On the Use of High‐Resolution and Deep‐Learning Seismic Catalogs for Short‐Term Earthquake Forecasts: Potential Benefits and Current Limitations.

Enhanced earthquake catalogs provide detailed images of evolving seismic sequences. Currently, these data sets take some time to be released but will soon become available in real time. Here, we explore whether and how enhanced seismic catalogs feeding into established short‐term earthquake forecasting protocols may result in higher predictive skill. We consider three enhanced catalogs for the 2016–2017 Central Italy sequence, featuring a bulk completeness lower by at least two magnitude units compared to the real‐time catalog and an improved hypocentral resolution. We use them to inform a set of physical Coulomb Rate‐and‐State (CRS) and statistical Epidemic‐Type Aftershock Sequence (ETAS) models to forecast the space‐time occurrence of M3+ events during the first 6 months of the sequence. We track model performance using standard likelihood‐based metrics and compare their skill against the best‐performing CRS and ETAS models among those developed with the real‐time catalog. We find that while the incorporation of the triggering contributions from new small magnitude detections of the enhanced catalogs is beneficial for both types of forecasts, these models do not significantly outperform their respective near real‐time benchmarks. To explore the reasons behind this result, we perform targeted sensitivity tests that show how (a) the typical spatial discretizations of forecast experiments (≥ $\ge $2 km) hamper the ability of models to capture highly localized secondary triggering patterns and (b) differences in earthquake parameters (i.e., magnitude and hypocenters) reported in different catalogs can affect forecast evaluation. These findings will contribute toward improving forecast model design and evaluation strategies for next‐generation seismic catalogs. Plain Language Summary: Modern enhanced seismicity catalogs provide an unprecedented picture of how earthquake sequences evolve. These next‐generation catalogs will be released and updated in real time conditions soon. Therefore, we ask whether the extra information they provide can be exploited to boost the performance of current popular models of short‐term earthquake forecasting, namely, physical models of fault‐to‐fault stress interactions and purely statistical models. We use three enhanced catalogs for the 2016–2017 Central Italy earthquake sequence to develop physical and statistical forecasts for the first 6 months of M3+ seismicity. By means of well‐established tests, we quantify the predictive skill of the models and benchmark them against forecasts developed using real‐time data sets only. We find that both physical and statistical forecasts benefit from gradually incorporating the triggering contributions from the many small, newly revealed events reported in the enhanced catalogs, but their overall performance does not convincingly improve compared to their respective real‐time realizations. Sensitivity tests show how future experimental setups should consider that (a) even small variations in the basic components of different catalogs can affect the performance of the resulting forecasts and (b) the typically adopted model spatial resolutions are too coarse to capture small‐scale triggering patterns described by enhanced catalogs. Key Points: We compare retrospective forecast models informed by enhanced versus real‐time earthquake catalogs for the 2016–2017 Central Italy sequenceTo realize the benefits of high‐resolution catalogs, models should integrate advanced experimental setups, like finer spatial gridsResults stimulate further testing on the optimal design of next‐generation forecast models based on enhanced seismic catalogs [ABSTRACT FROM AUTHOR]