Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

GLORIF1, a global river flow dataset created by integrating process-based modelling and machine learning.

Scientific data·2026
Same author

Radon risk mapping in Spain: a population and building-inclusive approach.

Environment international·2026
Same author

Long-Term Ecological Baselines and Critical Thresholds in Ombrotrophic Peatlands of Europe: Implications for Restoration Strategies.

Global change biology·2025
Same author

From collective to individual radon risk exposure: An insight into the current European regulation.

Environment international·2025
Same author

Response of the bGeigie Nano and CzechRad Monitors to Secondary Cosmic Radiation.

Sensors (Basel, Switzerland)·2025
Same author

Mapping the exposure to outdoor radon in the German population.

Journal of environmental radioactivity·2024

Related Experiment Video

Updated: Nov 28, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.2K

Mapping the geogenic radon potential for Germany by machine learning.

Eric Petermann1, Hanna Meyer2, Madlene Nussbaum3

  • 1Federal Office for Radiation Protection (BfS), Section Radon and NORM, Berlin, Germany.

The Science of the Total Environment
|December 1, 2020
PubMed
Summary

This study created a more accurate map of geogenic radon potential (GRP) in Germany using machine learning. The improved map better predicts indoor radon gas levels, crucial for lung cancer prevention.

Keywords:
Digital soil mappingGeogenic radon potentialMachine learningPartial dependenceSoil radonSpatial cross-validation

More Related Videos

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
09:44

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

10.5K
Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
12:26

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

13.6K

Related Experiment Videos

Last Updated: Nov 28, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.2K
Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
09:44

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

10.5K
Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM
12:26

Integrating Remote Sensing with Species Distribution Models; Mapping Tamarisk Invasions Using the Software for Assisted Habitat Modeling SAHM

Published on: October 11, 2016

13.6K

Area of Science:

  • Environmental Science
  • Geology
  • Public Health

Background:

  • Radon (Rn) is a radioactive gas and a significant indoor air pollutant, contributing to lung cancer. Indoor radon primarily originates from the ground.
  • Geogenic Radon Potential (GRP) quantifies the earth's contribution of radon, serving as a hazard indicator for elevated indoor radon concentrations.

Purpose of the Study:

  • To develop an improved, spatially continuous Geogenic Radon Potential (GRP) map for Germany.
  • To enhance the accuracy of hazard indication for elevated indoor radon concentrations.

Main Methods:

  • Utilized 4448 field measurements of GRP across Germany.
  • Applied and compared three machine learning algorithms: multivariate adaptive regression splines, random forest, and support vector machines.
  • Conducted spatial cross-validation using 40 km*40 km blocks to mitigate spatial auto-correlation and ensure robust performance assessment.

Main Results:

  • Random forest demonstrated the highest prediction accuracy among the tested algorithms.
  • Key predictors for GRP included geological factors, climate variables (temperature, precipitation, soil moisture), and soil properties (hydraulic, physical, and chemical).
  • Model interpretation confirmed geology's dominant role while highlighting significant influences from other environmental factors.

Conclusions:

  • The developed random forest-based GRP map significantly outperforms previous versions in predicting indoor radon potential.
  • The findings provide a more reliable tool for assessing and mitigating radon-induced health risks in Germany.