Learnable Maximum Amplitude Structure for Earthquake Event Classification

Shou Zhang, Bonhwa Ku, Hanseok Ko

Research output: Contribution to journalArticlepeer-review


Recently, most research has been conducted to minimize damage from earthquakes by establishing an early warning system through the analysis of short seismic waves. In particular, deep learning is widely used as it allows to learn complex patterns for earthquake detection from seismic data without complex physical knowledge. In this letter, we propose an improved ConvNetQuake for earthquake event classification by adding learnable features related to the maximum amplitude of the seismic waveform. Since the maximum amplitude is a major factor representing the characteristics of an earthquake, we presented a deep learning structure that can apply this factor in the process of determining whether an earthquake occurs. In the proposed structure, the maximum amplitude is transformed into a feature learned through multi-layer perceptron (MLP) and then concatenates with features extracted through a convolutional neural network (CNN). On the STanford EArthquake Dataset (STEAD) dataset, the proposed method significantly increases the performance for an earthquake event classification than the previous state-of-the-art (SOTA) method by only adding a few parameters.

Original languageEnglish
JournalIEEE Geoscience and Remote Sensing Letters
Publication statusPublished - 2022


  • Convolutional neural network (CNN)
  • earthquake event classification
  • global maximum pooling (GMP)
  • maximum amplitude
  • multi-layer perceptron (MLP)

ASJC Scopus subject areas

  • Geotechnical Engineering and Engineering Geology
  • Electrical and Electronic Engineering


Dive into the research topics of 'Learnable Maximum Amplitude Structure for Earthquake Event Classification'. Together they form a unique fingerprint.

Cite this