Predicting Deep Moonquake Source Regions Using Their Temporal and Spatial Patterns and Machine Learning

Abstract In the near future, lunar exploration should be enhanced by deploying a new seismic station on the farside of the Moon, the Farside Seismic Suite (FSS), a package of two seismometers recently selected by NASA to fly on a commercial lander. The new data should provide us with new insights into Moon's seismic activity, its interior, and composition. To fully benefit from the new data, we need to take advantage of the data acquired during the Apollo missions. The problem of relating new and old data is complex due to the single‐station nature of the future deployment. In this study, we tackle this issue by developing a machine learning model in the context of the deep moonquake (DMQ) classification problem. The DMQs form the largest group of detected events from Apollo data, and their source regions have been located and are known to exhibit temporal and spatial patterns connected with the monthly lunar tidal periods. Therefore, we propose to utilize a machine learning (ML) algorithm named random forest to identify DMQs source regions without using waveform information and only using the lunar orbital parameters related to DMQs time occurrences. We show that ML models perform well (with an accuracy >70%) when they are trained to classify 4 or fewer different source regions. This approach gives us a good first location approximation of the DMQs source regions and opens up a new approach to their location estimate when captured by the future FSS single‐station seismometers.