Channel Quality Index Dataset for High-Quality Channel Identification in Distributed Acoustic Sensing [Dataset]

This study investigates the automatic identification of high-quality channels in Distributed Acoustic Sensing (DAS) using a Machine Learning (ML)-based Channel Quality Index (CQI). The dataset consists of ten seismic events recorded by DAS, which were used to train the ML model for CQI computation. The primary objective was to develop a robust method for distinguishing high-quality DAS channels, optimizing seismic data analysis by filtering out noisy or low-quality channels. The results demonstrate that the proposed CQI-based approach effectively identifies high-quality channels, improving the reliability of DAS for seismic monitoring. This method enhances the usability of DAS recordings for earthquake detection and characterization, paving the way for more accurate and efficient seismic data processing

本研究借助基于机器学习（Machine Learning, ML）的信道质量指数（Channel Quality Index, CQI），开展分布式声学传感（Distributed Acoustic Sensing, DAS）优质信道的自动识别研究。本数据集包含由DAS采集得到的10次地震事件数据，该数据被用于训练用于计算CQI的机器学习模型。本研究的核心目标是开发一种鲁棒的优质DAS信道区分方法，并通过滤除含噪或低质量信道来优化地震数据分析流程。实验结果表明，所提出的基于CQI的方法可有效识别优质信道，提升了DAS用于地震监测的可靠性。该方法提升了DAS采集数据在地震检测与震源特征描述中的可用性，为更精准高效的地震数据处理工作奠定了基础。