Analysis of 7-years Radon time series at Campi Flegrei area (Naples, Italy) using artificial neural network method

F Ambrosino; C Sabbarese; V Roca; F Giudicepietro; G Chiodini

doi:10.1016/j.apradiso.2020.109239

Analysis of 7-years Radon time series at Campi Flegrei area (Naples, Italy) using artificial neural network method

Appl Radiat Isot. 2020 Sep:163:109239. doi: 10.1016/j.apradiso.2020.109239. Epub 2020 May 24.

Authors

F Ambrosino¹, C Sabbarese², V Roca³, F Giudicepietro⁴, G Chiodini⁵

Affiliations

¹ Centre for Isotopic Research on Cultural and Environmental Heritage (CIRCE), Department of Mathematics and Physics, University of Campania "Luigi Vanvitelli", Viale Lincoln 5, 81100, Caserta, Italy; National Institute of Nuclear Physics, Branch of Naples, Via Cinthia 21, 80126, Naples, Italy. Electronic address: fabrizio.ambrosino@unicampania.it.
² Centre for Isotopic Research on Cultural and Environmental Heritage (CIRCE), Department of Mathematics and Physics, University of Campania "Luigi Vanvitelli", Viale Lincoln 5, 81100, Caserta, Italy; National Institute of Nuclear Physics, Branch of Naples, Via Cinthia 21, 80126, Naples, Italy.
³ National Institute of Nuclear Physics, Branch of Naples, Via Cinthia 21, 80126, Naples, Italy.
⁴ National Institute of Geophysics and Volcanology (INGV), Naples Branch, Vesuvius Observatory, Via Diocleziano 328, 80124, Naples, Italy.
⁵ National Institute of Geophysics and Volcanology (INGV), Bologna Branch, Via D. Creti 12, 40124, Bologna, Italy.

PMID: 32561065
DOI: 10.1016/j.apradiso.2020.109239

Abstract

This paper reports the analysis of soil ²²²Rn data recorded over 7-years in the volcanic caldera of Campi Flegrei (Naples-Italy). The relationship between Radon activity concentration and several geophysical, geochemical and meteorological parameters, influencing the gas emissions, is estimated by the Artificial Neural Network (ANN) method. The analysis goals are: the estimation (replication) of the Radon time series from influencing parameters, the forecasting of an unknown part of it, and the search for anomalies. Results prove: (i) the effectiveness of the ANN method; (ii) Radon follow the periods of agitation of the caldera, demonstrated by the comparison with previous works using different methods.

Keywords: Anomaly detection; Artificial neural network; Influencing parameter; Radon; Signal forecasting; Signal replication.