Predicting radon flux density from soil surface using machine learning and GIS data

Sakhaiaan Gavriliev; Tatiana Petrova; Petr Miklyaev; Ekaterina Karfidova

doi:10.1016/j.scitotenv.2023.166348

Predicting radon flux density from soil surface using machine learning and GIS data

Sci Total Environ. 2023 Dec 10:903:166348. doi: 10.1016/j.scitotenv.2023.166348. Epub 2023 Aug 16.

Authors

Sakhaiaan Gavriliev¹, Tatiana Petrova², Petr Miklyaev³, Ekaterina Karfidova⁴

Affiliations

¹ Radiochemistry Department, Faculty of Chemistry, Lomonosov Moscow State University, Russian Federation; Sergeev Institute of Environmental Geoscience, RAS, Moscow, Russian Federation. Electronic address: sparklesweetieponycider@gmail.com.
² Radiochemistry Department, Faculty of Chemistry, Lomonosov Moscow State University, Russian Federation.
³ Sergeev Institute of Environmental Geoscience, RAS, Moscow, Russian Federation; STC for Radiation and Chemical Safety and Hygiene, FMBA, Moscow, Russian Federation.
⁴ Sergeev Institute of Environmental Geoscience, RAS, Moscow, Russian Federation.

PMID: 37591399
DOI: 10.1016/j.scitotenv.2023.166348

Abstract

Several machine learning algorithms including artificial neural networks (ANN), random forest (RF) and multivariate adaptive regression splines (MARS) were used to construct a radon flux density (RFD) map of Moscow for the purpose of finding which one of them would be the best for radon delineation. Predictors used included geological soil classes for quaternary and some pre-quaternary sediment types, elevations of quaternary and pre-quaternary layers, ²²⁶Ra content in soil, ambient dose equivalent rate (ADER), distances to geodynamically active zones and lineaments. Training of the models was performed using previously collected radon flux density data from approximately ten thousand of measurements over 756 sites. ANN and RF algorithms produced the best maps with high correlation coefficients and low mean squared error, while MARS failed to get a high correlation coefficient and low mean squared error. Predictions made using RF were found to be more conservative due to higher prediction values of RFD, while those made using ANN were likely more realistic in their prediction value distribution, leading to the conclusion that RF is better for the purposes of delineation, while ANN is better for predicting average RFD values. Based on the constructed maps, the main factors affecting the flow of radon in the city were determined.

Keywords: Machine learning; Mapping; Radium; Radon; Radon delineation; Radon flux density.