Indoor Radon

Indoor radon, a naturally occurring radioactive gas, poses a significant health risk due to its carcinogenic properties, prompting research focused on accurately mapping its concentration levels. Current research employs machine learning techniques, including probabilistic models like quantile regression forests and novel approaches leveraging the Radon transform and optimal transport theory for improved image analysis and classification of radon data. These advancements aim to enhance the spatial resolution and accuracy of indoor radon maps, ultimately improving risk assessment and informing public health interventions to mitigate radon exposure.