Long Short Term Memory networks (LSTM)-Monte-Carlo simulation of soil ionization using radon. (15th September 2021)

• Record Type: Journal Article
• Authors: Muhammad, Ahmad; Külahcı, Fatih; Salh, Hemn; Hama Rashid, Pishtiwan Akram
• Is Part Of: Journal of atmospheric and solar-terrestrial physics. Volume 221(2021)
• Publication Date: 2021-09-15
• Subjects: Radon -- Near surface ionization -- Monte Carlo simulation -- Earthquake forecasting -- Deep learning -- Seismo-ionospheric coupling -- LSTM; Geophysics -- Periodicals; Atmospheric physics -- Periodicals; Géophysique -- Périodiques; Météorologie physique -- Périodiques; Electronic journals; 551.51
• DOI: 10.1016/j.jastp.2021.105688
• Languages: English
• ISSNs: 1364-6826

Abstract

Abstract: Earthquake events are usually associated with atmospheric processes variations. Some of the important events in seismic periods include the atmospheric electricity/conductivity modification, which mostly depends on the ion population in the vicinity of earthquake preparation area. Radon, together with cosmic radiation are the major ionization sources in the lower troposphere. The radon induced soil ion-pair production rate was estimated for Erzincan, a city along the North Anatolian Fault Zone, Turkey. The Long Short-Term Memory networks (LSTM's) and Monte Carlo method are proposed to account for uncertainty in estimating the ion production rate. The advantage of the LSTM model is taken to study radon anomalies during the M = 5 Girlevik earthquake, Erzincan. Radon concentration is found to increase prior to the 5.0 Girlevik earthquake. According to estimations, 23 × 10 9 ion-pairs m −3 s −1 were generated at 1 m depth from the Earth's surface during this earthquake. The soil-ion production estimation rate due to radon and its progeny in Erzincan is at the order of 10 9 ion-pairs m −3 s −1 . When these generated ions and charged aerosols reach the surface and were added to other ionization sources, parameters such as the near surface conductivity and electric field would be modified. In addition, under pronounced conditions could favor ionospheric perturbations. Highlights: The effects of soil Rn gas on soil ionization are examined. The ion production rate is forecasted by using Rn gas. The effects of earthquakes on soil ionization are calculated theoretically.