Determination of radon prone areas by optimized binary classification

Geogenic radon prone areas are regions in which for natural reasons elevated indoor radon concentrations must be expected. Their identification is part of radon mitigation policies in many countries, as radon is acknowledged a major indoor air pollutant, being the second cause of lung cancer after smoking. Defining and estimating radon prone areas is therefore of high practical interest. In this paper a method is presented which uses the geogenic radon potential as predictor and thresholds of indoor radon concentration for defining radon prone areas, from which thresholds for the geogenic radon potential are deduced which decide whether a location is flagged radon prone or not, in the absence of actual indoor observations. The overall results are different maps of radon prone areas, derived from the geogenic radon map, and depending (1) on the criterion which defines what a radon prone area is; and (2) on the choice of score whose maximization defines the optimal classifier. Such map is not the result of a transfer model (geogenic to indoor radon), but of the optimization of a classification rule. The method is computationally simple but has its caveats and statistical traps, some of which are also addressed. (C) 2013 Elsevier Ltd. All rights reserved.