Physics-informed deep learning to forecast [Formula: see text] during hydraulic fracturing

Short-term forecasting of estimated maximum magnitude ([Formula: see text] ) is crucial to mitigate risks of induced seismicity during fluid stimulation. Most previous methods require real-time injection data, which are not always available. This study proposes two deep learning (DL) approaches, along with two data-partitioning methods, that rely solely on preceding patterns of seismicity. The first approach forecasts [Formula: see text] directly using DL; the second incorporates physical constraints by using DL to forecast seismicity rate, which is then used to estimate [Formula: see text] . These approaches are tested using a hydraulic-fracture monitoring dataset from western Canada. We find that direct DL learns from previous seismicity patterns to provide an accurate forecast, albeit with a time lag that limits its practical utility. The physics-informed approach accurately forecasts changes in seismicity rate, but sometimes under- (or over-) estimates [Formula: see text] . We propose that significant exceedance of [Formula: see text] may herald the onset of runaway fault rupture.