US 11,914,047 B2
Systems and methods for predicting ionospheric electron content
Isaac P. Moorman, Superior, CO (US)
Assigned to CACI, Inc.—Federal, Reston, VA (US)
Filed by CACI, Inc.—Federal, Arlington, VA (US)
Filed on Dec. 14, 2020, as Appl. No. 17/120,414.
Prior Publication US 2022/0187473 A1, Jun. 16, 2022
Int. Cl. G01S 19/07 (2010.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01)
CPC G01S 19/072 (2019.08) [G06N 3/08 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method for predicting total electron content (TEC) in an ionosphere, comprising:
obtaining a dataset;
preprocessing the obtained dataset by cropping and converting images in the dataset to red, green and blue (RGB) arrays;
inputting the dataset into a machine learning (ML) model, wherein the ML model is a combination of a long short-term memory (LSTM) neural network and a generative adversarial network (GAN) neural network;
training the LSTM-GAN ML model for at least 10 epochs, wherein each epoch includes a cycle of the LSTM-GAN ML model with assigned weights, and wherein the assigned weights are adjusted between successive epochs;
predicting, for a predetermined number of days, the TEC using the LSTM-GAN ML model; and
observing a performance improvement in loss after the at least 10 epochs over the obtained dataset based on the prediction,
wherein the prediction is made for a region having a number of ground transmitters satisfying a sparseness criterion.