Advances in Seismo-LAI anomalies detection within Google Earth Engine (GEE) cloud platform. Issue 12 (15th June 2022)

• Record Type: Journal Article
• Authors: Akhoondzadeh, Mehdi
• Is Part Of: Advances in space research. Volume 69:Issue 12(2022)
• Page Start: 4351
• Page End: 4357
• Publication Date: 2022-06-15
• Subjects: Earthquake precursor -- Satellites data -- Google Earth Engine (GEE) -- Lithospheric Atmospheric Ionospheric anomalies; Space sciences -- Periodicals; Astronautics -- Periodicals; Geophysics -- Periodicals; 500.505
• DOI: 10.1016/j.asr.2022.03.033
• Languages: English
• ISSNs: 0273-1177

Abstract

Highlights: This paper aims to explain the role of GEE in seismic anomalies detection. Two recent powerful earthquakes in Japan (13 February and 20 March 2021) were discussed. Time series of AOT, Chlorophyll and Ozone precursors deduced from GEE platform. They were investigated using Median and LSTM methods. Our satisfactory results show that we will see a significant leap forward in studies of earthquake precursors. Abstract: Nowadays, satellite data is an appropriate and undeniable source for studying earthquake precursors due to their diversity, wide coverage, being up to date and low cost. Time series analysis of satellite data plays an important role in the process of detecting seismic anomalies in earthquake warning systems. But in order to reduce uncertainty during the seismic anomalies detection, it is necessary the use a variety of satellite data, although it leads to increase of data size and processing time. This paper aims to explain the role of Google Earth Engine (GEE) cloud platform in considerable progress of seismo-Lithospheric Atmospheric Ionospheric (LAI) anomalies detection in earthquake early warning systems. Among the different studied earthquakes, for example two recent powerful earthquakes in Japan (13 February and 20 March 2021) have been discussed. Deduced time series of three precursors (i.e. Aerosol Optical Thickness (AOT), Chlorophyll and Ozone) from GEE platform were investigated using Median method and a Long Short-Term Memory (LSTM) neural network to detect potentially seismo-LAI anomalies. Our satisfactory results show that with the addition of other various satellite data and also known predictors intelligent algorithms such as deep learning to GEE platform, we will see a significant leap forward in studies of earthquake precursors.