Systematic review of statistical methods for the identification of buildings and areas with high radon levels

Radon is a natural and radioactive noble gas, which may accumulate indoors and cause lung cancers after long term-exposure. Being a decay product of Uranium 238, it originates from the ground and is spatially variable. Many environmental (i.e., geology, tectonic, soils) and architectural factors (i.e., building age, floor) influence its presence indoors, which make it difficult to predict. However, different methods have been developed and applied to identify radon prone areas and buildings. This paper presents the results of a systematic literature review of suitable statistical methods willing to identify buildings and areas where high indoor radon concentrations might be found. The application of these methods is particularly useful to improve the knowledge of the factors most likely to be connected to high radon concentrations. These types of methods are not so commonly used, since generally statistical methods that study factors predictive of radon concentration are focused on the average concentration and aim to identify factors that influence the average radon level. In this paper, an attempt has been made to classify the methods found, to make their description clearer. Four main classes of methods have been identified: descriptive methods, regression methods, geostatistical methods, and machine learning methods. For each presented method, advantages and disadvantages are presented while some applications examples are given. The ultimate purpose of this overview is to provide researchers with a synthesis paper to optimize the selection of the method to identify radon prone areas and buildings.