Atmospheric Anomalies Associated with the 2021 Mw 7.2 Haiti Earthquake Using Machine Learning from Multiple Satellites

Abstract

The remote sensing-based Earth satellites has become a beneficial instrument for the monitoring of natural hazards. This study includes a multi-sensors analysis to estimate the spatial-temporal variations of atmospheric parameters as precursory signals to the Mw 7.2 Haiti Earthquake (EQ). We studied EQ anomalies in Land Surface Temperature (LST), Air Temperature (AT), Relative Humidity (RH), Air Pressure (AP), and Outgoing Longwave Radiation (OLR). Moreover, we found EQ-associated atmospheric abnormalities in a time window of 3–10 days before the main shock by different methods (e.g., statistical, wavelet transformation, deep learning, and Machine Learning (ML)-based neural networks). We observed a sharp decrease in the RH and AP before the main shock, followed by an immense enhancement in AT. Similarly, we also observed enhancement in LST and OLR around the seismic preparation region within 3–10 days before the EQ, which validates the precursory behavior of all the atmospheric parameters. These multiple-parameter irregularities can contribute with the physical understanding of Lithosphere-Atmosphere-Ionosphere Coupling (LAIC) in the future in order to forecast EQs.

Ionospheric–Thermospheric Responses to Geomagnetic Storms from Multi-Instrument Space Weather Data

“…All the satellite and ground data showed significant storm-time variations in different phases [75][76][77][78][79]. These satellite data also showed variations in the lower ionosphere [80][81][82][83][84][85]. In this study, clear EEJ enhancement has been observed at the beginning of both the 2015 and 2018 storms.…”

Observation of the Preparation Phase Associated with Mw = 7.2 Haiti Earthquake on 14 August 2021 from a Geophysical Data Point of View

“…The value is the absolute one and not the exceedance of the threshold. Comparing the results of this work with previous ones [57,59,60], it is possible to confirm the presence of sparse anomalies in the last weeks and days before the earthquake, but it is possible to depict more interesting periods with higher anticipation time not investigated in previous work. This is not surprising, considering that a single fault's seismic recharge time could be hundreds or thousands of years [106].…”

“…He identified an increase in anomalies in the last 20 days before the earthquake, similar to the result of the recent catastrophic earthquake in Turkey [58]. Another work by Khan et al [59] used a machine learning technique to analyse satellite atmospheric data 30 days before and up to 15 days after the mainshock. They identified an anomaly increase ten days before the mainshock.…”

Spatial and Temporal Analysis of Climatic Precursors before Major Earthquakes in Iran (2011–2021)

“…Many of these studies focused on satellite data, because remote sensing offers distinct advantages over traditional approaches based on ground stations including global coverage and high spatial-temporal resolution [37]. Earthquake precursors derived from space-based observations, therefore, provided excellent insights into preseismic anomalies over epicentral regions [38]. Many scholars reported persistent and simultaneous anomalies in different observable parameters prior to major earthquakes [39].…”