Hybrid Model for Time Series of Complex Structure with ARIMA Components

Mandrikova, Oksana; Fetisova, Nadezhda; Polozov, Yuryi

doi:10.3390/math9101122

Cited by 28 publications

(19 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In statistical stage, exponential smoothing [4], Kalman filter [5] and auto-regression (AR) [6]. The AR is a basic method [7] and some improved methods have been proposed, such as auto-regressive moving average (ARMA) [8], auto-regressive integrated moving average (ARIMA) [9,10] and other forms [11,12], which have widely applied to time series forecasting in different fields [10,12,13]. The traditional methods are more suitable for the stable time series, but the sunspot a Correspondence to: Nian Fu.…”

Section: Introductionmentioning

confidence: 99%

The Sunspot Number Forecasting Using a Hybridization Model of EMD, LSTM and Attention Mechanism

Yang,

Fu,

Chen

2023

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Sunspot number forecasting is a significant task for human beings in order to observe solar activity, and it is a classical chaotic time series. To improve the forecasting accuracy, we proposed a hybrid forecasting model based on empirical mode decomposition, long short‐term memory neural network and attention mechanism. First, the empirical mode decomposition is used to transfer the sunspot number to several sub‐components called IMFs and residual. Then, the IMFs and residual are input to the prediction module that is composed of long short‐term memory neural network and attention mechanism. Finally, the forecasting result is accumulated by the IMFs and residual through the predict module. The RMSE, MAE, MAPE and R2 indexes of our method are 1.567, 1.048, 1.8% and 0.9997. We also compare with GRU, informer and XGBoost‐DL, our method improves accuracy above 24 and 18 of RMSE and MAE, respectively. The experiment results demonstrate our method has higher precision. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

show abstract

Section: Introductionmentioning

confidence: 99%

The Sunspot Number Forecasting Using a Hybridization Model of EMD, LSTM and Attention Mechanism

Yang,

Fu,

Chen

2023

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

show abstract

“…Classical approaches, such as median construction, regression models, spectral methods etc., widely used for data analysis, do not allow one to detect and to analyze ionospheric anomalies with sufficient effectiveness [2,3,9]. At the present time, modern methods from Data Mining set are being developed to investigate ionospheric data [8,[10][11][12][13]. They make it possible to obtain new knowledge from complex data applying non-conventional approaches and their combinations.…”

Section: Introductionmentioning

confidence: 99%

“…In the paper [8], the authors showed the possibility to combine wavelet filtering with NARX neural networks [14] for detection of anomalous periods in ionopspheric data. In earlier papers [10,15], computational solutions based on discrete wavelet transform and adaptive thresholds were proposed for ionospheric anomaly detection and analysis. In this paper we continue this investigation and propose a complex approach.…”

Section: Introductionmentioning

confidence: 99%

Complex approach to the detection of ionospheric anomalies based on ionospheric foF2 critical frequency data

Mandrikova,

Polozov

2023

29th International Symposium on Atmospheric and Ocean Optics: Atmospheric Physics

Self Cite

View full text Add to dashboard Cite

Time variations of the ionospheric foF2 critical frequency data during magnetic storms of different physical nature are under analysis. Data of Paratunka (53.0° N and 158.7° W, Russia, Kamchatskiy krai) and Wakkanai (45.16° N and 141.75° W, Japan) stations were used. We applied the methods developed on the basis of threshold wavelet filtering and a neural network of NARX architecture. The methods were realized numerically and adapted for the task of ionospheric anomaly detection. The methods results were compared with the 27-day median data. Analysis of the results for different stations showed general characteristic dynamics of ionospheric parameters during magnetic storms. Anomalous increase in electron concentration was observed during the storm main phase. It is likely to be associated with fast penetration of electric field into the plasma layer (PPEF effect). At the recovery phase, electron concentration significantly decreased and negative ionospheric storms developed. The fact of possible pre-increase in the ionosphere before magnetic storms was confirmed. It is of high applied significance.

show abstract

“…In this paper we propose to use the approach developed by the authors [31][32][33]. It is based on wavelet transform, which allows us to investigate complicated nonstationary changes in geophysical data and is widely used in physics, in particularly, in geophysics [4,7,9,26,[34][35][36][37][38]. Based on the wavelet transform, we proposed an automated method to detect geomagnetic pulsations [34,35], constructed an algorithm for automatic detection of magnetic storms with increased risk of occurrence of geomagneticallyinduced currents [3], and developed a method to calculate the geomagnetic activity index WISA [36,38].…”

Section: Introductionmentioning

confidence: 99%

Wavelet Model of Geomagnetic Field Variations and Its Application to Detect Short-Period Geomagnetic Anomalies

2022

Self Cite

View full text Add to dashboard Cite

Geomagnetic data analysis is an important basis for the investigation of the processes in the near-Earth space, Earth magnetosphere, and ionosphere. The negative impact of geomagnetic anomalies on modern technical objects and human health determine the applied significance of the investigation and requires the creation of effective methods for timely detection of the anomalies. Priory complicated structure of geomagnetic data makes their formalization and analysis difficult. This paper proposes a wavelet model for geomagnetic field variations. It describes characteristic changes and anomalies of different amplitude and duration. Numerical realization of the model provides the possibility to apply it in online analysis. We describe the process of model identification and show its efficiency in the detection of sudden, short-period geomagnetic anomalies occurring before and during magnetic storms. Raw second data of the Paratunka and Magadan observatories and post-processed minute data were used in the paper. The question of noise effect on the proposed model results was under consideration.

show abstract

Hybrid Model for Time Series of Complex Structure with ARIMA Components

Cited by 28 publications

References 46 publications

The Sunspot Number Forecasting Using a Hybridization Model of EMD, LSTM and Attention Mechanism

The Sunspot Number Forecasting Using a Hybridization Model of EMD, LSTM and Attention Mechanism

Complex approach to the detection of ionospheric anomalies based on ionospheric foF2 critical frequency data

Wavelet Model of Geomagnetic Field Variations and Its Application to Detect Short-Period Geomagnetic Anomalies

Contact Info

Product

Resources

About