Skip to content

Notebooks to partition a chunk of the STanford EArthquake Dataset (STEAD) and convert it to SeisBench format.

Notifications You must be signed in to change notification settings

Akari-T/STEAD-Data-to-SeisBench-Data

Repository files navigation

Converting from STanford EArthquake Dataset (STEAD) Format to Seisbench Format

Quick Overview: Google Colab notebooks to parse STEAD data, convert STEAD formatted data to Seisbench formatted data.

Motivation: To retrieve a small subset of the STEAD data, and convert to Seisbench format to use for Seisbench models.

  1. parse_STEAD_data.ipynb: Given a .hdf5 and .csv file pair from STEAD, takes a subset of the data. (Note: The STEAD Github shows a better method for partitioning data.)
  2. convert_STEAD_to_Seisbench.ipynb: Given a STEAD formatted dataset, converts the data to SeisBench format. Creates an .hdf5 and .csv file pair.

Developed for UW CSE547 Project.


prase_STEAD_data.ipynb

Creates a STEAD formatted .hdf5 and .csv file pair containing a subset of noise waveforms (STEAD chunk1) and a subset of earthquake waveforms (STEAD chunk2).


convert_STEAD_to_Seisbench.ipynb

Converts a STEAD formatted .hdf5 and .csv file pair to a SeisBench formatted .hdf5 and .csv file pair.


Possible Improvements: Use RDDs?

About

Notebooks to partition a chunk of the STanford EArthquake Dataset (STEAD) and convert it to SeisBench format.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published