Machine learning methods as a tool to analyse incomplete or irregularly sampled radon time series data

Janik, Mirosław; Bossew, Peter; Kurihara, Osamu

doi:10.1016/j.scitotenv.2018.02.233

Cited by 34 publications

(14 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In radon science, ML has first been used, to our knowledge, by [53,67] and [52] for spatial settings and by [111] in time series analysis. Current work at the BfS aims to improve regional GRP and IRC prediction by including high numbers (up to 100) of potential predictors [32].…”

Section: Machine Learning (Ml)mentioning

confidence: 99%

Development of a Geogenic Radon Hazard Index—Concept, History, Experiences

Bossew

Cinelli

Ciotoli

et al. 2020

IJERPH

View full text Add to dashboard Cite

Exposure to indoor radon at home and in workplaces constitutes a serious public health risk and is the second most prevalent cause of lung cancer after tobacco smoking. Indoor radon concentration is to a large extent controlled by so-called geogenic radon, which is radon generated in the ground. While indoor radon has been mapped in many parts of Europe, this is not the case for its geogenic control, which has been surveyed exhaustively in only a few countries or regions. Since geogenic radon is an important predictor of indoor radon, knowing the local potential of geogenic radon can assist radon mitigation policy in allocating resources and tuning regulations to focus on where it needs to be prioritized. The contribution of geogenic to indoor radon can be quantified in different ways: the geogenic radon potential (GRP) and the geogenic radon hazard index (GRHI). Both are constructed from geogenic quantities, with their differences tending to be, but not always, their type of geographical support and optimality as indoor radon predictors. An important feature of the GRHI is consistency across borders between regions with different data availability and Rn survey policies, which has so far impeded the creation of a European map of geogenic radon. The GRHI can be understood as a generalization or extension of the GRP. In this paper, the concepts of GRP and GRHI are discussed and a review of previous GRHI approaches is presented, including methods of GRHI estimation and some preliminary results. A methodology to create GRHI maps that cover most of Europe appears at hand and appropriate; however, further fine tuning and validation remains on the agenda.

show abstract

Section: Machine Learning (Ml)mentioning

confidence: 99%

Development of a Geogenic Radon Hazard Index—Concept, History, Experiences

Bossew

Cinelli

Ciotoli

et al. 2020

IJERPH

View full text Add to dashboard Cite

show abstract

“…The performances of the different methods were assessed by 5 × 10-fold cross-validation and by moving-window crossvalidation (Kasemsumran et al, 2006). For the 5 × 10fold cross-validation method, data were randomly split into 10 subgroups and predictions were carried out 10 times; each time one group is used for validation and nine are used for modelling the variable of interest (i.e.…”

Section: Cross-validationmentioning

confidence: 99%

The first version of the Pan-European Indoor Radon Map

Elío

Cinelli

Bossew

et al. 2019

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. A hypothetical Pan-European Indoor Radon Map has been developed using summary statistics estimated from 1.2 million indoor radon samples. In this study we have used the arithmetic mean (AM) over grid cells of 10 km × 10 km to predict a mean indoor radon concentration at ground-floor level of buildings in the grid cells where no or few data (N<30) are available. Four interpolation techniques have been tested: inverse distance weighting (IDW), ordinary kriging (OK), collocated cokriging with uranium concentration as a secondary variable (CCK), and regression kriging with topsoil geochemistry and bedrock geology as secondary variables (RK). Cross-validation exercises have been carried out to assess the uncertainties associated with each method. Of the four methods tested, RK has proven to be the best one for predicting mean indoor radon concentrations; and by combining the RK predictions with the AM of the grids with 30 or more measurements, a Pan-European Indoor Radon Map has been produced. This map represents a first step towards a European radon exposure map and, in the future, a radon dose map.

show abstract

“…The loss function has to be defined by the user, and a common choice is the Root-Mean-Square Error (RSME) (Janik et al, 2018). In our case the optimal idp was found to be 1.5 ( Figure 3), and interpolations of the AM were carried out using the observations within a distance of 1,000 km, and a minimum and maximum number of nearest observations was set to 5 and 75 respectively.…”

Section: Inverse Distance Weighted Interpolation (Idw)mentioning

confidence: 99%

“…MAE and RMSE are commonly used for assessing model performance; however, they may be influenced by outliers (Chen et al, 2017). RMSLE, on the contrary, is less sensitive to outliers and preferable when there is a large range in the values (Janik et al, 2018). These parameters are positive values and the closer they are to 0, the better is the model fit.…”

Section: Cross-validationmentioning

confidence: 99%

See 1 more Smart Citation

First steps towards an All-European Indoor Radon Map

Elío¹,

Cinelli²,

Bossew³

et al. 2019

Preprint

View full text Add to dashboard Cite

Abstract. A hypothetical All-European Indoor Radon Map has been developed using summary statistics estimated from 1.2 million indoor radon samples. In this study we have used the arithmetic mean (AM) over grid cells of 10 km × 10 km to predict a mean indoor radon concentration at ground floor level in the grid cells where no or few data are available (N < 30). Four interpolation techniques have been tested: inverse distance weighted (IDW); ordinary kriging (OK); collocated cokriging with uranium concentration as secondary variable (CoCK); and regression kriging with topsoil geochemistry and bedrock geology as secondary variables (RK). Cross-validation exercises have been carried out to assess the uncertainties associated with each method. Of the four methods tested, RK has proved to be the best one for predicting mean indoor radon concentrations, and by combining the RK predictions with the AM of the grids with 30 or more measurements, an All-European Indoor Radon Map has been produced. This map represents the first step towards a European radon exposure, and further on a radon dose map.

show abstract

Machine learning methods as a tool to analyse incomplete or irregularly sampled radon time series data

Cited by 34 publications

References 34 publications

Development of a Geogenic Radon Hazard Index—Concept, History, Experiences

Development of a Geogenic Radon Hazard Index—Concept, History, Experiences

The first version of the Pan-European Indoor Radon Map

First steps towards an All-European Indoor Radon Map

Contact Info

Product

Resources

About