PCA-MRM Model to Forecast TEC at Middle Latitudes

Abstract

The total electron content (TEC) over the Iberian Peninsula was modelled using PCA-MRM models based on decomposition of the observed TEC series using the principal component analysis (PCA) and reconstruction of the daily modes’ amplitudes by a multiple linear regression model (MRM) using space weather parameters as regressors. The following space weather parameters are used: proxies for the solar UV and XR fluxes, number of the solar flares of different classes, parameters of the solar wind and of the interplanetary magnetic field, and geomagnetic indices. Time lags of 1 and 2 days between the TEC and space weather parameters are used. The performance of the PCA-MRM model is tested using data for 2015, both geomagnetically quiet and disturbed periods. The model performs well for quiet days and days with solar flares but without geomagnetic disturbances. The MAE and RMSE metrics are of the order of 3–5 TECu for daytime and ~2 TECu for night-time. During geomagnetically disturbed periods, the performance of the model deteriorates but only for daytime: MAE and RMSE are of the order of 4–6 TECu and can rise to ~13 TECu for the strongest geomagnetic storms.

Total Electron Content PCA-NN Prediction Model for South-European Middle Latitudes

“…The dataset covering the year 2015 was used to build and test the PCA-MRM model to forecast TEC [6]. This model was used further as a reference model to test the performance of the newly developed prototype for the PCA-NN model.…”

“…The results of [6,13,17] were used to define the set of space weather parameters (SWp) which are predictors for TEC variations in PCA-NN models. In particular, the daily number of flares of different classes (B and C, and M) and the total number of flares (N) are used to understand the most influential (for TEC) class of flares: the total number of flares of any class, the number of the most abundant flares (B and C classes), or the number of moderate flares (M class).…”

“…Neural networks (NN), see, e.g., [2][3][4], and NN in combination with different decomposition methods such as ensemble empirical mode decomposition (EEMD) [5] and principal component analysis (PCA), see [6], and references therein for a review of PCA-NN-based TEC models, as well as, e.g., [7,8] of TEC data are often used to forecast TEC. Most of them use a set of space weather parameters (most often used are the solar F10.7 index and the geomagnetic indices Kp and Dst) as predictors for TEC variations.…”

“…Most of them use a set of space weather parameters (most often used are the solar F10.7 index and the geomagnetic indices Kp and Dst) as predictors for TEC variations. In general (see [6] and references therein), such models allow for forecasting TEC with RMSE or MAE (root mean squared error and mean absolute error, respectively) in a range from ~2 to 15 TECu depending on the season, geomagnetic and solar activity levels during the studied time interval, geographic location, and type of TEC data (single-station data or global ionospheric maps).…”

Research on the Impact of Hydro-PV Complementary System Operation on Power Grid Based on New Energy Consumption

“…Many mathematical models exist to predict PV output [10,11]. Morozova et al [12] proposed a multiple linear regression model (MRM) to reconstruct the daily mode amplitudes and improve the accuracy of the optical power prediction system. Ziadi et al [13] proposed an optimization technique based on load demand and PV generation forecast values to reduce the impact of forecast errors on power generation.…”