Adaptive Dendritic Cell-Negative Selection Method for Earthquake Prediction

Earthquake prediction (EQP) is an extremely difficult task, which has been overcome by adopting various technologies, with no further transformation so far. The negative selection algorithm (NSA) artificial intelligence method based on the biological immune system. It widely used in anomaly detection due to its advantages of requiring little normal data detect anomalies, including historical seismic-events-based EQP. However, NSA can suffer from undesirable effect drift, resulting outdated patterns learned data. To tackle this problem, changes must be detected and processed, stimulating fast algorithmic adaptation strategies. This study proposes a dendritic cell (DCA)-based adaptive learning for drift (DC-NSA) that dynamically adapts new input First, adopts Gutenberg–Richter (GR) law other earthquake distribution laws preprocess Then, employed EQP, then, (DCA) trigger gradient descent strategies update self-set NSA. Finally, proposed approach implemented predict earthquakes MW > 5 Sichuan surroundings during next month. experimental results demonstrate our DC-NSA superior existing state-of-the-art EQP approaches.