Classification and prediction of radon stable zone in uranium tailings pond: a case study from uranium tailings pond in sothern China

• Published in: Journal of radioanalytical and nuclear chemistry Vol. 332; no. 2; pp. 251 - 259
• Main Authors: Chen, Yifan, Wu, Xianwei, Zhang, Tiejun, Zhang, Min, Dai, Xingwang, Xu, Zhenghua, Liu, Yong
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.02.2023; Springer; Springer Nature B.V
• Subjects: Algorithms; Analysis; Back propagation networks; Case studies; Chemistry; Chemistry and Materials Science; Dam stability; Diagnostic Radiology; Error reduction; Hadrons; Heavy Ions; Inorganic Chemistry; Neural networks; Nuclear Chemistry; Nuclear energy; Nuclear Physics; Physical Chemistry; Ponds; Radium; Radon levels; Soil stability; Tailings; Uranium; Early warning; Radon; Stable zone; WOA-BP
• ISSN: 0236-5731; 1588-2780
• DOI: 10.1007/s10967-023-08764-0

Radon is a radioactive gas produced by the decay of radium in uranium tailings, which can migrate to the atmosphere through tiny pores in the soil and can be used to characterize the internal stability of tailings dam. A method for determining the stable zone of radon is proposed, in which the radon concentration of uranium tailings pond is divided into stable zone, asymptotically stable zone, and unstable zone, and through the WOA-BP neural network algorithm for intelligent early warning of stability zone. The results show that the MAPE (Mean Absolute Percentage Error) is reduced by 20.16% by dividing the stable region, And MAPE of WOA-BP neural network algorithm is 8.22% lower than that of BP neural network algorithm. It shows that this method can provide guidance for the safe and stable operation of uranium tailings pond.