Bagged neural network model for prediction of the mean indoor radon concentration in the municipalities in Czech Republic

Timková, Jana; Fojtı́ková, Ivana; Pacherova, Petra

doi:10.1016/j.jenvrad.2016.07.008

Cited by 20 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ver sions that are more elab o rate at tempt to de velop quan ti ta tive mod els of the spa tial struc ture us ing geostatistical tools. This in cludes ma chine learn ing [7,8], quantile re gres sion [9] and lo cal regres sion [10]. A hi er ar chi cal re gres sion model where spa tial de pend ence en ters via li thol ogy as a pre dic tor has been pro posed in [11] and fur ther de vel oped as a generalized ad di tive mixed model in Aus tria ( [12], not yet fully pub lished).…”

Section: Es Ti Ma Tion Of Ra Don Pri or Ity Ar Eassupporting

confidence: 64%

Radon priority areas - definition, estimation and uncertainty

Bossew

2018

Nucl Technol Radiat Prot

View full text Add to dashboard Cite

Pos ing a sub stan tial risk to hu man health, in door ra don has in creas ingly been sub ject to reg ula tion. One key con cept is the one of ra don prone or pri or ity ar eas, which are un der stood as re gions where pre ven tion, mit i ga tion or remediation ac tion should be taken with pri or ity. Ra don pri or ity ar eas must be de fined, and once de fined, es ti mated from data. Ra don pri or ity area es ti ma tion or de lin ea tion amounts to a clas si fi ca tion prob lem, as a do main (a coun try) has to be di vided into mu tu ally ex clu sive zones of dif fer ent "priorityness". Clas si fy ing ar eas into pri or ity zones en tails de ci sions about ac tion to be im ple mented. Touch ing stake holder in ter ests, may prove eco nom i cally and po lit i cally costly. There fore, de ci sions should be jus ti fiable, which im plies, among other, re li abil ity of the ra don pri or ity area es ti mate, mean ing statis ti cally, con trol ling for es ti ma tion un cer tainty. Some as pects of ra don pri or ity area def i nition, es ti ma tion, and un cer tainty will be dis cussed in this pa per.

show abstract

Section: Es Ti Ma Tion Of Ra Don Pri or Ity Ar Eassupporting

confidence: 64%

Radon priority areas - definition, estimation and uncertainty

Bossew

2018

Nucl Technol Radiat Prot

View full text Add to dashboard Cite

show abstract

“…The application of an explorative statistical technique as performed via a principal component analysis (PCA) on several covariates was developed by [31], thus using the first PC as GRHI. Recent attempts ( [32,33,52,53]) utilized machine learning (ML) methods, which are considered particularly powerful for "high dimensional" multivariate settings and in particular, also for confirmative statistical techniques such as spatial regression (i.e., statistical approaches with many predictors).…”

Section: History Of the Geogenic Radon Hazard Indexmentioning

confidence: 99%

“…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

“…The relationship between the mean observed indoor radon concentrations and the independent predictors (geological, radiometric etc) was modeled using a bagged neural network and Czech national data base of 150 000 indoor radon measurements. The average percentage of explained variability from crossvalidation was 61.5% in training sets and 23.6% in validation sets (Timkova et al, 2017). Thus, the studies of geogenic radiation and radon potential provide an example of a successful interdisciplinary multigroup research.…”

mentioning

confidence: 93%