Development of a High-Resolution Indoor Radon Map Using a New Machine Learning-Based Probabilistic Model and German Radon Survey Data.

BACKGROUND: Radon is a carcinogenic, radioactive gas that can accumulate indoors and is undetected by human senses. Therefore, accurate knowledge of indoor radon concentration is crucial for assessing radon-related health effects or identifying radon-prone areas. OBJECTIVES: Indoor radon concentration at the national scale is usually estimated on the basis of extensive measurement campaigns. However, characteristics of the sampled households often differ from the characteristics of the target population owing to the large number of relevant factors that control the indoor radon concentration, such as the availability of geogenic radon or floor level. Furthermore, the sample size usually does not allow estimation with high spatial resolution. We propose a model-based approach that allows a more realistic estimation of indoor radon distribution with a higher spatial resolution than a purely data-based approach. METHODS: A multistage modeling approach was used by applying a quantile regression forest that uses environmental and building data as predictors to estimate the probability distribution function of indoor radon for each floor level of each residential building in Germany. Based on the estimated probability distribution function, a probabilistic Monte Carlo sampling technique was applied, enabling the combination and population weighting of floor-level predictions. In this way, the uncertainty of the individual predictions is effectively propagated into the estimate of variability at the aggregated level. RESULTS: The results show an approximate lognormal distribution of indoor radon in dwellings in Germany with an arithmetic mean of 63 Bq/m3, a geometric mean of 41 Bq/m3, and a 95th percentile of 180 Bq/m3. The exceedance probabilities for 100 and 300 Bq/m3 are 12.5% (10.5 million people affected) and 2.2% (1.9 million people affected), respectively. In large cities, individual indoor radon concentration is generally estimated to be lower than in rural areas, which is due to the different distribution of the population on floor levels. DISCUSSION: The advantages of our approach are that is yields a) an accurate estimation of indoor radon concentration even if the survey is not fully representative with respect to floor level and radon concentration in soil, and b) an estimate of the indoor radon distribution with a much higher spatial resolution than basic descriptive statistics. https://doi.org/10.1289/EHP14171.

A new perspective in radon risk assessment: Mapping the geological hazard as a first step to define the collective radon risk exposure.

Radon is a radioactive gas and a major source of ionizing radiation exposure for humans. Consequently, it can pose serious health threats when it accumulates in confined environments. In Europe, recent legislation has been adopted to address radon exposure in dwellings; this law establishes national reference levels and guidelines for defining Radon Priority Areas (RPAs). This study focuses on mapping the Geogenic Radon Potential (GRP) as a foundation for identifying RPAs and, consequently, assessing radon risk in indoor environments. Here, GRP is proposed as a hazard indicator, indicating the potential for radon to enter buildings from geological sources. Various approaches, including multivariate geospatial analysis and the application of artificial intelligence algorithms, have been utilised to generate continuous spatial maps of GRP based on point measurements. In this study, we employed a robust multivariate machine learning algorithm (Random Forest) to create the GRP map of the central sector of the Pusteria Valley, incorporating other variables from census tracts such as land use as a vulnerability factor, and population as an exposure factor to create the risk map. The Pusteria Valley in northern Italy was chosen as the pilot site due to its well-known geological, structural, and geochemical features. The results indicate that high Rn risk areas are associated with high GRP values, as well as residential areas and high population density. Starting with the GRP map (e.g., Rn hazard), a new geological-based definition of the RPAs is proposed as fundamental tool for mapping Collective Radon Risk Areas in line with the main objective of European regulations, which is to differentiate them from Individual Risk Areas.

Use of random forest algorithm for predictive modelling of transfer factor soil-plant for radiocaesium: A feasibility study.

A German dataset with soil-plant transfer factors for radiocaesium including many co-variables was analysed and prepared for the application of the Random Forest (RF) algorithm using the R libraries 'party', and 'caret'. A RF predictive model for soil-plant transfer factor was created based on 10 co-variables. These are, for example, taxonomic plant family, plant part, soil type and the exchangeable potassium concentration in the soil. The RF model results were compared with the results of two (semi-)mechanistic models. Of the more than 3000 entries in the original dataset, only about 1200 could be used, as this was the largest complete dataset with the largest number of co-variables available. The obtained RF predictive model can reproduce the experimental observations better than the two (semi)-mechanistic models, which are based on many assumptions and fixed parameter values. Model performance was quantified using the metrics of Root Mean Square Error (rmse) and Mean Absolute Error (mae). The RF model was able to reproduce the variability of the data by up to 6 orders of magnitude. The categorical co-predictors, especially taxonomic plant family and plant part, have a greater influence than the numerical co-predictors, such as pH and exchangeable soil potassium concentration. This feasibility study shows that RF is a promising tool to obtain predictive models for transfer factors. However, to build a widely applicable predictive model, a dataset is needed that contains at least thousands of entries for transfer factors and for the most important co-variables and considers a large parameter space.

Autonomous Large-Scale Radon Mapping and Buoyant Plume Modeling Quantify Deep Submarine Groundwater Discharge: A Novel Approach Based on a Self-Sufficient Open Ocean Vehicle.

Groundwater discharge into the sea occurs along many coastlines around the world in different geological settings and constitutes an important component of global water and matter budget. Estimates of how much water flows into the sea worldwide vary widely and are largely based on onshore studies and hydrological or hydrogeological modeling. In this study, we propose an approach to quantify a deep submarine groundwater outflow from the seafloor by using autonomously measured ocean surface data, i.e., 222Rn as groundwater tracer, in combination with numerical modeling of plume transport. The model and field data suggest that groundwater outflows from a water depth of ∼100 m can reach the sea surface implying that several cubic meters per second of freshwater are discharged into the sea. We postulate an extreme rainfall event 6 months earlier as the likely trigger for the groundwater discharge. This study shows that measurements at the sea surface, which are much easier to conduct than discharge measurements at the seafloor, can be used not only to localize submarine groundwater discharges but, in combination with plume modeling, also to estimate the magnitude of the release flow rate.

Machine learning in environmental radon science.

Temporal dynamic as well as spatial variability of environmental radon are controlled by factors such as meteorology, lithology, soil properties, hydrogeology, tectonics, and seismicity. In addition, indoor radon concentration is subject to anthropogenic factors, such as physical characteristics of a building and usage pattern. New tools for spatial and time series analysis and prediction belong to what is commonly called machine learning (ML). The ML algorithms presented here build models based on sample and predictor data to extract information and to make predictions. We give a short overview on ML methods and discuss their respective merits, their application, and ways of validating results. We show examples of 1) geogenic radon mapping in Germany involving a number of predictors, and of 2) time series analysis of a long-term experiment being carried out in Chiba, Japan, involving indoor radon concentrations and meteorological predictors. Finally, we identified the main weakness of the techniques, and we suggest actions to overcome their limitations.

Radon (222Rn) as tracer for submarine groundwater discharge investigation-limitations of the approach at shallow wind-exposed coastal settings.

Mapping radon (222Rn) distribution patterns in the coastal sea is a widely applied method for localizing and quantifying submarine groundwater discharge (SGD). While the literature reports a wide range of successful case studies, methodical problems that might occur in shallow wind-exposed coastal settings are generally neglected. This paper evaluates causes and effects that resulted in a failure of the radon approach at a distinct shallow wind-exposed location in the Baltic Sea. Based on a simple radon mass balance model, we discuss the effect of both wind speed and wind direction as causal for this failure. We show that at coastal settings, which are dominated by gentle submarine slopes and shallow waters, both parameters have severe impact on coastal radon distribution patterns, thus impeding their use for SGD investigation. In such cases, the radon approach needs necessarily to allow for the impact of wind speed and wind direction not only during but also prior to the field campaign.

Radon hazard vs. radon risk - On the effectiveness of radon priority areas.

The detrimental health effects of radon have been acknowledged by national and international legislation such as the European Union Basic Safety Standards (EURATOM-BSS Article 103/3) which requires member states to delineate radon priority areas. These radon priority areas are conventionally based on the concept of hazard by using indoor radon concentration or geogenic radon potential for its delineation. While this approach is efficient for finding many affected buildings with limited resources and, hence, reducing the individual risk, it is probably inefficient for reducing the collective risk if hazard and risk areas differ. In this study we map collective radon risk for Germany by linking information of geogenic radon hazard with exposure (residential building stock). The resulting map of affected residential buildings reveals distinct spatial contrasts compared to the hazard-based map. Further, an analysis based on hypothetical hazard zones elucidates that in Germany the vast majority of affected buildings (i.e., above threshold concentration) are located outside of areas of high and very high hazard. Consequently, in Germany, a radon policy focusing on areas of very high hazard only and within these areas on high concentration buildings only would presumably have no significant effect on the reduction of the total number of radon attributable lung cancer fatalities, i.e. less than 1% of annual radon attributable lung cancer fatalities. We conclude that for reducing the collective risk significantly, also complementary measures are of particular relevance.

The need for Pan-European automatic pollen and fungal spore monitoring: A stakeholder workshop position paper.

BACKGROUND: Information about airborne pollen concentrations is required by a range of end users, particularly from the health sector who use both observations and forecasts to diagnose and treat allergic patients. Manual methods are the standard for such measurements but, despite the range of pollen taxa that can be identified, these techniques suffer from a range of drawbacks. This includes being available at low temporal resolution (usually daily averages) and with a delay (usually 3-9 days from the measurement). Recent technological developments have made possible automatic pollen measurements, which are available at high temporal resolution and in real time, although currently only scattered in a few locations across Europe. MATERIALS & METHODS: To promote the development of an extensive network across Europe and to ensure that this network will respond to end user needs, a stakeholder workshop was organised under the auspices of the EUMETNET AutoPollen Programme. Participants discussed requirements for the groups they represented, ranging from the need for information at various spatial scales, at high temporal resolution, and for targeted services to be developed. RESULTS: The provision of real-time information is likely to lead to a notable decrease in the direct and indirect health costs associated with allergy in Europe, currently estimated between €50-150 billion/year.1 DISCUSSION & CONCLUSION: A European measurement network to meet end user requirements would thus more than pay for itself in terms of potential annual savings and provide significant impetus to research across a range of disciplines from climate science and public health to agriculture and environmental management.

Mapping indoor radon hazard in Germany: The geogenic component.

Indoor radon is considered as an indoor air pollutant due to its carcinogenic effect. Since the main source of indoor radon is the ground beneath the house, we utilize the geogenic radon potential (GRP) and a geogenic radon hazard index (GRHI) for predicting the geogenic component of the indoor Rn hazard in Germany. For this purpose, we link indoor radon data (n = 44,629) to maps of GRP and GRHI and fit logistic regression models to calculate the probabilities that indoor Rn exceeds thresholds of 100 Bq/m3 and 300 Bq/m3. The estimated probability was averaged for every municipality by considering only the estimates within the built-up area. Finally, the mean exceedance probability per municipality was coupled with the respective residential building stock for estimating the number of buildings with indoor Rn above 100 Bq/m3 and 300 Bq/m3 for each municipality. We found that (1) GRHI is a better predictor than GRP for indoor radon hazard in Germany, (2) the estimated number of buildings above 100 Bq/m3 and 300 Bq/m3 in Germany is ~2 million (11.6% of all residential buildings) and ~ 350,000 (1.9%), respectively, (3) areas where 300 Bq/m3 exceedance is greater than 10% comprise only 0.8% of the German building stock but 6.3% of buildings with indoor Rn exceeding 300 Bq/m3, and (4) most urban areas and, hence, most buildings (77%) are located in low hazard regions. The implications for Rn protection are twofold: (1) the Rn priority area concept is cost-efficient in a sense that it allows to find the most buildings that exceed a threshold concentration with a given amount of resources, and (2) for an optimal reduction of lung cancer risk areas outside of Rn priority areas must be addressed since most hazardous indoor Rn concentrations occur in low to medium hazard areas.

Mapping the geogenic radon potential for Germany by machine learning.

The radioactive gas radon (Rn) is considered as an indoor air pollutant due to its detrimental effects on human health. In fact, exposure to Rn belongs to the most important causes for lung cancer after tobacco smoking. The dominant source of indoor Rn is the ground beneath the house. The geogenic Rn potential (GRP) - a function of soil gas Rn concentration and soil gas permeability - quantifies what "earth delivers in terms of Rn" and represents a hazard indicator for elevated indoor Rn concentration. In this study, we aim at developing an improved spatial continuous GRP map based on 4448 field measurements of GRP distributed across Germany. We fitted three different machine learning algorithms, multivariate adaptive regression splines, random forest and support vector machines utilizing 36 candidate predictors. Predictor selection, hyperparameter tuning and performance assessment were conducted using a spatial cross-validation where the data was iteratively left out by spatial blocks of 40 km*40 km. This procedure counteracts the effect of spatial auto-correlation in predictor and response data and minimizes dependence of training and test data. The spatial cross-validated performance statistics revealed that random forest provided the most accurate predictions. The predictors selected as informative reflect geology, climate (temperature, precipitation and soil moisture), soil hydraulic, soil physical (field capacity, coarse fraction) and soil chemical properties (potassium and nitrogen concentration). Model interpretation techniques such as predictor importance as well as partial and spatial dependence plots confirmed the hypothesized dominant effect of geology on GRP, but also revealed significant contributions of the other predictors. Partial and spatial dependence plots gave further valuable insight into the quantitative predictor-response relationship and its spatial distribution. A comparison with a previous version of the German GRP map using 1359 independent test data indicates a significantly better performance of the random forest based map.

Development of a Geogenic Radon Hazard Index-Concept, History, Experiences.

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.