PmPNet, A Deep Neural Network for Creating Reliable PmP Database

By utilizing the high-quality PmP dataset (10,192 manual picks by Li et al., 2022) in southern California, we develop PmPNet (Ding et al., 2022), a deep-neural-network-based algorithm to automatically identify PmP waves efficiently. PmPNet applies similar techniques in the machine learning community to address the unbalancement of PmP datasets. The trained optimal PmPNet can efficiently achieve high precision and high recall simultaneously to automatically identify PmP waves from a massive seismic database. Here, we share our developed code with the community, for more detailed information about the code (running environment set-up, usage, etc.), please refer to PmPWorld documentation.