Denoising methods are a highly desired component of signal processing, and they can separate the signal of interest from noise to improve the subsequent signal analyses. In this paper, an advanced denoising method based on a fully convolutional encoder–decoder neural network is proposed. The method simultaneously learns the sparse features in the time–frequency domain, and the mask-related mapping function for signal separation. The results show that the proposed method has an impressive performance on denoising microseismic signals containing various types and intensities of noise. Furthermore, the method works well even when a similar frequency band is shared between the microseismic signals and the noises. The proposed method, compared to the existing methods, significantly improves the signal–noise ratio thanks to minor changes of the microseismic signal (less distortion in the waveform). Additionally, the proposed methods preserve the shape and amplitude characteristics so that it allows better recovery of the real waveform. This method is exceedingly useful for the automatic processing of the microseismic signal. Further, it has excellent potential to be extended to the study of exploration seismology and earthquakes.

The deformation of high-steep rocky banks is caused by the self-weight of overlying rock mass and the fluctuation of reservoir water. In this paper, the newly developed testing equipment and the particle flow code (PFC) were used to complete the cross-scale study of the high-steep rocky banks under different mechanical states. The test conditions involved the dry state, saturated state, and hydraulic coupling states under different confining pressures. Combined with the micrographs of the fractured surface under different mechanical states, it can be found that the participation of the water could reduce the bond contact and accelerate the deformation of the particles, ultimately leading to an increase in the plastic deformation and a decrease in the peak strength of the rock mass. Compared to the saturated state, the water in the hydraulic coupling state was not transferred though the storage space was compressed; thus, the water pressure would further promote the extension of the microcracks. When considering the fluctuations of the reservoir water, the changes in the mechanical state may accelerate the degradation rate of the rock mass. The related methods can provide data support and a theoretical basis to the evolution trend of high-steep rocky reservoir banks.