Groundwater radon concentrations can reflect the changes of crustal stress and strain. Scholars and scientific institutions have also recorded groundwater radon precursor anomalies before earthquakes. Therefore, groundwater radon monitoring is an effective means of predicting seismic activities. However, the variation of radon concentrations within groundwater is not only affected by structural factors, but also by environmental factors, such as air pressure, temperature, and rainfall. This causes difficulty in identifying the possible precursor anomalies. Therefore, the EMD-LSTM model is proposed to identify the radon anomalies. This study investigated the time series data of groundwater radon from well #32 located in Sichuan province. Three models (including the LSTM (Long Short-Term Memory) model with auxiliary data, the EMD-LSTM (Empirical Mode Decomposition Long Short-Term Memory) model with auxiliary data, and the EMD-LSTM model without auxiliary data) were developed in order to predict groundwater radon variations. The results indicated that the prediction accuracy of the EMD-LSTM model was much higher than that of the LSTM model, and the EMD-LSTM model without auxiliary data also can obtain an ideal prediction result. Furthermore, the different durations of seismic activities T (T = ±10, ±30, ±50, and ±100) were also investigated by comparing the identification results. The identification rate of the precursor anomalies was the highest when T = ±30. The EMD-LSTM model identified five possible radon anomalies among the seven selected earthquakes. Taking well #32 as an example, we provided a promising method, that was the EMD-LSTM model, to detect the groundwater radon anomalies. It also suggested that the EMD-LSTM model can be used to identify the possible precursor anomalies within future studies.

A M_S6.8 earthquake struck Luding Country in Ganzi Prefecture, Sichuan Province on 5 September 2022. The earthquake occurred on the Moxi segment of Xianshuihe fault zone (XFZ), one of the most seismically active faults in the Chinese mainland. In this study, multiple periods of the Global Positioning System (GPS) velocity field and continuous observational data are collected to analysis the tectonic deformation and evolution characteristics before the Luding earthquake, from the perspectives of the kinematic behavior of seismogenic fault, the multi-scale strain features around the study region, and the variation of GPS baselines across the epicenter area. Then the following conclusions are obtained: 1) The accelerated compression of baselines SCGZ-SCXJ (Ganzi to Xiaojin in Sichuan province) and SCLH-SCXJ (Luhuo to Xiaojin in Sichuan province) in Bayan Har block indicate that under the influence of the coseismic rupture of Maduo M_S7.4 earthquake, the boundary faults decoupled and accelerated the push southward and eastward, leading to the acceleration of strain accumulation and the increase of seismic risk in the divergence area bounded by the southeastern XFZ and the southwestern Longmenshan fault zone (LFZ). 2) Luding earthquake located in the weakened region around the edge of the large strike-slip fault zone with high shear strain rate, and the tensile zone of the strain perpendicular to the fault direction, denoting that the reduction of the normal strain in the locked background is strongly related to fault rupture and earthquake nucleation.

A MS6.8 earthquake struck Luding Country in Ganzi Prefecture, Sichuan Province on September 5, 2022. The earthquake occurred on the Moxi segment of Xianshuihe fault zone (XFZ), one of the most seismically active faults in the China mainland. In this study, multiple periods of the Global Positioning System (GPS) velocity fields and continuous observational data are collected to analysis the tectonic deformation and evolution characteristics before the Luding earthquake, from the perspectives of the kinematic behaviors of seismogenic faults, the multi-scale strain features around the study region, and the variation of GPS baseline across the epicenter area. Then the following conclusions are obtained: (1) The accelerated compression of baselines SCGZ-SCXJ and SCLH-SCXJ in Bayan Har block indicate that boundary faults are decoupling and accelerated southward and eastward pushing under the influence of the coseismic rupture of Maduo MS7.4 earthquake, which leads to the acceleration of the strain accumulation and the increase of seismic risk in the divergence area bounded by the southern section of XFZ and the southwestern section of Longmenshan fault zone (LFZ). (2) Luding earthquake located in the weakened region around the edge of the large strike-slip fault zone with high shear strain rate, and the tensile zone of the strain perpendicular to the fault direction, denoting that the reduction of the normal strain in the locked background is strongly related to fault rupture and earthquake nucleation.