Clustering continuous Apollo’s Lunar seismic data with unsupervised deep learning

【作者】 刘欣； 肖卓伟； 李娟；

【机构】 Key Laboratory of Earth and Planetary Physics, Institute of Geology and Geophysics, Chinese Academy of Sciences； College of Earth and Planetary Sciences, University of Chinese Academy of Sciences；

【摘要】 <正>Despite the intensive and comprehensive studies on the seismicity of the Moon, little attention is paid to exploring and clustering continuous Apollo Lunar seismic data. In this study, we adopt an unsupervised deep-learning method for classifying and clustering the segments of continuous seismograms. Our approach learns the complex features of waveform segments and determines their classes: it leverages deep convolutional networks for feature extraction, principal component analysis for feature reduction, and k-means clustering for generating pseudo-labels.更多还原