Automated anomalous behaviour detection in soil radon gas prior to earthquakes using computational intelligence techniques. (July 2019)

• Record Type: Journal Article
• Authors: Tareen, Aleem Dad Khan; Asim, Khawaja M.; Kearfott, Kimberlee Jane; Rafique, Muhammad; Nadeem, Malik Sajjad Ahmed; Iqbal, Talat; Rahman, Saeed Ur
• Is Part Of: Journal of environmental radioactivity. Volume 203(2019)
• Page Start: 48
• Page End: 54
• Publication Date: 2019-07
• Subjects: Soil radon -- Time series -- Computational intelligence models -- Seismic events -- Meteorological parameters; Radioactivity -- Periodicals; Radiation, Background -- Periodicals; Radioecology -- Periodicals; Radioactive pollution -- Periodicals; Environmental Pollutants -- Periodicals; Radioactive Pollutants -- Periodicals; Radioactivity -- Periodicals; Radioécologie -- Périodiques; Pollution radioactive -- Périodiques; Fond de rayonnement -- Périodiques; 539.752
• DOI: 10.1016/j.jenvrad.2019.03.003
• Languages: English
• ISSNs: 0265-931X

Abstract

Abstract: In this article, three computational intelligence (CI) models were developed to automatically detect anomalous behaviour in soil radon gas ( 222 Rn) time series data. Data were obtained at a fault line and analysed using three machine learning techniques with the aim at identifying anomalies in temporal radon data prompted by seismic events. Radon concentrations were modelled with corresponding meteorological and statistical parameters. This leads to the estimation of soil radon gas without and with meteorological parameters. The comparison between computed radon concentration and actual radon concentrations was used in finding radon anomaly based upon automated system. The anomaly in radon time series data could be considered due to noise or seismic activity. Findings of study show that under meticulously characterized environments, on exclusion of noise contribution, seismic activity is responsible for anomalous behaviour seen in radon time series data. Graphical abstract: Measured radon concentrations and those predicted from meteorological and statistical parameters using the feed forward neural network (FFNN) technique.Image 1 Highlights: Computational intelligence (CI) models developed to automatically detect anomalous behaviour in soil radon. Accuracy of the models is quantified using the mean absolute error, root mean square error and mean square error. For pre-assumed conditions model accurately predicts radon concentrations and the statistics of their temporal variations. The FFNN) is the most suitable CI technique to detect anomalies in radon time series triggered by seismic activity.