Modeling the Relationship Between Radon Anomalies and Seismic Activity Using Artificial Neural Networks and Statistical Methods

The paper presents an approach for detecting anomalies in radon concentration in seismically active areas. It involves training multiple artificial neural networks (ANNs) to predict radon concentration during periods without seismic events. The trained ANNs model the typical radon variations under non-seismic conditions, and the predicted values for normal radon behavior are compared with actual radon concentrations around the time of recorded earthquakes. Significant deviations from the predicted values are interpreted as radon anomalies potentially associated with upcoming seismic events. The methodology includes wavelet transformation for noise removal, a multilayer ANN trained using the Levenberg–Marquardt algorithm, and a segmentation approach based on radial zones (annuli) for localized predictions. Large datasets from three radon measurement stations in Bulgaria—Yambol, Dimitrovgrad, and Krupnik—were used. Data from seismic periods were excluded during the training of the neural networks to ensure that the models learn only the natural radon variations under non-seismic conditions. Key results indicate that, in Yambol and Dimitrovgrad, the actual radon concentration exceeds the predicted normal levels during earthquakes, whereas in Krupnik, radon concentration is lower than expected during seismic events. Analysis of the pre-seismic period shows elevated radon levels 48 h before earthquakes at some stations, while expected anomalies were not observed at others. Through this study, we demonstrate the effectiveness of ANN models in modeling radon behavior under non-seismic conditions and identifying deviations that may be linked to seismic activity. We believe that the obtained results contribute to the ongoing discussion on radon concentration anomalies as potential earthquake precursors and suggest that local geological and environmental factors may further influence radon emissions in different ways.