Abstract Summary
Forecasting the occurrence of slip behaviors, either aseismic creep or dynamic slip, relies heavily on understanding the evolution of friction controls during the interseismic creep, particularly those significantly modified from the previous slip events. Here we collected the experimental data from a series of fluid injection experiments and built a dual-stage attention-based recurrent neural network model to uncover the contributions of controlling factors. The results reveal that the shear stress becomes the dominant control of slip behaviors after the first dynamic slip event, promoting the propagation of rupture front and the occurrence of dynamic slip.
