learning-based time-domain denoising method for micro-earthquake recor-dings by combining a convolutional neural network(CNN)and a bidirectional long short-term memory network(BiLSTM).Based on micro-earthquake observation data from Zigong and Neijiang areas of Sichuan,the structural model and focal mechanism of the region are used to generate a synthetic noise-free dataset by numerical modeling,which is then combined with observed micro-earthquake noise to create a synthetic noisy dataset.A high-performance and stable denoising model is obtained through training of the deep learning network,demonstrating excellent generalization performance on the validation set.Compared with traditional methods,the proposed method demonstrates excellent denoising performance and better preserves the detailed characteristics of both the waveform and the spectrum of the noise-free signal.Application to micro-earthquake observation data of Zigong and Neijiang areas demonstrates the model's strong denoising performance and generalization ability on real-world data.关键词
微小地震/噪声去除/卷积神经网络(CNN)/双向长短期记忆网络(BiLSTM)/深度学习Key words
micro-earthquake/denoising/CNN/BiLSTM/deep learning引用本文复制引用
王泰然,鲍逸非..基于卷积神经网络和双向长短期记忆网络的微地震记录去噪方法[J].北京大学学报（自然科学版）,2025,61(3):487-500,14.基金项目
国家自然科学基金(42304110)资助 （42304110）
