Related papers: Time Series Forecasting: A Nonlinear Dynamics Appr…

The Sun shows a wide range of temporal variations, from a few seconds to decades and even centuries, broadly classified into two classes short-term and Long-term. The solar dynamo mechanism is believed to be responsible for these global…

We attempt to forecast the Sun's sunspot butterfly diagram in both space (i.e. in latitude) and time, instead of the usual one-dimensional time series forecasts prevalent in the scientific literature. We use a prediction method based on the…

Using neural networks as a prediction method, we attempt to demonstrate that forecasting of the Sun's sunspot time series can be extended to the spatial-temporal case. We employ this machine learning methodology to forecast not only in time…

The dynamic activity of the Sun -- sustained by a magnetohydrodynamic dynamo mechanism working in its interior -- modulates the electromagnetic, particulate and radiative environment in space. While solar activity variations on short…

Despite the known general properties of the solar cycles, a reliable forecast of the 11-year sunspot number variations is still a problem. The difficulties are caused by the apparent chaotic behavior of the sunspot numbers from cycle to…

Human living environment is influenced by intense solar activity. The solar activity exhibits periodicity and regularity. Although many deep-learning models are currently used for solar cycle prediction, most of them are based on a…

Time series modeling for predictive purpose has been an active research area of machine learning for many years. However, no sufficiently comprehensive and meanwhile substantive survey was offered so far. This survey strives to meet this…

Prediction models that capture and use the structure of state-space dynamics can be very effective. In practice, however, one rarely has access to full information about that structure, and accurate reconstruction of the dynamics from…

We study the origin of the predictive skill of some methods to forecast the strength of solar activity cycles. A simple flux transport model for the azimuthally averaged radial magnetic field at the solar surface is used, which contains a…

In this paper, we demonstrate the importance of embedding temporal information for an accurate prediction of solar irradiance. We have used two sets of models for forecasting solar irradiance. The first one uses only time series data of…

For oscillating time series, the prediction is often focused on the turning points. In order to predict the turning point magnitudes and times it is proposed to form the state space reconstruction only from the turning points and modify the…

Solar activity cycle varies in amplitude. The last Cycle 24 is the weakest in the past century. Sun's activity dominates Earth's space environment. The frequency and intensity of the Sun's activity are accordant with the solar cycle. Hence…

Sunspot numbers form a comprehensive, long-duration proxy of solar activity and have been used numerous times to empirically investigate the properties of the solar cycle. A number of correlations have been discovered over the 24 cycles for…

The sunspot number data during the past 400 years indicates that both the profile and the amplitude of the solar cycle have large variations. Some precursors of the solar cycle were identified aiming to predict the solar cycle. The polar…

A Bayesian method for forecasting solar cycles is presented. The approach combines a Fokker--Planck description of short--timescale (daily) fluctuations in sunspot number (\citeauthor{NobleEtAl2011}, 2011, \apj{} \textbf{732}, 5) with…

Time series analysis is used to understand and predict dynamic processes, including evolving demands in business, weather, markets, and biological rhythms. Exponential smoothing is used in all these domains to obtain simple interpretable…

A new formula for predicting solar cycles based on the current theoretical understanding of the solar cycle from flux transport dynamo is presented. Two important processes---fluctuations in the Babcock-Leighton mechanism and variations in…

We introduce a technique of time series analysis, potential forecasting, which is based on dynamical propagation of the probability density of time series. We employ polynomial coefficients of the orthogonal approximation of the empirical…

With recent advances in the field of machine learning, the use of deep neural networks for time series forecasting has become more prevalent. The quasi-periodic nature of the solar cycle makes it a good candidate for applying time series…

We introduce a novel modeling approach for time series imputation and forecasting, tailored to address the challenges often encountered in real-world data, such as irregular samples, missing data, or unaligned measurements from multiple…