Shaking Up Predictions: Deep Learning Revolutionizes Earthquake Forecasts

Researchers have developed a deep learning model, RECAST, that outperforms traditional methods in predicting earthquake aftershocks, especially with larger datasets. This advancement promises improved earthquake forecasting using comprehensive global data. The new model, known as the Recurrent Earthquake foreCAST (RECAST), outperformed the current model, known as the Epidemic Type Aftershock Sequence (ETAS) model, for earthquake catalogs of about 10,000 events and greater.