GNSS-RO Machine Learning Feature Sets used for Classification of Cubesat GNSS-RO Disturbances

General Description:

This dataset includes feature sets extracted from GNSS-RO profiles used for multiclass classifcation model training and testing the classifier from 

Dittmann, Chang, & Morton (202?) Machine Learning Classification of Ionosphere and RFI Disturbances in Spaceborne GNSS Radio Occultation Measurements.

In this work we apply a combination of physics-based feature engineering with data-driven supervised machine learning to improve classification of low earth orbit Spire Global GNSS radio occultation disturbances.

Included in this dataset:

data
├── converted_labels.pkl #(feature set catalogs)
├── **.pkl
└── data
├── feature_set_all_single_file
│ └── all_fdf_v2.pkl #(6 months of feature sets concatenated into single object)
└── feature_sets
├── 2022.206.117.01.01.G23.SC001_0001.pkl #(individual profile feature sets)
├── 202***.pkl

References:

This conference proceedings and/or manuscript (TBA) for further description.

This notebook for reproducing this experiment's result and using these datasets.

The python library associated with this dataset.