Exploring the Potential of Neural Networks to Predict Statistics of Solar Wind Turbulence
Abstract Time series data sets often have missing or corrupted entries, which need to be handled in subsequent data analysis. For example, in the context of space physics, calibration issues, satellite telemetry issues, and unexpected events can make parts of a time series unusable. This causes prob...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-09-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2022SW003200 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536325169184768 |
|---|---|
| author | Daniel Wrench Tulasi N. Parashar Ritesh K. Singh Marcus Frean Ramesh Rayudu |
| author_facet | Daniel Wrench Tulasi N. Parashar Ritesh K. Singh Marcus Frean Ramesh Rayudu |
| author_sort | Daniel Wrench |
| collection | DOAJ |
| description | Abstract Time series data sets often have missing or corrupted entries, which need to be handled in subsequent data analysis. For example, in the context of space physics, calibration issues, satellite telemetry issues, and unexpected events can make parts of a time series unusable. This causes problems for understanding the dynamics of the heliosphere and space weather environment. Various approaches exist to tackle this problem, including mean/median imputation, linear interpolation, and autoregressive modeling. Here, we study the utility of artificial neural networks (ANNs) to predict statistics of sparse time series. Our focus is not on time series prediction but on gleaning the best possible information about the statistical behavior of the system. As an example application, we focus on the structure functions of turbulent time series measured in the solar wind. Using a data set with artificial gaps, a neural network is trained to predict second‐order structure functions and then tested on an unseen data set to quantify its performance. A small feedforward ANN, with only 20 hidden neurons, can predict the large‐scale fluctuation amplitudes better than mean imputation or linear interpolation when the percentage of missing data is high. Although they perform worse than the other methods when it comes to capturing both the shape and fluctuation amplitude together, their performance is better in a statistical sense for large fractions of missing data. Caveats regarding their utility, the optimization procedure, and potential future improvements are discussed. |
| format | Article |
| id | doaj-art-426ecb61d750499daa2a83d1a229b3a2 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2022-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-426ecb61d750499daa2a83d1a229b3a22025-01-14T16:31:12ZengWileySpace Weather1542-73902022-09-01209n/an/a10.1029/2022SW003200Exploring the Potential of Neural Networks to Predict Statistics of Solar Wind TurbulenceDaniel Wrench0Tulasi N. Parashar1Ritesh K. Singh2Marcus Frean3Ramesh Rayudu4Victoria University of Wellington Wellington New ZealandVictoria University of Wellington Wellington New ZealandDepartment of Physical Sciences Indian Institute of Science Education and Research Kolkata Mohanpur IndiaVictoria University of Wellington Wellington New ZealandVictoria University of Wellington Wellington New ZealandAbstract Time series data sets often have missing or corrupted entries, which need to be handled in subsequent data analysis. For example, in the context of space physics, calibration issues, satellite telemetry issues, and unexpected events can make parts of a time series unusable. This causes problems for understanding the dynamics of the heliosphere and space weather environment. Various approaches exist to tackle this problem, including mean/median imputation, linear interpolation, and autoregressive modeling. Here, we study the utility of artificial neural networks (ANNs) to predict statistics of sparse time series. Our focus is not on time series prediction but on gleaning the best possible information about the statistical behavior of the system. As an example application, we focus on the structure functions of turbulent time series measured in the solar wind. Using a data set with artificial gaps, a neural network is trained to predict second‐order structure functions and then tested on an unseen data set to quantify its performance. A small feedforward ANN, with only 20 hidden neurons, can predict the large‐scale fluctuation amplitudes better than mean imputation or linear interpolation when the percentage of missing data is high. Although they perform worse than the other methods when it comes to capturing both the shape and fluctuation amplitude together, their performance is better in a statistical sense for large fractions of missing data. Caveats regarding their utility, the optimization procedure, and potential future improvements are discussed.https://doi.org/10.1029/2022SW003200turbulencemachine learningmissing datatime seriessolar wind |
| spellingShingle | Daniel Wrench Tulasi N. Parashar Ritesh K. Singh Marcus Frean Ramesh Rayudu Exploring the Potential of Neural Networks to Predict Statistics of Solar Wind Turbulence Space Weather turbulence machine learning missing data time series solar wind |
| title | Exploring the Potential of Neural Networks to Predict Statistics of Solar Wind Turbulence |
| title_full | Exploring the Potential of Neural Networks to Predict Statistics of Solar Wind Turbulence |
| title_fullStr | Exploring the Potential of Neural Networks to Predict Statistics of Solar Wind Turbulence |
| title_full_unstemmed | Exploring the Potential of Neural Networks to Predict Statistics of Solar Wind Turbulence |
| title_short | Exploring the Potential of Neural Networks to Predict Statistics of Solar Wind Turbulence |
| title_sort | exploring the potential of neural networks to predict statistics of solar wind turbulence |
| topic | turbulence machine learning missing data time series solar wind |
| url | https://doi.org/10.1029/2022SW003200 |
| work_keys_str_mv | AT danielwrench exploringthepotentialofneuralnetworkstopredictstatisticsofsolarwindturbulence AT tulasinparashar exploringthepotentialofneuralnetworkstopredictstatisticsofsolarwindturbulence AT riteshksingh exploringthepotentialofneuralnetworkstopredictstatisticsofsolarwindturbulence AT marcusfrean exploringthepotentialofneuralnetworkstopredictstatisticsofsolarwindturbulence AT rameshrayudu exploringthepotentialofneuralnetworkstopredictstatisticsofsolarwindturbulence |