Geodesic
The use of long short-term memory and gated recurrent unit for predicting the values of geomagnetic indices
Vestnik KRAUNC. Fiziko-matematičeskie nauki, Tome 33 (2020) no. 4, pp. 110-121

Voir la notice de l'article provenant de la source Math-Net.Ru

In this work, with the help of deep learning, predicting the values of the following geomagnetic indices (GI) is considered: Dst, Kp, AE and Ap. For forecasting we use the architectures are long short-term memory (LSTM) and gated recurrent unit (GRU). For various GI indices, the loss function is analyzed depending on the periodicity of the source data. It has been established that forecasting accuracy increases with decreasing periodicity of the initial data of geomagnetic indices. For the analysis, the following periods of the initial GI data were used: hour, 3 hours, day. For the analysis we used hour, 3 hours and day periods of the initial GI source data.
Keywords: geomagnetic indices, forecasting, Dst index, Kp-index, AE index, AP index, long short-term memory, managed recurrent blocks. 
@article{VKAM_2020_33_4_a9,
     author = {V. A. Mochalov and A. V. Mochalova},
     title = {The use of long short-term memory and gated recurrent unit for predicting the values of geomagnetic indices},
     journal = {Vestnik KRAUNC. Fiziko-matemati\v{c}eskie nauki},
     pages = {110--121},
     publisher = {mathdoc},
     volume = {33},
     number = {4},
     year = {2020},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VKAM_2020_33_4_a9/}
}
TY  - JOUR
AU  - V. A. Mochalov
AU  - A. V. Mochalova
TI  - The use of long short-term memory and gated recurrent unit for predicting the values of geomagnetic indices
JO  - Vestnik KRAUNC. Fiziko-matematičeskie nauki
PY  - 2020
SP  - 110
EP  - 121
VL  - 33
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/VKAM_2020_33_4_a9/
LA  - ru
ID  - VKAM_2020_33_4_a9
ER  - 
%0 Journal Article
%A V. A. Mochalov
%A A. V. Mochalova
%T The use of long short-term memory and gated recurrent unit for predicting the values of geomagnetic indices
%J Vestnik KRAUNC. Fiziko-matematičeskie nauki
%D 2020
%P 110-121
%V 33
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/VKAM_2020_33_4_a9/
%G ru
%F VKAM_2020_33_4_a9
V. A. Mochalov; A. V. Mochalova. The use of long short-term memory and gated recurrent unit for predicting the values of geomagnetic indices. Vestnik KRAUNC. Fiziko-matematičeskie nauki, Tome 33 (2020) no. 4, pp. 110-121. http://geodesic.mathdoc.fr/item/VKAM_2020_33_4_a9/