Long Short-Term Memory Neural Network for Ionospheric Total Electron Content Forecasting Over China

The aim of this study was to model and predict seasonal ionospheric total electron content (TEC) using artificial neural network (ANN). Within this scope, GPS observations acquired from ANKR GPS station (Turkey) in 2015 were utilized to model TEC variations. Considering all data for each season, training and testing data were set as 80% and 10%, respectively, and the rest of the data were used to estimate TEC values using extracted mathematical models of ANN method. Day of Year (DOY), hour, F107 cm index (solar activity), Kp index and DsT index (magnetic storm index) were considered as the input parameters in ANN. The performances of ANN models were evaluated using RMSE and $R$
 statistical metrics for each season. As a result of the analyses, considering the prediction results, ANN presented more successful predictions of TEC values in winter and autumn than summer and spring with RMSE 3.92 TECU and 3.97 TECU, respectively. On the other hand the $R$
 value of winter data set (0.74) was lower than the autumn data set (0.88) while the RMSE values were opposite. This situation can be caused by the accuracy and precision of data sets. The results showed that the ANN model predicted GPS-TEC in a good agreement for ANKR station.

Modeling and predicting seasonal ionospheric variations in Turkey using artificial neural network (ANN)

The causes of solar variations and their impact on climatic environments have been andstill are the subject of large debate. The possible influence of planetary perturbations on thesolar cycles have also been recently the subject of multiples controverses. The goal of thepresent thesis is to provide some insight on this problem by a new computation of the planetaryperturbations on the Sun, at short, middle and and long time scales.At first, we describe our current understanding of the physical causes of the solar activityand their major observable manifestations, such as the sun spots records. We provide somehistorical background for the numerous records of solar activity proxies. We also review thedifferent approaches to explain the solar planetary relationships through an analysis of thepublished literature.The main purpose of the present work is to study the possible influence of the planetarygravitational perturbations on the solar cycles. In a first part, we analyse the short, middle andlong term solar activity behavior by using the quasiperiodic approximations provided by thefrequency map analysis method to determine the main periodicities of the solar cycles. Thisallows us to provide some reconstruction of the long timescale changes of solar activity variation.The reconstructed activity series are compared with the observed solar activity data and thelong term natural archives such as radioisotopes proxies. The reconstructed series still preservethe well recorded historical grand minima and maxima events and provide us some extendeddata for the study of the long timescale evolution of solar cycles.There has already been some attempts to explain the direct or partial influences of anexternal (e.g., the planets ) or an internal (e.g., its dynamo) effects on the solar changes. In thepresent work, we investigate the planetary tidal influence on solar cycle variations. We havedeveloped a realistic dynamical model for describing the tidal effect exerted by the perturbationof the planets of the Solar system on the deformation of the non-spherical Sun’s surface whichmay partially modulate its activity variations. The model is limited to the dynamical effects ofthe planets on the Sun and do not take account any physical interior process of the Sun. TheSun is considered as an homogeneous three axial non spherical body.The variations of the potential coefficients induced by the effects of body tides are com-puted, using the last INPOP planetary ephemerides and the long term solutions La2004. Thesemi-analytical expressions of the deformation coefficients of potential are derived. Thus, theestimations of the planetary tides effects of each planets and their combinations are comparedto the solar activity records and their reconstructed series. Hence, the correlations between thevariations of the deformation of Sun’s surface and its activity records are discussed.

Search for planetary influences on solar activity

Feed forward neural network based ionospheric model for the East African region

Performance evaluation of neural network TEC forecasting models over equatorial low-latitude Indian GNSS station

This study investigated the effect of student-centered instruction in improving students graphical interpretation skills and conceptual understanding of kinematical motion in Bistu Gebre Michael Catholic general and preparatory school found in Bahir Dar town of Amhara National Regional State, Ethiopia. A total of 77 (39 female and 38 male) grade nine students were involved in the study. The design adopted in the study was non-randomized pre-test and post-test control group design. The instrument used in gathering data for the study was background survey, Graphical Interpretation Skill Test (GIST) and Motion Content Test (MCT). Chi-square (  2 ) and t-test were used as statistical analysis. The internal reliability coefficient of the test was 0.73 using Kuder Richardson Formula-20 (KR-20). The result showed that studentcentered instruction was found to be more promising in improving students‟ graphical interpretation skill and conceptual understanding of kinematical motion.

https://dialnet.unirioja.es/descarga/articulo/3696010.pdf

The Effects of Student-Centered Approach in Improving Students' Graphical Interpretation Skills and Conceptual Understanding of Kinematical Motion

Local TEC modelling and forecasting using neural networks

Modelling the Earth's ionospheric characteristics is the focal task for the ionospheric community to mitigate its effect on the radio communication, and satellite navigation. However, several aspects of modelling are still challenging, for example, the storm time characteristics. This paper presents modelling efforts of TEC taking into account solar and geomagnetic activity, time of the day and day of the year using neural networks (NNs) modelling technique. The NNs have been designed with GPS-TEC measured data from low and mid-latitude GPS stations. The training was conducted using the data obtained for the period from 2011 to 2014. The model prediction accuracy was evaluated using data of year 2015. The model results show that diurnal and seasonal trend of the GPS-TEC is well reproduced by the model for the two stations. The seasonal characteristics of GPS-TEC is compared with NN and NeQuick 2 models prediction when the latter one is driven by the monthly average value of solar flux. It is found that NN model performs better than the corresponding NeQuick 2 model for low latitude region. For the mid-latitude both NN and NeQuick 2 models reproduce the average characteristics of TEC variability quite successfully. An attempt of one day ahead forecast of TEC at the two locations has been made by introducing as drivers previous day solar flux and geomagnetic index values. The results show that a reasonable day ahead forecast of local TEC can be achieved.

A. Tebabal

Papers

The Effects of Student-Centered Approach in Improving Students' Graphical Interpretation Skills and Conceptual Understanding of Kinematical Motion

Feed forward neural network based ionospheric model for the East African region

Local TEC modelling and forecasting using neural networks

Local TEC Modelling and Forecasting using Neural Networks

Modeling total solar irradiance from PMOD composite using feed-forward neural networks