Microseismic data have a low signal-to-noise ratio (S/N). Existing waveform classification and arrival-picking methods are not effective enough for noisy microseismic data with low S/N. We have adopted a novel antinoise classifier for waveform classification and arrival picking by combining the continuous wavelet transform (CWT) and the convolutional neural network (CNN). The proposed CWT-CNN classifier is applied to synthetic and field microseismic data sets. Results show that CWT-CNN classifier has much better performance than the basic deep feedforward neural network (DNN), especially for microseismic data with low S/N. The CWT-CNN classifier has a shallow network architecture and small learning data set, and it can be trained quickly for different data sets. We have determined why CWT-CNN has better performance for noisy microseismic data. CWT can decompose the microseismic data into time-frequency spectra, where effective signals and interfering noise are easier to distinguish. With the help of CWT, CNN can focus on the specific frequency components to extract useful features and build a more effective classifier.

The reservoir quality of tight sandstone is usually affected by pore throat structures, and understanding pore throat structures and their fractal characteristics is crucial for the exploration and development of tight sandstone gas. In this study, fractal dimensions of pore throat structures and the effect of diagenesis on the fractal dimension of tight sandstone sweet spot in Huagang Formation, Jiaxing area, East China Sea Basin were studied by means of thin sections, scanning electron microscopes, X-ray diffraction analysis, scanning electron microscope quantitative mineral evaluation, and high pressure mercury injection experiments. The results show that the total fractal dimension ranges of type I, type II, and type III sweet spots were 2.62–2.87, 2.22–2.56, and 2.71–2.77, respectively. The negative correlation between total fractal dimensions, porosity, and permeability of type I sweet spots was different from those of type II and type III sweet spots. The negative correlation between total fractal dimensions of type II and type III sweet spots and maximum mercury saturation, average pore throat radius, and skewness were significant, whereas the correlation between total fractal dimensions of type I sweet spots, and maximum mercury saturation, average pore throat radius and skewness were not significant. The positive correlation between the total fractal dimensions of type II and type III sweet spots and the relative sorting coefficient, displacement pressure, and efficiency of mercury withdrawal were significant, whereas the correlation between the total fractal dimension of type I sweet spots and relative sorting coefficients, displacement pressures and efficiency of mercury withdrawal were not significant. The effect of diagenesis on fractal dimensions was investigated. Compaction reduced the pore space of tight sandstone and increased fractal dimensions. Quartz cementation and calcite cementation blocked pores and throats, reduced pore space, and increased fractal dimensions. Chlorite coat can inhibit compaction, protect pore throat structures, and maintain fractal dimensions. Most clay minerals filled primary pores and secondary pores and increased fractal dimensions. Dissolution increased the pore space of tight sandstone and decreased the fractal dimensions of the pore throat structures. The pore throat structures of type I sweet spots were mainly composed of macropores, mesopores, transitional pores, and micropores, and the fractal dimension of type I sweet spots was chiefly controlled by chlorite coat formation, dissolution, and a small amount of compaction. This study provides a reference for pore throat structure and fractal dimension analysis of tight sandstone sweet spots.