DOE OSTI · code-176312
WaveDP
Abstract
We developed a robust deep learning model designed to effectively reduce background noise and measure signal arrival times from seismic waveforms. This model processes a 57-second, three-component seismogram to predict the probability of Primary (P) and Secondary (S) waves for each timestamp, while also generating a denoised seismogram. Training was conducted using the benchmark STEAD dataset, which includes globally distributed earthquake signals recorded at local distances ranging from 0 to 350 kilometers.
Keep this discovery
Explore connections, maps & timelines
Chai, Chengping [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (0000000267926014), Rose, Derek [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (0000000252174374), Scott, Stewart [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (0000000343205818), Martindale, Nathan [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (0000000250365433), Adams, Mark [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (0000000254142800). 2026-02-24. WaveDP. https://doi.org/10.11578/dc.20260223.1
Cite the original work for its findings. Save a collection to share your selection of sources.