This project is a part of the MMS mission at the University of Colorado-Boulder's Laboratory for Atmospheric and Space Physics and the University of New Hampshire's Space Science Center.
The mp-dl-unh software is designed to provide automated magnetopause crossing selection suggestions for the SITL selection team. The software uses a TensorFlow Keras LSTM (long short term memory) neural network trained on previous magnetopause selections in order to generate suggested crossing selection windows.
- Matthew R. Argall, University of New Hampshire Space Science Center
- Marek Petrik, University of New Hampshire Department of Computer Science
- Numpy
- Pandas
- Scipy
- Keras
- TensorFlow
- Spacepy