Work Description

==============
| README.txt |
==============

Project Information
===================
Date: 25 May, 2020

Dataset Title: Data for Improvement of Plasma Sheet Neural Network Accuracy with
Inclusion of Physical Information

Dataset Creators: B. M. Swiger, M. W. Liemohn, N. Y. Ganushkina

Dataset Contact: swigerbr@umich.edu (B. M. Swiger)

Primary Funding:
NASA Grant #NNX17AB87G; NASA ROSES Grant #NNX17AI48G, #80NSSC20K0353,
Heliophysics Phase I DRIVE Science Center SOLSTICE #80NSSC20K0600;
Michigan Space Grant Consortium, NASA Grant #NNX15AJ20H.

Key Words:
==========
neural network, plasma sheet, solar wind, machine learning, keV electron flux,
deep learning, feature engineering, space weather

Research Abstract:
==================
The near-Earth plasma sheet is the source for electrons in the inner
magnetosphere. The coupling between the solar wind and the near-Earth plasma
sheet is dominated by non-linear processes, making any relationship difficult
to infer. We report on the development of a neural network to capture the
non-linear behavior between solar wind variations and the response of
energetic electron flux in the plasma sheet. To train the neural network
algorithm, we developed a data set with inputs from solar wind monitoring
spacecraft. The targets come from three probes of the Time History of Events
and Macroscale Interactions during Substorms mission as the spacecraft
traversed the plasma sheet from years 2008-2019. Preliminary findings during
the development of the neural network model show that tuning input parameters
based on previously known physical properties is conducive to improving model
performance.

Methodology:
============
We sampled the near-Earth plasma sheet using data from the NASA Time History of
Events and Macroscale Interactions During Substorms mission. For the
observations of the plasma sheet, we used corresponding interplanetary
observations using the OMNI database. We used these data to develop a
data-driven model that predicts plasma sheet electron flux from upstream
solar wind variations. The model output data are included in this work, along
with code for analyzing the model performance and producing figures used in the
related publication.

Files contained here:
=====================
The files include data files in Python pickle binary format (extension .pkl).
There is a Python source code file (.py extension) and a Jupyter Notebook
(.ipynb extension) that are used to read the data files, calculate metrics,
and create figures. The Jupyter Notebook is also provided as a static PDF.

The same data files are also available in HDF5 format (extension .hdf5).

How to use the data and code:
=============================
Both the Jupyter Notebook and Python source files are self-documented. Python 3
is recommended and assumed will be used. In addition to the standard Python
library, one will need matplotlib, pandas, numpy, and notebook packages.
The Python source files can be run via command line or in any interactive
development environment. Many different version of the above packages will be
compatible. The exact versions are listed in the included conda environment
file (.yml extension).

Related Publication:
====================
Swiger, B. M. et al. 2020. Improvement of Plasma Sheet Neural Network Accuracy
With Inclusion of Physical Information. Frontiers in Astronomy and Space
Science, https://doi.org/10.3389/fspas.2020.00042.

Use and Access:
===============
The data are made available under an Attribution-NonCommercial 4.0
International license (CC BY-NC 4.0).