Skip to content

RAPID EARTHQUAKE EARLY WARNING SYSTEM MACHINE LEARNING FRAMEWORK

License

Notifications You must be signed in to change notification settings

PintCoders/ml-quakes-project

This branch is up to date with SYSTEMS-STUDENT/ml-quakes-project:master.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

b174a86 · Jun 18, 2018

History

14 Commits
Jun 17, 2018
Jun 17, 2018
Jun 17, 2018
Jun 18, 2018
Jun 18, 2018
Jun 18, 2018
Jun 18, 2018
Jun 18, 2018
Jun 18, 2018
Jun 18, 2018
Jun 18, 2018
Jun 18, 2018
Jun 18, 2018
Jun 18, 2018

Repository files navigation

RAPID EARTHQUAKE EARLY WARNING SYSTEM MACHINE LEARNING FRAMEWORK

This work implements four different deep learning model to predict:

  1. The arrival of the S-wave in a four different locations.
  2. The magnitude of the S-wave.
  3. The epicenter.
  4. The depth of the earthquake.

Based on the following independent variable:

  1. Ten different detecting stations's locations.
  2. Ten different detecting stations's P-wave arrival time.

REQUIREMENTS

  1. Having a dedicated NVIDIA GPU + CUDA 8.0

INSTALLING

$ pip install --user pipenv
$ pipenv install --skip-lock

RUNNING IT

$ pipenv run python ./driver.py

Our models start converging at a number of epochs = 2000. Thus to Change the number of epochs:

$ EPOCHS=3000 pipenv run python ./driver.py

AUTHORS

Hero email
Vicente Adolfo Bolea Sanchez vicente.bolea@gmail.com
Olzhas Kaiyrakhmet olzhabay.i@gmail.com>

About

RAPID EARTHQUAKE EARLY WARNING SYSTEM MACHINE LEARNING FRAMEWORK

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 96.1%
  • Shell 3.9%