An end-to-end DNN-HMM based system with duration modeling for robust earthquake detection

• Published in: Computers & geosciences Vol. 179; p. 105434
• Main Authors: Murúa, Catalina, Marín, Marcelo, Cofré, Aarón, Wuth, Jorge, Pino, Oscar Vásquez, Yoma, Néstor Becerra
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-10-2023
• Subjects: Deep learning; DNN-HMM; Duration models; Limited training data; Microseismicity; Robust automatic earthquake detection; Deep learning; Duration models; Robust automatic earthquake detection; Microseismicity; Limited training data; DNN-HMM
• ISSN: 0098-3004; 1873-7803
• DOI: 10.1016/j.cageo.2023.105434

Developing a reliable and robust automatic earthquake detection system is quite a challenging and highly necessary task as two conditions can make this task a difficult one. First, earthquake detection systems may perform more poorly if they are employed in a region that is different from the one where the training database corresponds to. Systems trained with local databases are assumed to perform better. Nevertheless, these databases are usually limited. Second, the performance of such systems worsens when the SNR of the seismogram signals decreases. This paper proposes an end-to-end DNN-HMM based scheme to address these limitations, i.e. it does not require previous phase-picking, backed by engineered features and combined with duration modeling of states and seismic events. The proposed engine requires 10- or 15-times fewer parameters than state-of-the-art methods and therefore needs a smaller training database. Modeling duration can improve the noise robustness of the detection system significantly, particularly with limited training data; having a negligible increase in the number of training parameters. The system described here provides a F1-score 101% higher on average than schemes published elsewhere with Iquique and North Chile databases. It provides a reduction in F1-score equal to 10% when the average SNR is reduced by approximately 18 dB. This reduction in F1-score is at least half of the one observed with the state-of-the-art schemes in the same testing conditions. With respect to the detection of small earthquakes at short epicenter-station distances, the averaged precision provided by the DNN-HMM system with duration modeling is at least 5% higher than other systems.
•Robust earthquake detection with a DNN-HMM system and duration modeling.•Models trained on local data are more accurate than those trained on global data.•Fewer trainable parameters requires smaller training databases.•Duration modeling increases the noise robustness of earthquake detection.•Engineering features softens the requirement of training data size.