EUVIMEDEUVIMED entdecken
Crossref

Study on the release pattern of radon exhalation in the overburden soil of uranium tailings under arid climate and prediction based on Fully Connected Neural Network (FCNN)-based deep learning radon prediction model

Xianwei Wu, Yifan Chen, Dongying Lin, Shijie Fang, Le Xiao, Chengyan Yan, Yong Liu

Journal of Environmental Radioactivity · 2026

DOI: 10.1016/j.jenvrad.2025.107883 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Environmental Radioactivity, 2026. Verfasst von Xianwei Wu und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Physics and Optoelectronic Engineering, Shenzhen University, Shenzhen, 518060, Guangdong, China. Hauptthemen laut MEDLINE: Radon, Radiation Monitoring, Soil Pollutants, Radioactive, Air Pollutants, Radioactive. Die Arbeit nennt 29 Literaturangaben. Gefördert von: China Postdoctoral Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting radon exhalation rate under high-temperature and sun-exposure conditions has always been a challenging issue for uranium tailings management units, involving the coupled effects of three important factors: temperature, humidity, and fractures rate. Under arid climate conditions, a series of indoor simulation experiments with different temperatures were conducted on the covering soil of uranium tailings. The Fully Connected Neural Network (FCNN)-based deep learning radon prediction model was proposed, and through error comparison with the Long Short-Term Memory (LSTM) model, the FCNN-based deep learning radon prediction model model demonstrated a better ability to reflect the laws of radon gas release and could more accurately express the relationships between temperature, soil moisture content, the overburden fractures rate, and radon exhalation rate. This paper provides a feasible prediction method for radon control and prevention in uranium tailings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadonRadiation MonitoringSoil Pollutants, RadioactiveAir Pollutants, RadioactiveUraniumNeural Networks, ComputerDeep LearningPrediction AlgorithmsPredictive Learning ModelsDesert Climate

Stichwörter der Autor:innen

FCNNHigh-temperatureRadon exhalation rateRadon prediction modelUranium tailings

Substanzen

RadonUraniumSoil Pollutants, RadioactiveAir Pollutants, Radioactive

Autor:innen und Institutionen

  • College of Physics and Optoelectronic Engineering, Shenzhen University, Shenzhen, 518060, Guangdong, China.
  • College of Physics and Optoelectronic Engineering, Shenzhen University, Shenzhen, 518060, Guangdong, China. Electronic address: usccyf@163.com.
  • Hunan Province Engineering Technology Research Center of Uranium Tailings Treatment, Hengyang, 421001, Hunan, China.

Förderung

  • China Postdoctoral Science Foundation

Zitieren

APA

Wu, X., Chen, Y., Lin, D., Fang, S., Xiao, L., Yan, C., & Liu, Y. (2026). Study on the release pattern of radon exhalation in the overburden soil of uranium tailings under arid climate and prediction based on Fully Connected Neural Network (FCNN)-based deep learning radon prediction model. Journal of Environmental Radioactivity. https://doi.org/10.1016/j.jenvrad.2025.107883

Vancouver

Wu X, Chen Y, Lin D, Fang S, Xiao L, Yan C, et al. Study on the release pattern of radon exhalation in the overburden soil of uranium tailings under arid climate and prediction based on Fully Connected Neural Network (FCNN)-based deep learning radon prediction model. Journal of Environmental Radioactivity. 2026. doi:10.1016/j.jenvrad.2025.107883

BibTeX
@article{Wu2026,
  author = {Wu, Xianwei and Chen, Yifan and Lin, Dongying and Fang, Shijie and Xiao, Le and Yan, Chengyan and Liu, Yong},
  title = {Study on the release pattern of radon exhalation in the overburden soil of uranium tailings under arid climate and prediction based on Fully Connected Neural Network (FCNN)-based deep learning radon prediction model},
  journal = {Journal of Environmental Radioactivity},
  year = {2026},
  doi = {10.1016/j.jenvrad.2025.107883}
}
Kostenlos starten →