Study on Longwave Radiation Anomalies in the Dual Earthquakes in Turkey Based on LSTM

This study employs the Long Short-Term Memory (LSTM) deep learning model to analyze the dual earthquake events that occurred in Turkey on February 6, 2023. The model is trained using Outgoing Longwave Radiation (OLR) data from the 11 years preceding the earthquakes. The research area is centered around the seismic grid, covering a spatial range of 5°×5°. Predictions are made using a 5-day sliding time window, and anomalies are identified within a 95% confidence interval. The results highlight multiple concentrated anomalies in the three months leading up to the earthquakes. These findings contribute to a deeper understanding of seismic precursors and underscore the potential of utilizing OLR data in earthquake prediction models. The research emphasizes the importance of fully considering temporal and spatial factors in earthquake event prediction, providing valuable insights for earthquake monitoring and early warning systems.