Neural networks for automated classification of ionospheric irregularities in HF radar backscattered signals

Wing, Simon; Greenwald, R. A.; Meng, C.‐I.; Sigillito, V. G.; Hutton, Larrie V.

doi:10.1029/2003rs002869

Cited by 11 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, an NN was used to classify geospace physical boundaries in the plasma data [ Newell et al , 1990, 1991]. More recently, an NN was used to classify high‐frequency (HF) radar backscattered signals [ Wing et al , 2003].…”

Section: Methodsmentioning

confidence: 99%

Kp forecast models

et al. 2005

Self Cite

View full text Add to dashboard Cite

[1] Magnetically active times, e.g., Kp > 5, are notoriously difficult to predict, precisely the times when such predictions are crucial to the space weather users. Taking advantage of the routinely available solar wind measurements at Langrangian point (L1) and nowcast Kps, Kp forecast models based on neural networks were developed with the focus on improving the forecast for active times. To satisfy different needs and operational constraints, three models were developed: (1) a model that inputs nowcast Kp and solar wind parameters and predicts Kp 1 hour ahead; (2) a model with the same input as model 1 and predicts Kp 4 hour ahead; and (3) a model that inputs only solar wind parameters and predicts Kp 1 hour ahead (the exact prediction lead time depends on the solar wind speed and the location of the solar wind monitor). Extensive evaluations of these models and other major operational Kp forecast models show that while the new models can predict Kps more accurately for all activities, the most dramatic improvements occur for moderate and active times. Information dynamics analysis of Kp suggests that geospace is more dominated by internal dynamics near solar minimum than near solar maximum, when it is more directly driven by external inputs, namely solar wind and interplanetary magnetic field (IMF).

show abstract

Section: Methodsmentioning

confidence: 99%

Kp forecast models

et al. 2005

Self Cite

View full text Add to dashboard Cite

show abstract

“…The SKEM and PSKEM classifier algorithms were also tested on a number of other benchmark data sets including (i) rice varieties [36], consisting of 3810 samples of 7-D features in 2 classes; (ii) ionosphere [37], containing 351 samples of 34-D data in 2 classes; (iii) fashion MNIST [38] -a one-for-one replacement for MNIST with 60,000 training and 10,000 greyscale test images of 28 x 28 pixels in 10 classes; (iv) CIFAR-10 [39], which contains 50,000 training and 10,000 test RGB images of 32 x 32 pixels in 10 classes. The rice and ionosphere datasets are available from the UCI archive [40].…”

Section: Further Performance Benchmarksmentioning

confidence: 99%

Improvements to Supervised EM Learning of Shared Kernel Models by Feature Space Partitioning

Pulford¹

2022

Preprint

View full text Add to dashboard Cite

Expectation maximisation (EM) is usually thought of as an unsupervised learning method for estimating the parameters of a mixture distribution, however it can also be used for supervised learning when class labels are available. As such, EM has been applied to train neural nets including the probabilistic radial basis function (PRBF) network or shared kernel (SK) model. This paper addresses two major shortcomings of previous work in this area: the lack of rigour in the derivation of the EM training algorithm; and the computational complexity of the technique, which has limited it to low dimensional data sets. We first present a detailed derivation of EM for the Gaussian shared kernel model PRBF classifier, making use of data association theory to obtain the complete data likelihood, Baum's auxiliary function (the E-step) and its subsequent maximisation (M-step). To reduce complexity of the resulting SKEM algorithm, we partition the feature space into R non-overlapping subsets of variables. The resulting product decomposition of the joint data likelihood, which is exact when the feature partitions are independent, allows the SKEM to be implemented in parallel and at R 2 times lower complexity. The operation of the partitioned SKEM algorithm is demonstrated on the MNIST data set and compared with its non-partitioned counterpart. It eventuates that improved performance at reduced complexity is achievable. Comparisons with standard classification algorithms are provided on a number of other benchmark data sets.

show abstract

“…In particular, several attempts have been made to use neural networks and linear filters for predicting geomagnetic indices and radiation belt electrons (Baker, 1990;Valdivia et al, 1996;Sutcliffe, 1997;Lundstedt, 1997Lundstedt, , 2005Boberg et al, 2000;Vassiliadis, 2000;Gleisner and Lundstedt, 2001;Li, 2001;Vandegriff, 2005;Wing et al, 2005). Neural networks have also been used to classify space boundaries and ionospheric high frequency radar returns (Newell et al, 1991;Wing et al, 2003), and total electron content (Tulunay et al, 2006;Habarulema et al, 2007). A feature that makes space weather very remarkable and perfectly posed for machine learning research is that the huge amount of data is usually collected with taxpayer money and is therefore publicly available.…”

Section: Machine Learning and Space Weathermentioning

confidence: 99%

Introduction

Camporeale

Wing

2018

Machine Learning Techniques for Space Weather

View full text Add to dashboard Cite

A common goal of scientific disciplines is to understand the relationships between observable quantities and to construct models that encode such relationships. Eventually any model, and its supporting hypothesis, needs to be tested against observations-the celebrated Popper's falsifiability criterion (Popper, 1959). Hence, experiments, measurements, and observationsin one word data-have always played a pivotal role in science, at least since the time of Galileo's experiment dropping objects from the leaning tower of Pisa.Yet, it is only in the last decade that libraries' bookshelves have started to pile up with books about the data revolution, big data, data science, and various modifications of these terms. While there is certainly a tendency both in science and publishing to re-brand old ideas and to inflate buzzwords, one cannot deny that the unprecedented large amount of collected data of any sort-be it customer buying preferences, health and genetic records, high energy particle collisions, supercomputer simulation results, or of course, space weather data-makes the time we are living in unique in history. The discipline that benefits the most from the explosion of the data revolution is certainly machine learning. This field is traditionally seen as a subset of artificial intelligence, although its boundaries and definition are somehow blurry. For the purposes of this book, we broadly refer to machine learning as the set of methods and algorithms that can be used for the following problems: (1) make predictions in time or space of a continuous quantity (regression); (2) assign a datum to a class within a prespecified set (classification); (3) assign a datum to a class within a set that is determined by the algorithm itself (clustering); (4) reduce the dimensionality of a dataset, by exposing relationships among variables; and (5) establish linear and nonlinear relationships and causalities among variables.Machine learning is in its golden age today for the simple reason that methods, algorithms, and tools, studied and designed during the last two decades (and sometimes forgotten), have started to produce unexpectedly good results in the last 5 years, exploiting the historically unique combination of big data availability and cheap computing power.The single methodology that has been popularized the most by nonspecialist media as the archetype of machine learning's groundbreaking promise is probably the massive multilayer neural network, which is often referred to as deep learning (LeCun et al., 2015). For instance, deep learning is the technology behind the recent successes in image and speech recognition (with the former recently achieving better-than-human accuracy; He et al., 2015) and the first computer ever defeating a world champion in the game of Go (Silver, 2016).The popular media often focus on the technological applications of machine learning, which has propelled recent advances in many areas, such as self-driving cars, online fraud detection, personalized advertisement and recommendation, real-...

show abstract

Neural networks for automated classification of ionospheric irregularities in HF radar backscattered signals

Cited by 11 publications

References 11 publications

Kp forecast models

Kp forecast models

Improvements to Supervised EM Learning of Shared Kernel Models by Feature Space Partitioning

Introduction

Contact Info

Product

Resources

About