Essential Site Maintenance: Authorea-powered sites will be updated circa 15:00-17:00 Eastern on Tuesday 5 November.
There should be no interruption to normal services, but please contact us at [email protected] in case you face any issues.

loading page

Automatic Spread-F Detection Using Deep Learning
  • +1
  • Christopher Luwanga,
  • Tzu-Wei Fang,
  • Amal Chandran,
  • Yu-Ju Lee
Christopher Luwanga
Nanyang Technological University

Corresponding Author:[email protected]

Author Profile
Tzu-Wei Fang
CIRES-University of Colorado
Author Profile
Amal Chandran
Nanyang Technological University
Author Profile
Yu-Ju Lee
Cooperative Institute for Research in Environmental Sciences, University of Colorado Boulder
Author Profile

Abstract

Spread-F (SF) is a feature that can be visually observed on ionograms when the ionosonde signals are significantly impacted by plasma irregularities in the ionosphere. Depending on the scale of the plasma irregularities, radio waves of different frequencies are impacted differently when the signals pass through the ionosphere. An automated method for detecting SF in ionograms is presented in this study. Through detecting the existence of SF in ionograms we can help identify instances of plasma irregularities that are potentially affecting the high-frequency radio wave systems. The ionogram images from Jicamarca observatory in Peru, during the years 2008 to 2019, are used in this study. Three machine learning approaches have been carried out: supervised learning using Support Vector Machines, and two neural network-based learning methods: autoencoder and transfer learning. Of these three methods, the transfer learning approach, which uses convolutional neural network architectures demonstrates the best performance. The best existing architecture that is suitable for this problem appears to be the ResNet50. On a test set of 2050 ionograms the ResNet50 model provides an accuracy of 89 percent, recall of 87 percent, precision of 95 percent as well as Area Under the Curve (AUC) of 96 percent. In addition to the model, this work also provides a labelled dataset of over 28,000 ionograms, which is extremely useful for the community for future machine learning studies.
May 2022Published in Radio Science volume 57 issue 5. 10.1029/2021RS007419