Enhancing Ring Laser Gyroscope data analysis through Neural Networks for Earthquake detection and Phenomenon identification

This work focuses on developing neural networks to optimize the ring laser gyroscope data analysis, for the GINGER experiment. The first neural network aims to provide data with minimal delays suitable to detect earthquakes. Comparing this neural network with a tool implemented in Labview based on the Fast Fourier Transform, the neural network is twice as precise with the same delay. The second network learns to recognize various phenomena in the data, such as transients from laser dynamics like split modes or mode jumps. These capabilities are realized through the automated labeling of data using neural networks and the implementation of a mask that facilitates the selection of high-quality data. The curated dataset can then undergo traditional offline analysis. The third network is a map to transform earthquake signals seen by the GIGS seismometer into the signals seen by the co-located GINGERINO ring laser prototype, useful to study rotational models of earthquakes.