Spread-F characteristics over Tucumán near the southern anomaly crest in South America during the descending phase of solar cycle 24

González, Gilda de Lourdes

doi:10.1016/j.asr.2021.11.009

Cited by 7 publications

(4 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar result has also been found by other researchers who showed that in 2015 the season with the lowest SF occurrence rate was during June solstice (González, 2022) though in their case June solstice season include months May to August. Both the lowest and highest ratios are very coarse since they are simply calculated by dividing the total number of SF by the total number of samples in that period.…”

Section: Sf Occurrence Relation To Earth Seasonssupporting

confidence: 88%

Using deep learning for studying spread-F in the ionosphere

Luwanga

View full text Add to dashboard Cite

National Oceanic and Atmospheric Administration (NOAA) agency in the United States of America, has been the most phenomenal advisor. She constantly challenged me to develop a scientific mindset-to say what I can back up with evidence, to think about why things are this way or that, and above all to pay close attention even to the minutest details. I believe that developing a scientific worldview is one of my most significant outcomes from this work, for it is a skill I will apply in life in general.Thank you for the guidance and prodding.I am grateful to Associate Professor Erry Gunawan who provided support by reviewing my progress. He was also kind enough to take over as my supervisor later in my PhD journey. Thank you to Dr. Yu-Ju Lee who helped me with the technicalities of developing good machine learning models.Thank you to the Nanyang Technological University for the resources and environment to do this research, and to the Singapore government and its lovely people for welcoming me here in Singapore. vi At around the age that I am typing this, my mother had five children that she had to take care of on her own. She worried about whether I, or any of us, would make it to secondary school. I now appreciate much more what a giant of a woman she is to have enabled me to come this far. Her love and support have been immense. I dedicate this work to her. Taŵonga amama.

show abstract

Section: Sf Occurrence Relation To Earth Seasonssupporting

confidence: 88%

Using deep learning for studying spread-F in the ionosphere

Luwanga

View full text Add to dashboard Cite

show abstract

“…In short, during quiet time, the ionograms without Spread‐F present clean images containing clear lines as ionospheric traces, indicating the background electron density profile; during disturbance time, the ionograms with different kinds of Spread‐F present vague images containing large color blocks, indicating the structure/irregularity which could affect radio wave propagation (Abdu et al., 1983; Gonzalez, 2022; Pezzopane et al., 2013). Therefore, the prediction of both ionograms with/without Spread‐F is important to the research and application.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Ionograms With/Without Spread‐F at Hainan by a Combined Spatio‐Temporal Neural Network

Gao,

Cai,

Wang

et al. 2024

Space Weather

View full text Add to dashboard Cite

An intelligent high‐definition and short‐term prediction of ionograms with/without Spread‐F for the observation at Hainan (19.5°N, 109.1°E, magnetic 11°N) is presented in this paper, which comprises a spatio‐temporal ConvGRU network and a super‐resolution EDSR network. Our prediction is based on spatio‐temporal features in the ionogram graph only. There are 469,227 ionograms classified into 5 categories, that is, frequency/range/mix/strong range/no Spread F, over a solar cycle (14 years) labeled manually by the research group, and we process these ionograms into two data sets for training the two networks mentioned above. A series of comprehensive experiments have been designed and conducted to determine the optimal super‐parameters. Our method inputs 8 consecutive authentic ionograms (lasting 2 hr) and generates the next 2 figures (next 30 min). Remarkably, all predicted figures achieve a high accuracy rate of over 94% in predicting the occurrence of Spread‐F.

show abstract

“…Although the SF types in ionograms could reveal many processes and mechanisms in the ionosphere, benefiting both science and space weather applications, identifying the characteristic figures still relies on visual inspection (Abdu et al., 1983; Bowman et al., 1988; Gonzalez, 2022; Pezzopane et al., 2013; Rastogi & Woodman, 1978). Recent advancements in machine learning have enabled the automatic identification of certain ionogram features.…”

Section: Introductionmentioning

confidence: 99%

Automatic Detection and Classification of Spread‐F From Ionosonde at Hainan With Image‐Based Deep Learning Method

Wang,

Zhan,

Gao

et al. 2023

Space Weather

View full text Add to dashboard Cite

An intelligent Spread‐F image detection and classification method is presented in this paper based on an ionogram image set using deep learning models. The ionogram images from the Hainan station, spanning from 2002 to 2015, have been manually labeled into five categories, resulting in a unique ionogram image set for supervised learning models. To balance the number of different types, simulated noises were added to these images. Based on 80,000 samples with Spread‐F and 20,000 samples without, numerous experiments have been conducted to train VGG, ResNet, EfficientNet, ViT, MobileNet, and other networks. The results on the test set indicate that these models except VGG have a good ability of exacting features of different types, leading to a high level of accuracy in detecting Spread‐F and a relatively accurate classification of it. The ionogram images in 2016 are then employed as another test set to further examine the performance of the trained models. Both quantitative and qualitative analyses have demonstrated the results obtained by deep learning models are highly consistent with manual identification.

show abstract

Spread-F characteristics over Tucumán near the southern anomaly crest in South America during the descending phase of solar cycle 24

Cited by 7 publications

References 74 publications

Using deep learning for studying spread-F in the ionosphere

Using deep learning for studying spread-F in the ionosphere

Prediction of Ionograms With/Without Spread‐F at Hainan by a Combined Spatio‐Temporal Neural Network

Automatic Detection and Classification of Spread‐F From Ionosonde at Hainan With Image‐Based Deep Learning Method

Contact Info

Product

Resources

About