A study on the effect of input data length on deep learning basedmagnitude classifier

The rapid characterisation of earthquake parame-ters such as its magnitude is at the heart of Earth-quake Early Warning (EEW). In traditional EEW methods the robustness in the estimation of earth-quake parameters have been observed to increase with the length of input data. Since time is a crucial factor in EEW applications, in this paper we propose a deep learning based magnitude clas-sifier and, further we investigate the effect of using five different durations of seismic waveform data after first P-wave arrival– ۱s, ۳s, ۱۰s, ۲۰s and ۳۰s. This is accomplished by testing the performance of the proposed model that combines Convolution and Bidirectional Long-Short Term Memory units to classify waveforms based on their magnitude into three classes– "noise", "low-magnitude events" and "high-magnitude events". Herein, any earthquake signal with magnitude equal to or above ۵.۰ is la-belled as high-magnitude. We show that the varia-tion in the results produced by changing the length of the data, is no more than the inherent random-ness in the trained models, due to their initialisa-tion.