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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Seismic intensity prediction in a geographical area from early or initialseismic waves received by a few seismic stations is a critical component of aneffective Earthquake Early Warning (EEW) system. State-of-the-art deeplearning-based techniques for this task suffer from limited accuracy in theprediction and, more importantly, require input waveforms of a large timewindow from a handful number of seismic stations, which is not practical forEEW systems. To overcome the above limitations, in this paper, we propose anovel deep learning approach, Seismic Contrastive Graph Neural Network (SC-GNN)for highly accurate seismic intensity prediction using a small portion ofinitial seismic waveforms received by a few seismic stations. The SC-GNNcomprises two key components: (i) a graph neural network (GNN) to propagatespatiotemporal information through the nodes of a graph-like structure ofseismic station distribution and wave propagation, and (ii) a self-supervisedcontrastive learning component to train the model with larger time windows andmake predictions using shorter initial waveforms. The efficacy of our proposedmodel is thoroughly evaluated through experiments on three real-world seismicdatasets, showing superior performance over existing state-of-the-arttechniques. In particular, the SC-GNN model demonstrates a substantialreduction in mean squared error (MSE) and the lowest standard deviation of theerror, indicating its robustness, reliability, and a strong positiverelationship between predicted and actual values. More importantly, the modelmaintains superior performance even with 5s input waveforms, making itparticularly efficient for EEW systems.

Real-time Seismic Intensity Prediction using Self-supervised Contrastive GNN for Earthquake Early Warning