A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Indoor radon interval prediction in the Swedish building stock using machine learning
https://orcid.org/0000-0002-2178-5391
https://orcid.org/0000-0002-5044-6989
Abstract Indoor radon represents a health hazard for occupants. However, the indoor radon measurement rate is low in Sweden because of no mandatory requirements. Measuring indoor radon on an urban scale is complicated, machine learning exploiting existing data for pattern identification provides a cost-efficient approach to estimate indoor radon exposure in the building stock. Extreme gradient boosting (XGBoost) models and deep neural network (DNN) models were developed based on indoor radon measurement records, property registers, and geogenic information. The XGBoost models showed promising results in predicting indoor radon intervals for different types of buildings with macro-F1 between 0.93 and 0.96, whereas the DNN models attained macro-F1 between 0.64 and 0.74. After that, the XGBoost models trained on the national indoor radon dataset were transferred to fit building registers in metropolitan regions to estimate the indoor radon intervals in non-measured and measured buildings by regions and building classes. By comparing the prediction results and the statistical summary of indoor radon intervals in measured buildings, the model uncertainty and validity were determined. The study ascertains the prediction performance of machine learning models in classifying indoor radon intervals and discusses the benefits and limitations of the data-driven approach. The research outcomes can assist preliminary large-scale indoor radon distribution estimation for relevant authorities and guide onsite measurements for prioritized building stock prone to indoor radon exposure.
Highlights Status-quo of indoor radon in Sweden is investigated by building types and regions. Machine learning is promising for indoor radon interval prediction in building stock. Large post-war buildings with basements and natural ventilation are prone to radon. XGBoost models outperform DNN models with high performances in all building types. Indoor radon distribution in non-measured buildings is estimated and verified.
Indoor radon interval prediction in the Swedish building stock using machine learning
https://orcid.org/0000-0002-2178-5391
https://orcid.org/0000-0002-5044-6989
Abstract Indoor radon represents a health hazard for occupants. However, the indoor radon measurement rate is low in Sweden because of no mandatory requirements. Measuring indoor radon on an urban scale is complicated, machine learning exploiting existing data for pattern identification provides a cost-efficient approach to estimate indoor radon exposure in the building stock. Extreme gradient boosting (XGBoost) models and deep neural network (DNN) models were developed based on indoor radon measurement records, property registers, and geogenic information. The XGBoost models showed promising results in predicting indoor radon intervals for different types of buildings with macro-F1 between 0.93 and 0.96, whereas the DNN models attained macro-F1 between 0.64 and 0.74. After that, the XGBoost models trained on the national indoor radon dataset were transferred to fit building registers in metropolitan regions to estimate the indoor radon intervals in non-measured and measured buildings by regions and building classes. By comparing the prediction results and the statistical summary of indoor radon intervals in measured buildings, the model uncertainty and validity were determined. The study ascertains the prediction performance of machine learning models in classifying indoor radon intervals and discusses the benefits and limitations of the data-driven approach. The research outcomes can assist preliminary large-scale indoor radon distribution estimation for relevant authorities and guide onsite measurements for prioritized building stock prone to indoor radon exposure.
Highlights Status-quo of indoor radon in Sweden is investigated by building types and regions. Machine learning is promising for indoor radon interval prediction in building stock. Large post-war buildings with basements and natural ventilation are prone to radon. XGBoost models outperform DNN models with high performances in all building types. Indoor radon distribution in non-measured buildings is estimated and verified.
Indoor radon interval prediction in the Swedish building stock using machine learning
https://orcid.org/0000-0002-2178-5391
https://orcid.org/0000-0002-5044-6989
Abstract Indoor radon represents a health hazard for occupants. However, the indoor radon measurement rate is low in Sweden because of no mandatory requirements. Measuring indoor radon on an urban scale is complicated, machine learning exploiting existing data for pattern identification provides a cost-efficient approach to estimate indoor radon exposure in the building stock. Extreme gradient boosting (XGBoost) models and deep neural network (DNN) models were developed based on indoor radon measurement records, property registers, and geogenic information. The XGBoost models showed promising results in predicting indoor radon intervals for different types of buildings with macro-F1 between 0.93 and 0.96, whereas the DNN models attained macro-F1 between 0.64 and 0.74. After that, the XGBoost models trained on the national indoor radon dataset were transferred to fit building registers in metropolitan regions to estimate the indoor radon intervals in non-measured and measured buildings by regions and building classes. By comparing the prediction results and the statistical summary of indoor radon intervals in measured buildings, the model uncertainty and validity were determined. The study ascertains the prediction performance of machine learning models in classifying indoor radon intervals and discusses the benefits and limitations of the data-driven approach. The research outcomes can assist preliminary large-scale indoor radon distribution estimation for relevant authorities and guide onsite measurements for prioritized building stock prone to indoor radon exposure.
Highlights Status-quo of indoor radon in Sweden is investigated by building types and regions. Machine learning is promising for indoor radon interval prediction in building stock. Large post-war buildings with basements and natural ventilation are prone to radon. XGBoost models outperform DNN models with high performances in all building types. Indoor radon distribution in non-measured buildings is estimated and verified.
Indoor radon interval prediction in the Swedish building stock using machine learning
Wu, Pei-Yu (author) / Johansson, Tim (author) / Sandels, Claes (author) / Mangold, Mikael (author) / Mjörnell, Kristina (author)
Building and Environment ; 245
2023-09-24
Article (Journal)
Electronic Resource
English
Indoor climate in the Swedish housing stock
| NTIS | 1993
Indoor air quality in the Swedish housing stock and its dependence on building characteristics
| British Library Online Contents | 2013
Indoor air quality in the Swedish housing stock and its dependence on building characteristics
| Online Contents | 2013
Prediction of Indoor Radon Based on Soil Radon and Soil Permeability
| Online Contents | 1999
Indoor radon from building material - remedial action using adsorptive wallpapers
| British Library Conference Proceedings | 1995