Kelian Dascher-Cousineau, University of California, Berkeley

Seismology is witnessing explosive growth in the diversity and scale of earthquake catalogs. A key motivation for this community effort is that more data should translate into better earthquake forecasts. In this presentation, I report on recent works in 1) improving aftershock forecasts, 2) investigating the seismic triggering potential of slow slip events, and 3) introducing deep learning methods for earthquake forecasting. Our results underscore the importance of large datasets in yielding robust earthquake forecasts. Furthermore, they illustrate how more data can unlock new, more flexible methodologies.