By using shallow seismic exploration, composite drilling section exploration and sample dating test, we have obtained precise positions, burial depths of uppermost point and activity characteristics of Hetan-Guotan buried fault and Zhenjing-Zhenbei buried fault in Zhongwei Basin. The results show that the latest active period of Hetan-Guotan buried fault is the middle-late Middle Pleistocene, and the latest active period of Zhenjing-Zhenbei buried fault is the Early and Middle Pleistocene. The two buried faults became inactive at the end of the Middle Pleistocene and have been inactive since the Late Pleistocene.

Remote-sensing images are visually interpreted in this study to obtain information on buildings in the urban and rural areas of Ningxia, China. Overall, area estimates yielded by the proposed equations followed a normal distribution. Correlation and error analyses indicated that the coefficients are reasonable and reliable and that the building area estimates have an accuracy of 90% and are also reliable. These results were used in conjunction with drone aerial images, Baidu street view images, and paper maps to determine the seismic performance (SP) of the buildings in the study area. On this basis, the buildings were classified into three groups, namely, those with the required SP, suspected substandard SP, and substandard SP. Examination based on the field survey data collected from at least one sample site in each village and township in all 22 county-level divisions (CLDs) of Ningxia showed an average SP accuracy of 76% for all 22 CLDs and an SP accuracy exceeding 70% for 20 (91%) of the 22 CLDs. Based on this approach and the results obtained, the ArcGIS spatial analysis method was employed to determine the percentages and distribution patterns of the buildings in the three SP groups in the 22 CLDs. The results revealed the following features. Buildings with the required SP were clustered in the urban areas of each CLD, with a few in the village and township government seats. Buildings with suspected substandard SP were distributed predominantly in the rural-urban fringe (RUF) areas and the village and township government seats. Buildings with substandard SP were found primarily in urban villages, RUF areas, and urban areas. The soundness of the spatial analysis results was corroborated by the field survey data, lending credence to the feasibility of the proposed calculation method. This method can satisfy the real-world need for rapidly assessing the SP and distribution of buildings in a region before an earthquake occurs and provide a reliable reference for disaster prevention, mitigation, and relief efforts.

Accurately and quickly identifying the types of natural and unnatural earthquake events is the basic premise of monitoring, prediction, early warning, and other study in the field of seismology, which is of great significance to the prevention, evaluation, emergency rescue, and other work of earthquake disasters. Convolutional neural network model is a representative artificial intelligence deep learning algorithm, which has been widely used in computer vision, natural language processing, object type identification, and other fields in recent years. In this study, AlexNet convolutional neural network model is selected to study the type identification of 1539 earthquake event waveform records in and around Ningxia Hui Autonomous Region, China. Earthquake event waveform records contain three types: natural earthquake, explosion, and collapse, in which both explosion and collapse are unnatural earthquakes. MATLAB software is used to build the training module and test module for AlexNet convolutional neural network model, and the earthquake event waveform record is transformed into an image format file of 224 times 224 pixels as input parameters. Finally, AlexNet convolutional neural network model has the ability of automatic identification of earthquake event types. The results of this study show that the identification accuracy of earthquake event type in training module is 99.97%, the average value of loss function is 0.001, the identification accuracy of earthquake event type in test set is 98.51%, and the average value of loss function is 0.059. After training and testing, 60 different types of earthquake event waveform records were randomly selected, and AlexNet convolutional neural network model was used to identify them automatically. The automatic identification accuracy of natural earthquakes, explosions, and collapses was 90%, 80%, and 85%, respectively. After training AlexNet convolutional neural network model with earthquake event waveform records, it can have accurate and fast automatic identification ability. The accuracy of automatic identification is comparable to that of professional seismic workers, and the time of automatic identification is greatly reduced compared with that of professional seismic workers. This study can provide an implementation idea of deep learning based on artificial intelligence for the identification of earthquake event types and make contributions to the cause of earthquake prevention and disaster reduction.

Based on a large amount of drilling and geophysical exploration work in the Zhongwei Basin, and combined with the collected borehole data of a seismic safety assessment, this paper summarizes and builds 16 typical pebble soil layer calculation models. The effects of the thickness of the pebble layer, the thickness of the overlying silty clay, the top interface of the pebble layer on the peak acceleration and the response spectrum of the site seismic response were analyzed using the equivalent linearization method of the one-dimensional soil layer seismic response. The analysis results showed that the variation in pebble layer thickness had no obvious effect on the peak acceleration of the ground surface under different inputs; the influence of the pebble layer thickness on the ground acceleration response spectrum was primarily concentrated in the middle/high-frequency band of 0.2–0.6 s. Within this range, the acceleration response spectrum of the site with a 30 m pebble layer thickness was small, and the response spectrum curve showed a “trough” shape with a certain “weak isolation” effect. Under the same pebble layer thickness, the upper ground surface peak acceleration with a silty clay layer thickness increased with the increase in the central basin pebble soil field, where a short cycle of the seismic wave amplification effect was more obvious. The response spectrum peak period points were within 0.1–0.2 s and were influenced by the action of rare earthquakes. Moreover, the response spectrum curve showed a more obvious phenomenon of “twin peaks”, and the second peak point appeared in the period of 0.5–0.7 s. With the increase in the input intensity, the PGA amplification ratio of the pebble-top interface was significantly smaller than that of the site surface; under different intensities of input, the acceleration response spectrum of the pebble-top interface showed a “trough” phenomenon that was lower than the bedrock input at approximately 0.1 s. Under the action of rare ground motion, the acceleration response spectrum curve of the pebble-top interface showed a “double peak” phenomenon, and within 0.24–0.4 s, the spectrum value was lower than the bedrock input, showing an obvious shock absorption and isolation effect. Under the action of an earthquake, the energy of the pebble-top interface was concentrated in the low-frequency range of 1.1–2.2 Hz, and the amplification effect was obvious. In the range of 8–10 Hz, the amplitude was lower than the bedrock input, and the seismic isolation effect was obvious.