The conventional arrival pick-up algorithms cannot avoid the manual modification of the parameters for the simultaneous identification of multiple events under different signal-to-noise ratios (SNRs). Therefore, in order to automatically obtain the arrivals of multiple events with high precision under different SNRs, in this study an algorithm was proposed which had the ability to pick up the arrival of microseismic or acoustic emission events based on deep recurrent neural networks. The arrival identification was performed using two important steps, which included a training phase and a testing phase. The training process was mathematically modelled by deep recurrent neural networks using Long Short-Term Memory architecture. During the testing phase, the learned weights were utilized to identify the arrivals through the microseismic/acoustic emission data sets. The data sets were obtained by rock physics experiments of the acoustic emission. In order to obtain the data sets under different SNRs, this study added random noise to the raw experiments’ data sets. The results showed that the outcome of the proposed method was able to attain an above 80 per cent hit-rate at SNR 0 dB, and an approximately 70 per cent hit-rate at SNR −5 dB, with an absolute error in 10 sampling points. These results indicated that the proposed method had high selection precision and robustness.

A novel ground penetrating radar (GPR)-based subsurface water content classification and prediction technique using deep neural networks is proposed. The fantastic advantages of deep network in classification and regression tasks show the huge potential to measure soil moisture content status quickly after the network trained. The technique is based on convolutional neural network (CNN), and does not need to extract data features in advance. We design two CNNs for the classification and regression tasks separately. Both networks can be divided into two parts: convolutional layers following max-pooling layers to extract features, and classifier or regressor part for output prediction. One network’s output is a classification prediction (moisture quantitative classification), the other is prediction of a continuous variable (water content). We train the classification network firstly, and then use transfer learning technique to reuse the feature extraction part to train the regression network. With application of transfer learning, the regression task needs less training dataset and can achieve a good performance. Our method can be applied on many field, such as roadbed maintenance and continuous soil water content estimation.

Case retrieval is the major step in case-based reasoning (CBR). The similarity measurement between historical cases and the target case is very important in the case retrieval, and affects the results of the decision. In CBR practical application, there are hybrid attribute values for case attributes. The representation of the case and performing case retrieval with high retrieval accuracy for hybrid multiple formats of attribute values are significant challenges, but an in-depth study is lacking. The objective of this paper is to develop a new case retrieval method to hybrid multi-attribute, which contains four formats of attribute values, i.e., crisp numbers, interval numbers, multi-granularity linguistic variables, and intuitionistic fuzzy numbers (IFNs). First, crisp numbers, interval numbers, and multi-granularity linguistic variables are transformed into IFNs and an attribute similarity measurement based on IFNs is proposed. The attribute weights are determined by an optimal matching model. This model belongs to a type of multi-objective problem and can be solved using the min-max method. Furthermore, the case similarities between historical cases and the target case are obtained by aggregating attribute similarities using evidence reasoning, and the proper historical case(s) can be retrieved according to the obtained hybrid case similarities. Finally, a case study of the gas explosion in China’s Fujian province is conducted to demonstrate the proposed approach and its potential application.

It is important to autopick an event’s arrival time and classify the corresponding phase for seismic data processing. Traditional arrival-time picking algorithms usually need 3C seismograms to classify event phase. However, a large number of borehole seismic data sets are recorded by arrays of hydrophones or distributed acoustic sensing elements whose sensors are 1C and cannot be analyzed for particle motion or phase polarization. With the development of deep learning techniques, researchers have tried data mining with the convolutional neural network (CNN) for seismic phase autopicking. In the previous work, CNN was applied to process 3C seismograms to detect phase and pick arrivals. We have extended this work to process 1C seismic data and focused on two main points. One is the effect of the label vector on the phase detection performance. The other is to propose an architecture to deal with the challenge from the insufficiency of training data in the coverage of different scenarios of VP/VS ratios. Two novel points are summarized after this analysis. First, the width of the label vector can be designed through signal time-frequency analysis. Second, a combination of CNN and recurrent neural network architecture is more suitable for designing a P- and S-phase detector to deal with the challenge from the insufficiency of training data for 1C recordings in time-lapse seismic monitoring. We perform experiments and analysis using synthetic and field time-lapse seismic recordings. The experiments show that it is effective for 1C seismic data processing in time-lapse monitoring surveys.