TroyNet (Picker-only) Deep Learning Model for Seismic Phase Picking

This repository contains the small test dataset and trained model files used to evaluate TroyNet deep learning model developed for automated seismic phase picking in northwestern Türkiye. The dataset includes a few thousands labeled three-component seismograms (30 seconds long, sampled at 100 Hz), each annotated with manually picked P- and S-wave arrivals. Our original training, validation and test data have 198K waveforms that were recorded between 2008 and 2022 by KOERI and regional seismic networks, all preprocessed with 1–45 Hz bandpass filtering and amplitude normalization. In addition to the small test dataset, this archive provides two training model checkpoints to compare TroyNet against PhaseNet, and a Python script for running the tests.