Exploring the potential of neural networks to predict statistics of solar wind turbulence

Abstract

Time series datasets often have missing or corrupted entries, which need to be ignored 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. 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, particularly second-order structure functions, of turbulent time series concerning the solar wind. Using a dataset with artificial gaps, a neural network is trained to predict second-order structure functions and then tested on an unseen dataset 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 optimisation procedure, and potential future improvements are discussed.

17 pages, 5 figures, 2 tables

References in corpus (7)

• Solar Flare Prediction Using SDO/HMI Vector Magnetic Field Data with a Machine-Learning Algorithm
• The Evolution and Role of Solar Wind Turbulence in the Inner Heliosphere
• Classification of Solar Wind with Machine Learning
• Physical Interpretation of the Angle Dependent Magnetic Helicity Spectrum in the Solar Wind: The Nature of Turbulent Fluctuations near the Proton Gyroradius Scale
• Magnetic turbulence spectra and intermittency in the heliosheath and in the local interstellar medium
• Stochastic interpolation of sparsely sampled time series via multi-point fractional Brownian bridges
• Identifying magnetic reconnection in 2D Hybrid Vlasov Maxwell simulations with Convolutional Neural Networks

Cited by in corpus (2)

• Identifying Galaxy Cluster Mergers with Deep Neural Networks using Idealized Compton-y and X-ray maps
• De-Biasing Structure Function Estimates From Sparse Time Series of the Solar Wind: A Data-Driven Approach