SOM-Based Visualization for Classifying Large-Scale Sensing Data of Moonquakes

Large-scale seismic data were obtained from seismometers located on the Moon by the NASA Apollo missions from 1969 to 1977. According to previous analysis of the lunar seismic data, we found that deep moonquakes occur periodically from identical sources at a depth of about 700 to 1200km. The deep moonquakes occurred from identical sources have high similarities among each waveform. This similarity is important to classify the sources and investigate the generation mechanism of moonquakes. From the reason, classification of moonquakes has been processed. We, therefore, develop the web system for visualizing moonquakes considering the waveform similarity to progress study of moonquake classification. Our system maps moonquakes data to two dimensional output space using Self-Organizing Map (SOM). We embed Hadoop in the back-end system to apply SOM to enormous moonquakes data. In this paper, to select a feature for SOM, we evaluate several features based on classified data. Using selected feature, we perform SOM to moonquake data and discuss its result.