<p>Long-term diffusion of H<sup>79</sup>SeO<sub>3</sub><sup>−</sup>, <sup>99</sup>TcO<sub>4</sub><sup>−</sup>, <sup>238</sup>UO<sub>2</sub><sup>2+</sup>, and <sup>237</sup>NpO<sub>2</sub><sup>+</sup> in compacted bentonite was investigated using a combined GAN-DNN and PINN model. The apparent diffusion coefficient (<i>D</i><sub>a</sub>) of HSeO<sub>3</sub><sup>−</sup> and ReO<sub>4</sub><sup>−</sup> was measured using a through-diffusion method to validate the generalization of GAN-DNN. Subsequently, the PINN model simulated the spatiotemporal evolution of radionuclide concentrations over 1000-year using the GAN-DNN-predicted <i>D</i><sub>a</sub> as inputs. It reveals that strong sorption effectively restricted <sup>238</sup>UO<sub>2</sub><sup>2+</sup> and <sup>237</sup>NpO<sub>2</sub><sup>+</sup> diffusion, whereas anionic exclusion facilitated the penetration of 66%–86% of <sup>99</sup>TcO<sub>4</sub><sup>−</sup> and H<sup>79</sup>SeO<sub>3</sub>⁻ to penetrate the 0.36&#xa0;m engineered barrier of the Beishan repository in China.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Long-term prediction of radionuclide migration in bentonite: diffusion experiments and combined GAN-DNN-PINN model

  • Tao Wu,
  • Ke Xu,
  • Jiaxing Feng,
  • Xuewen Gao,
  • Jilong He,
  • Yaolin Zhao

摘要

Long-term diffusion of H79SeO3, 99TcO4, 238UO22+, and 237NpO2+ in compacted bentonite was investigated using a combined GAN-DNN and PINN model. The apparent diffusion coefficient (Da) of HSeO3 and ReO4 was measured using a through-diffusion method to validate the generalization of GAN-DNN. Subsequently, the PINN model simulated the spatiotemporal evolution of radionuclide concentrations over 1000-year using the GAN-DNN-predicted Da as inputs. It reveals that strong sorption effectively restricted 238UO22+ and 237NpO2+ diffusion, whereas anionic exclusion facilitated the penetration of 66%–86% of 99TcO4 and H79SeO3⁻ to penetrate the 0.36 m engineered barrier of the Beishan repository in China.