Application User Guides > Source and Shaking Parameters Estimation
P Wave Detection Tool user guide
TIP
This document contains instructions for running application P and S Waves Detection Tool within the EPISODES Platform. The application is a tool for automatic detection of the first arrival time of the P waves. The detection is carried out in a time window of 4 seconds. It uses Deep Learning technique based on a convolutional neural network to process the seismograms and detect the first arrival times. The algorithm finds the arrival times with the mean difference from the human-created picks of -0.003 s with the standard deviation of 0.023 s. The model is based on Ross, Meier and Hauksson (2018).
To obtain more general information about working with applications within the Platform, see Applications Quick Start Guide.
NOTE
CATEGORY Source and Shaking Parameters Estimation
KEYWORDS Waveform viewing, Picking on waveform
CITATION If you use the results or visualizations retrieved from this application in a publication, then you must cite the data source as follows:
Ross, Z. E., Meier, M.-A., & Hauksson, E. (2018). P wave arrival picking and first-motion polarity determination with deep learning. Journal of Geophysical Research: Solid Earth, 123, 5120– 5129. doi: 10.1029/2017JB015251.
Orlecka-Sikora, B., Lasocki, S., Kocot, J. et al. (2020) An open data infrastructure for the study of anthropogenic hazards linked to georesource exploitation., Sci Data 7, 89, doi: 10.1038/s41597-020-0429-3.
Input file specification
The application requires a SAC Waveform (or any subtype) containing seismogram on which the wave arrival time should be detected.

Filling form values
The application form has only one value to be filled - the center of the time window in which the algorithm should look for the wave arrival (marked in Figure 2). This might be either filled by hand or chosen from the input seismogram visualisation (by clicking on the plot) - the chosen window center is marked with black dashed line and the area in which the algorithm will be able to find the wave arrival is marked with a light grey background.
Note, that the center of the window will look similar to the pick signifying the wave arrival (see the next section and Figure 3), but the latter has a more exact location within the grey area from Figure 2.

Produced output
The output of the application is a time value marking the wave detection (marked in Figure 3). The time is also displayed as a pick on the original input file.

Related Documents
- Localization user guide
- Phase Association user guide
- Seismic Catalog Recalculation user guide
- Spectral Parameters user guide
- Response Spectra user guide
- P Wave Detection Tool user guide
- P and S Waves Detection Tool user guide
- Estimation of source parameters in time-varying production parameters geometry user guide
- Spectral Analysis user guide
- Seismogram picking tool user guide
- Ground Motion Parameters user guide
- FOCI user guide
- Mechanism: Full Moment Tensor user guide
- Coda Wave Interferometry detection of velocity changes user guide
- Waveform-based seismic event location user guide
- Template-Matching based Detection Algorithm user guide
- Mechanism: Shear-Tensile crack user guide
- Mechanism: Shear slip user guide
- Effective stress drop estimate user guide
