Data for Monitoring Fracture Saturation with Internal Transportable Seismic Sources and Twin Neural Networks

<p>Seismic coda-wave analysis is a well-developed method for detecting subtle physical changes in complex media by measuring arrival times in the late-arriving energy from multiply-scattered or reflected waves. However, a challenge arises when multiply-scattered waves are not sufficiently separated in time from the direct arrivals to provide a clear coda wave train. Additional complications for monitoring changes in fracture systems arise when the signals originate from unsynchronized internal sources, such as natural induced seismicity, from acoustic emission, or from transportable intra-fracture sources (chattering dust), that generate uncontrolled signals that vary in arrival time, amplitude and frequency content. Here, we use a twin neural network (also known as a Siamese neural network) for dimensionality reduction to analyze signals from chattering dust to classify the fluid saturation state of a synthetic fracture system. The twin neural network with shared weights generates a low-dimensional representation of the data input by minimizing contrastive loss, serving as the input to a multiclass classifier that accurately classifies whether multiple fractures in a fracture system are fully saturated or partially saturated, or whether a change in saturation has occurred in different fractures in the system. These results show that information buried in unresolved codas from uncontrolled sources can be extracted using machine learning to monitor the evolution of fracture systems caused by physical and chemical processes even when the scattered and direct wave fields overlap.</p>

<p>The data sets used in the analysis are contained in this data set.  </p>

<p>Dataset S1: This data set contains the cleaned and normalized signals from the moving source experiments for the 2 class analysis. The S1.zip file contacts an information file (READ_ME_Moving_2_20210411_Infomation) about the number of signals, time per points and column information in the “.txt” files in the 6 directories.  The directory names are based on the group numbers listed in Supplement Table S5.  </p>

<p>Dataset S2: This data set contains the cleaned and normalized signals from the moving source experiments for the 4 class analysis The S2.zip file contacts an information file (README_5_W0W1R2P3W4P5_Information.rtf) about the number of signals, time per points and column information in the “.txt” files in the 4 directories.  The directory names are based on the group numbers listed in Supplement Table S5.  </p>

<p>Dataset S3: This data set contains the original signals from the stationary source experiments for the 4 class non-prospective analysis The S3.zip file contacts 4 directories that each contain a README file with information file about the number of signals, time per points. The directory names are based on the group numbers listed in Supplement Table S5.  The first column of the data file contains the test number, the second column represents the event number for a particular test and the 3rd column is set to 0. The rest of the columns contain the signals.</p>

<p>Dataset S4: This data set contains the original signals from the stationary source experiments for the 4 class -prospective analysis.  The S4.zip file contacts 8 directories that each contain a README file with information file about the number of signals, time per points. The directory names are based on the group numbers listed in Supplement Table S5.  The first column of the data file contains the test number, the second column represents the event number for a particular test and the 3rd column is set to 0. The rest of the columns contain the signals.</p>