Efficient similar waveform search using short binary codes obtained through a deep hashing technique

TL;DR

This paper introduces a deep learning-based hashing method that enables rapid, large-scale seismic waveform similarity searches using 64-bit binary codes, significantly reducing computation time and memory requirements.

Contribution

The study presents a novel deep hashing technique for seismic waveform search that is faster and more memory-efficient than previous methods, facilitating large-scale seismic data analysis.

Findings

Hamming distance calculation is 1000 times faster than network correlation.

Detected 23,462 additional seismic events using hashing-based template matching.

Achieved large-scale waveform search within 15.5 hours using parallel processing.

Abstract

A similar waveform search plays a crucial role in seismology for detecting seismic events, such as small earthquakes and low-frequency events. However, the high computational costs associated with waveform cross-correlation calculations represent bottlenecks during the analysis of long, continuous records obtained from numerous stations. In this study, we developed a deep-learning network to obtain 64-bit hash codes containing information on seismic waveforms. Using this network, we performed a similar waveform search for ~35 million moving windows developed for the 30 min waveforms recorded continuously at 10 MHz sampling rates using 16 acoustic emission transducers during a laboratory hydraulic fracturing experiment. The sampling points of each channel corresponded to those of the 5.8-year records obtained from typical seismic observations at 100 Hz sampling rates. Of the 35 million windows, we searched for windows with small average Hamming distances among the hash codes of 16 channel waveforms against template hash codes of 6057 events that were catalogued using conventional autoprocessing techniques. The calculation of average Hamming distances is 1000 times faster than that of the corresponding network correlation. This hashing-based template matching enabled the detection of 23,462 additional events. We also demonstrated the feasibility of the hashing-based autocorrelation analysis, where similar event pairs were extracted without templates, by calculating the average Hamming distances for all possible pairs of the ~35 million windows. This calculation required only 15.5 h under 120 thread parallelisation. This deep hashing approach significantly reduced the required memory compared with locality-sensitive hashing approaches based on random permutations, enabling similar waveform searching on a large-scale dataset.