<ul data-eligibleForWebStory="false"><li>Researchers developed a deep learning model using a transformer encoder to classify volcanic earthquakes objectively and efficiently, reducing reliance on subjective human judgment.</li><li>The model achieved high F1 scores for volcano tectonic, low-frequency earthquakes, and noise classification, outperforming a traditional CNN-based method.</li><li>Attention weight visualizations revealed the model focuses on key waveform features similar to human experts, but inconsistencies in training data influenced classification accuracy.</li><li>Experiments emphasized the importance of balancing data quality and diversity, with proximity to the crater impacting model performance and interpretability, aiding in better understanding seismic activity at Mount Asama.</li></ul>

Automated Classification of Volcanic Earthquakes Using Transformer Encoders: Insights into Data Quality and Model Interpretability

Discover more