What question did this study set out to answer?

This research aims to develop an accurate model for estimating earthquake magnitude from initial seismic signals.

July 1, 2026npj natural hazards.Open Access

Attention-based learning for early earthquake magnitude estimation from strong-motion records

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial shows improved earthquake magnitude estimation in multiple tectonic regions, suggesting advancements for early warning systems.

This research aims to develop an accurate model for estimating earthquake magnitude from initial seismic signals.
Developed a deep-learning model named A2MAG to analyze the first 3 seconds of strong-motion acceleration records.
Trained and tested the model on over 130,000 waveforms from more than 12,000 earthquakes recorded between 1996 and 2024.
Evaluated performance in estimating both earthquake magnitude and P-wave arrival times.
Achieved a mean absolute error of 0.33 magnitude units in estimating earthquake magnitude.
Estimated P-wave arrival times with a mean absolute error of 0.07 seconds.
Model systematically underestimates large earthquakes (M > 6) due to longer rupture durations.

Zhang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial shows improved earthquake magnitude estimation in multiple tectonic regions, suggesting advancements for early warning systems.