Indoor radon interval prediction in the Swedish building stock using machine learning
(2023) In Building and Environment 245.- 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... (More)
- 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. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/0435d56a-576f-4f98-8a4e-264ffe58e57e
- author
- Wu, Pei-Yu LU ; Johansson, Tim ; Sandels, Claes ; Mangold, Mikael and Mjörnell, Kristina LU
- organization
- publishing date
- 2023-09
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Building and Environment
- volume
- 245
- pages
- 13 pages
- publisher
- Elsevier
- external identifiers
-
- scopus:85172459457
- ISSN
- 0360-1323
- DOI
- 10.1016/j.buildenv.2023.110879
- language
- English
- LU publication?
- yes
- id
- 0435d56a-576f-4f98-8a4e-264ffe58e57e
- date added to LUP
- 2023-10-10 16:12:14
- date last changed
- 2023-10-16 10:24:13
@article{0435d56a-576f-4f98-8a4e-264ffe58e57e,
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.}},
author = {{Wu, Pei-Yu and Johansson, Tim and Sandels, Claes and Mangold, Mikael and Mjörnell, Kristina}},
issn = {{0360-1323}},
language = {{eng}},
publisher = {{Elsevier}},
series = {{Building and Environment}},
title = {{Indoor radon interval prediction in the Swedish building stock using machine learning}},
url = {{http://dx.doi.org/10.1016/j.buildenv.2023.110879}},
doi = {{10.1016/j.buildenv.2023.110879}},
volume = {{245}},
year = {{2023}},
}