The most stable isotope of radon is Radon-222, which is a decay product of radium-226 and an indirect decay product of uranium-238, a natural radioactive element. According to the United States Environmental Protection Agency (USEPA), radon is the primary cause of lung cancer among non-smokers. The USEPA classifies Ohio as a zone 1 state because the average radon screening level is more than 4 picocuries per liter. To perform preventive measures, knowing radon concentration levels in all the zip codes of a geographic area is necessary. However, it is impractical to collect the information from all the zip codes due to its inapproachability. Several interpolation techniques have been implemented by researchers to predict the radon concentrations in places where radon data is not available. Hence, to improve the prediction accuracy of radon concentrations, a new technique called Quantile Regression Forests (QRF) is proposed in this thesis.
The conventional techniques like Kriging, Local Polynomial Interpolation (LPI), Global Polynomial Interpolation (GPI), and Radial Basis Function (RBF) estimate output using complex mathematics. Artificial Neural Networks (ANN) have been introduced to overcome this problem. Although ANNs show better prediction accuracy in comparison to more conventional techniques, many issues arise, including local minimization and over fitting. To overcome the inadequacies of existing methods, statistical learning techniques such as Support Vector Regression (SVR) and Random Forest Regression (RFR) were implemented. In this thesis, Quantile Regression Forest (QRF) is introduced and compared with SVR, RFR, and other interpolation techniques using available operational performance measures. The study shows that QRF has least validation error compared with other interpolation techniques.