Deep Neural Networks for Earthquake Detection and Source Region Estimation in North Central Venezuela

 

Ruben Tous¹, Leonardo Alvarado^2,4,

Beatriz Otero¹, Leonel Cruz¹ and Otilio Rojas^2,3

¹Universitat Politècnica de Catalunya (UPC). Barcelona, Spain.

²Universidad Central de Venezuela, Facultad de Ciencias, Caracas, Venezuela.

³Barcelona Supercomputing Center (BSC). Barcelona, Spain.

⁴Venezuelan Foundation for Seismological Research, FUNVISIS, Caracas, Venezuela.

Publicado en: Bulletin of the Seismological Society of America, 110(5), 2519-2529.

Abstract

Reliable earthquake detection algorithms are necessary to properly analyze and catalog the continuously growing seismic records. We report the results of applying a deep convolutional neural network, called UPC-UCV, over single-station three-channel signal windows for P-wave earthquake detection and source region estimation in north central Venezuela. The analysis is performed on a new dataset of hand-picked arrivals of P-waves from local events, named CARABOBO, built and made public for reproducibility and benchmarking purposes. The CARABOBO dataset consists of three-channel continuous data recorded by the broadband stations of the Venezuelan Foundation of Seismological Research (FUNVISIS) in the region of 9.5 to 11.5◦N and 67.0 to 69.0◦W during the time period from April 2018 to April 2019. During this period, 949 earthquakes were recorded in that area, corresponding to earthquakes with magnitudes in the range from 1.1 to 5.2 Mw. To estimate the epicentral source region of a detected event, the proposed network employs geographical distribution of the CARABOBO dataset into K clusters as a basis. This geographical partitioning  is automatically performed by the k-means algorithm, and the optimality of the K values for our dataset has been assessed using the Elbow (K = 5) and Silhouette (K = 3) methods. For target seismicity, the proposed network achieves 95.27% detection accuracy and 93.36% source region estimation accuracy when using K = 5 geographic clusters. The location accuracy slightly increases to 95.68% in the case of K = 3 geographic partitions. The detection capability of this network has also been tested on the OKLAHOMA dataset, which compiles over two thousand local earthquakes that occurred in this US state. Without any modification, the proposed network yields excellent detection results when trained and evaluated on that dataset (98.21% accuracy; ConvNetQuake, fine-tuned for this dataset, achieves a 97.32% accuracy), corresponding to a totally different geographical region.

Keywords: Seismology, Deep learning, Convolutional neural network (CNN), Earthquake localization, Single-station seismic análisis

Disponible en: https://drive.google.com/file/d/1O2iPwOZG8NoaTS-Be5ZPtRGL4K-eMFiq/view?usp=sharing