Machine Learning-Based Radon Monitoring System

Abstract

Radon (Rn) is a biological threat to cells due to its radioactivity. It is capable of penetrating the human body and damaging cellular DNA, causing mutations and interfering with cellular dynamics. Human exposure to high concentrations of Rn should, therefore, be minimized. The concentration of radon in a room depends on numerous factors, such as room temperature, humidity level, existence of air currents, natural grounds of the buildings, building structure, etc. It is not always possible to change these factors. In this paper we propose a corrective measure for reducing indoor radon concentrations by introducing clean air into the room through forced ventilation. This cannot be maintained continuously because it generates excessive noise (and costs). Therefore, a system for predicting radon concentrations based on Machine Learning has been developed. Its output activates the fan control system when certain thresholds are reached.

Metrology for Indoor Radon Measurements and Requirements for Different Types of Devices

“…In this context, it is crucial to reiterate that the effective radon regulation industry in the US is primarily achieved through the public's participation in large-scale (mass) short-term indoor radon measurements in all states, aimed at identifying hazardous buildings, rather than detailing RPAs [17]. However, instead of refining the indoor radon measurement protocol based on the US approach and developing its metrological support, European radon specialists, including the metrological community, pin high hopes on the possibility of identifying hazardous buildings without conducting indoor radon measurements [21] by predicting annual average indoor radon levels based on building and environmental characteristics using modern machine learning algorithms [21][22][23][24][25]. Indeed, there has been a significant increase in publications on this topic in recent years, although some of them are not related to solving the problem of identifying hazardous buildings [22].…”

“…However, instead of refining the indoor radon measurement protocol based on the US approach and developing its metrological support, European radon specialists, including the metrological community, pin high hopes on the possibility of identifying hazardous buildings without conducting indoor radon measurements [21] by predicting annual average indoor radon levels based on building and environmental characteristics using modern machine learning algorithms [21][22][23][24][25]. Indeed, there has been a significant increase in publications on this topic in recent years, although some of them are not related to solving the problem of identifying hazardous buildings [22]. At the same time, among the recently published relevant studies based on machine learning, it is reported that a satisfactory accuracy in predicting mean indoor radon is only achieved at the municipal level, while "accurate prediction of point estimates such as the conditional mean of indoor radon is not yet possible, which is consistent with many other studies" [21].…”