TITLE:
Investigation of Relation between Solar Activity and Earthquakes with Deep Learning Method
AUTHORS:
Leilei Li, Hong Gu, Ryosuke Kikuyama, Ryuei Nishii, Pan Qin
KEYWORDS:
Deep Learning, Earthquakes, Prediction, Solar Activities, Temporal Convolution Network
JOURNAL NAME:
International Journal of Geosciences,
Vol.12 No.8,
August
25,
2021
ABSTRACT: Solar activity (SA) has been hypothesized to be a trigger of earthquakes,
although it is not as intuitively associated as other potential triggers such
as tidal stress, rainfall, and the building
of artificial water reservoirs. Here, we investigate the relation between SA and global earthquake numbers (GEN) by
using a deep learning method to test the hypothesis. We use the daily
data of GEN and SA (1996/01/01-2019/12/31) to construct a temporal convolution network (TCN). From the computational
results, we confirm that the TCN captures the relation between SA and earthquakes with magnitudes from 4.0 to 4.9. We
also find that the TCN achieves
better fitting and prediction performance compared with previous work.