English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Earthquake detection and phase identification are fundamental and challenging tasks in observational seismology. Deep learning has achieved considerable progress in these two tasks. To overcome the limitations of existing methods, mainly because of the lack of large labeled seismic datasets and the separation of detection and identification tasks, we introduced the continuous wavelet transform (CWT)- convolutional neural networks (CNN) Few-shot learning Earthquake model (CCFE), a deep learning model for simultaneous earthquake detection and phase identification. CCFE can perform few-shot learning with minimal labeled seismic data by utilizing continuous wavelet transform and lightweight convolutional neural networks with fewer layers. We tested our model in the Huoshan area of southern China and found that CCFE outperformed both traditional and published representative deep learning models for detection and identification in this area and that combining detection and identification tasks enhances the performance of each task separately. We found 76&#x0025; more earthquakes using CCFE than the manual catalog across 15 days of continuous data from the Huoshan region. In regions with low seismicity, CCFE can aid in enhancing earthquake monitoring capacity.

CCFE: A Few-Shot Learning Model for Earthquake Detection and Phase Identification