The 2023 Mw 6.8 Morocco earthquake induced atmospheric and ionospheric anomalies

Journal of Atmospheric and Solar-Terrestrial Physics, Journal Year: 2024, Volume and Issue: 262, P. 106323 - 106323

Published: Aug. 3, 2024

Language: Английский

---

Prediction of ionospheric TEC during the occurrence of earthquakes in Indonesia using ARMA and CoK models

Frontiers in Astronomy and Space Sciences, Journal Year: 2024, Volume and Issue: 11

Published: Sept. 3, 2024

Predicting ionospheric Total Electron Content (TEC) variations associated with seismic activity is crucial for mitigating potential disruptions in communication networks, particularly during earthquakes. This research investigates applying two modelling techniques, Autoregressive Moving Average (ARMA) and Cokriging (CoK) based models to forecast TEC changes linked events Indonesia. The study focuses on significant earthquakes: the December 2004 Sumatra earthquake August 2012 Sulawesi earthquake. GPS data from a BAKO station near Indonesia solar geomagnetic were utilized assess causes of variations. earthquake, registering magnitude 9.1–9.3, exhibited notable 5 days before event. Analysis revealed that weakly activities. Both ARMA CoK employed predict Earthquakes. model demonstrated maximum prediction 50.92 TECU Root Mean Square Error (RMSE) value 6.15, while predicted 50.68 an RMSE 6.14. having 6.6, anomalies 6 For both earthquakes, showed weak associations activities but stronger correlations earthquake-induced electric field considered stations. 54.43 3.05, 52.90 7.35. Evaluation metrics including RMSE, Absolute Deviation (MAD), Relative Error, Normalized (NRMSE) accuracy reliability models. results indicated captured general trend variations, nuances emerged their responses events. heightened sensitivity disturbances, evident day whereas more consistent performance across pre- post-earthquake periods.

Language: Английский

---

Application of Model-Based Time Series Prediction of Infrared Long-Wave Radiation Data for Exploring the Precursory Patterns Associated with the 2021 Madoi Earthquake

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(19), P. 4748 - 4748

Published: Sept. 28, 2023

Taking the Madoi MS 7.4 earthquake of 21 May 2021 as an example, this paper proposes using time series prediction models to predict outgoing long-wave radiation (OLR) anomalies and study short-term pre-earthquake signals. Five models, including autoregressive integrated moving average (ARIMA) long memory (LSTM), were trained with OLR data aseismic moments in 5° × spatial range around epicenter. The model highest accuracy was selected retrospectively values during period before area. It found, by comparing predicted actual value, that similarity indexes two lower than index period, indicating significantly differed from series. Meanwhile, temporal distribution characteristics 90 days analyzed a 95% confidence interval criterion anomalies, following found: out 25 grids, 18 grids showed anomalies—the different appeared on similar dates, high centrally at earthquake, which supports hypothesis signals may be associated earthquake.

Language: Английский

---

Elite GA-based Feature Selection of LSTM for Earthquake Prediction

Research Square (Research Square), Journal Year: 2023, Volume and Issue: unknown

Published: June 19, 2023

Earthquake magnitude prediction is an extremely difficult task that has been studied by various machine learning researchers. However, the redundant features and time series properties hinder development of models. Elite Genetic Algorithm (EGA) advantages in searching optimal feature subsets, meanwhile, Long Short-Term Memory (LSTM) dedicated to processing complex data. Therefore, we propose EGA-based selection LSTM model (EGA-LSTM) for earthquake prediction. First, acoustic electromagnetics data AETA system developed are fused preprocessed EGA, aiming find strong correlation indicators. Second, introduced execute with selected features. Specifically, RMSE ratio chosen as fitness components EGA. Finally, test proposed EGA-LSTM on Sichuan province, including influence different periods ($timePeriod$) function weights ($\omega_a$ $\omega_F$) results. Linear Regression (LR), Support Vector (SVR), Adaboost, Random Forest (RF), standard GA (SGA), steadyGA, three Differential Evolution Algorithms (DEs) adopted our baselines. Experimental results demonstrate all methods can get best performance when $timePeriod = 0:00-8:00$, $\omega_a=1$, $\omega_F=0.8$. Moreover, approach superior state-of-the-art approaches evaluation indicators MAE, MSE, RMSE, $R_2$. Non-parametric tests reveal significantly from others outperforms LSTM.

Language: Английский

---

GNSS TEC and Swarm Satellites for the detection of Ionospheric Anomalies Possibly associated with 2018 Alaska Earthquake

Research Square (Research Square), Journal Year: 2023, Volume and Issue: unknown

Published: Nov. 21, 2023

Abstract In the hunt for seismic precursors with GNSS to detect earthquake-related anomalies in ionosphere are proved as an effective strategy. One method is use TEC distinguish between and induced by geo magnetic storm. this study, data of four sites near epicenter November 30, 2018, Alaska earthquake (Mw 7.1) examined. We also examined from Swarm satellites during local day nighttime further support EQ-induced perturbations ionosphere. six days before major EQ, stations' displayed considerable disturbance positive crossing upper bound. The stations EQ detected 1 6 prior EQ. swarm confirmed these findings. On other hand, retrieving all preparation phase weak storm (Kp 4, Dst − 50 nT), we discover evidence low-intensity 25–30 shock. Further research shows that UTC 17:30 23:00 storm-induced anomaly (caused = -50 nT Kp 4) predominates 17:00 23:30. phase, primary shock helpful separating geomagnetic anomalies. Additionally, using monitoring, work contributes growing lithosphere-ionosphere connection concept.

Language: Английский

---