English
Related papers

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

200 papers

The Sun's activity cycle governs the radiation, particle and magnetic flux in the heliosphere creating hazardous space weather. Decadal-scale variations define space climate and force the Earth's atmosphere. However, predicting the solar…

Solar and Stellar Astrophysics · Physics 2019-09-11 Prantika Bhowmik , Dibyendu Nandy

Time series forecasting is a critical task in various domains, where accurate predictions can drive informed decision-making. Traditional forecasting methods often rely on current observations of variables to predict future outcomes,…

Machine Learning · Computer Science 2026-03-17 Wentao Gao , Xiaojing Du , Wenjun Yu , Xiongren Chen , Yifan Guo , Feiyu Yang

The relative number of sunspots represents the longest evidence describing the level of solar activity. As such, its use goes beyond solar physics, e.g. towards climate research. The construction of a single representative series is a…

Solar and Stellar Astrophysics · Physics 2022-12-07 Michal Švanda , Martina Pavelková , Jiří Dvořák , Božena Solarová

The prediction of the evolution of individual solar cycles is a developing field, faced with divergence of forecasts even for a few years in the future. Specifically for solar flares, long-term modeling is practically absent even in rough…

Solar and Stellar Astrophysics · Physics 2020-07-30 Eleni Petrakou

As the use of solar power increases, having accurate and timely forecasts will be essential for smooth grid operators. There are many proposed methods for forecasting solar irradiance / solar power production. However, many of these methods…

Machine Learning · Computer Science 2023-07-11 Timothy Cargan , Dario Landa-Silva , Isaac Triguero

We present the assessment of a diffusion-dominated mean field axisymmetric dynamo model in reproducing historical solar activity and forecast for solar cycle 25. Previous studies point to the Sun's polar magnetic field as an important proxy…

Solar and Stellar Astrophysics · Physics 2018-06-29 Alejandro Macario-Rojas , Katharine L. Smith , Peter C. E. Roberts

In the prediction of oscillating time series, the interest is in the turning points of successive oscillations rather than the samples themselves. For this purpose a scheme has been proposed; the state space reconstruction is limited to the…

Chaotic Dynamics · Physics 2008-09-15 D. Kugiumtzis , I. Vlachos

The magnetic cycle of the Sun, as manifested in the cyclic appearance of sunspots, significantly influences our space environment and space-based technologies by generating what is now termed as space weather. Long-term variation in the…

Solar and Stellar Astrophysics · Physics 2011-10-27 Dibyendu Nandy

Space weather is a matter of practical importance in our modern society. Predictions of forecoming solar cycles mean amplitude and duration are currently being made based on flux-transport numerical models of the solar dynamo. Interested in…

Solar and Stellar Astrophysics · Physics 2013-12-05 Sabrina Maite Sanchez , Alexandre Fournier , Julien Aubert

In this paper, we show empirical evidence on how to construct the optimal feature selection or input representation used by the input layer of a feedforward neural network for the propose of forecasting spatial-temporal signals. The…

Neural and Evolutionary Computing · Computer Science 2019-07-24 Eurico Covas , Emmanouil Benetos

The solar cycle onset at mid-latitudes, the slow down of the sunspot drift toward the equator, the tail-like attachment and the overlap of successive cycles at the time of activity minimum are delicate issues in $\alpha\Omega$ dynamo wave…

Solar and Stellar Astrophysics · Physics 2016-09-07 R. Simoniello , S. C. Tripathy , K. Jain , F. Hill

Dynamics of complex systems is studied by first considering a chaotic time series generated by Lorenz equations and adding noise to it. The trend (smooth behavior) is separated from fluctuations at different scales using wavelet analysis…

Chaotic Dynamics · Physics 2009-11-11 Dilip P. Ahalpara , Jitendra C. Parikh

Time-series forecasting plays an important role in many domains. Boosted by the advances in Deep Learning algorithms, it has for instance been used to predict wind power for eolic energy production, stock market fluctuations, or motor…

Machine Learning · Computer Science 2021-07-23 Luis P. Silvestrin , Leonardos Pantiskas , Mark Hoogendoorn

Forecasting the evolution of complex systems is one of the grand challenges of modern data science. The fundamental difficulty lies in understanding the structure of the observed stochastic process. In this paper, we show that every…

Statistics Theory · Mathematics 2020-01-01 Xiucai Ding , Zhou Zhou

We compare two candidate nonlinearities for regulating the solar cycle within the Babcock-Leighton paradigm: tilt quenching (whereby the tilt of active regions is reduced in stronger cycles) and latitude quenching (whereby flux emerges at…

Solar and Stellar Astrophysics · Physics 2024-12-04 Anthony R. Yeates , Luca Bertello , Alexander A. Pevtsov , Alexei A. Pevtsov

The paper introduces a novel topological method for prediction and modeling for a nonlinear time--series that exhibit recurring patterns. According to the model, global manifold of the reconstructed state--space can be approximated by a few…

Chaotic Dynamics · Physics 2017-11-21 Sajini Anand P S , Prabhakar G Vaidya

This paper compares different forecasting methods and models to predict average values of solar irradiance with a sampling time of 15 min over a prediction horizon of up to 3 h. The methods considered only require historic solar irradiance…

Applications · Statistics 2019-07-30 Christian A. Hans , Elin Klages

Satellite-based solar irradiation forecasting is useful for short-term intra-day time horizons, outperforming numerical weather predictions up to 3-4 hours ahead. The main techniques for solar satellite forecast are based on sophisticated…

Atmospheric and Oceanic Physics · Physics 2020-09-02 Franco Marchesoni-Acland , Rodrigo Alonso Suárez

Deep learning has shown impressive results in a variety of time series forecasting tasks, where modeling the conditional distribution of the future given the past is the essence. However, when this conditional distribution is…

Machine Learning · Computer Science 2024-02-27 Siqi Liu , Andreas Lehrmann

We propose a retrodictive forecasting paradigm for time series: instead of predicting the future from the past, we identify the future that best explains the observed present via inverse MAP optimization over a Conditional Variational…

Machine Learning · Computer Science 2026-03-03 Cedric Damour