December 5, 2025Seismological Research Letters

Analyzing Earthquake’s Onset-Magnitude Correlation Using Modeled Source Time Functions of Recorded Earthquakes and Machine Learning

View Full Paper

Ask AI

Bookmark

Authors

GRGopala Krishna RoddaBen-Gurion University of the Negev

Discussion

Member takes

Implication

Machine learning predicts moment magnitude with a mean absolute error of 0.21 units, suggesting early warning systems can benefit from initial source time functions.

Key Points

Predictions yield a mean absolute error of 0.21 magnitude units for moment magnitude assessment, demonstrating the model's effectiveness.
The convolutional neural network–recurrent neural network model leverages only the initial 2 seconds of source time functions for its forecasting.
Analysis shows correlation coefficients reach 0.71, providing insight into linking initial rupture characteristics and final earthquake size.
The research supports enhancing early warning systems and indicates further exploration of diverse data is necessary for improved predictions.

Cite This Study

Gopala Krishna Rodda (2025) studied this question.

synapsesocial.com/papers/6940224e2d562116f28fc041 https://doi.org/10.1785/0220240161

View Full Paper

Ask AI

Bookmark

Implication

Machine learning predicts moment magnitude with a mean absolute error of 0.21 units, suggesting early warning systems can benefit from initial source time functions.

Analyzing Earthquake’s Onset-Magnitude Correlation Using Modeled Source Time Functions of Recorded Earthquakes and Machine Learning

Discussion

Member takes

Implication

Key Points

Cite This Study

Analyzing Earthquake’s Onset-Magnitude Correlation Using Modeled Source Time Functions of Recorded Earthquakes and Machine Learning

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider