Volume 2, Issue 3, October 2009, Pages 267 - 276
Neural Networks Simulation of the Transport of Contaminants in Groundwater
Received 1 April 2009, Accepted 7 July 2009, Available Online 1 October 2009.
- https://doi.org/10.2991/ijcis.2009.2.3.8How to use a DOI?
- Keywords: Neural networks, performance assessment of radioactive waste repositories, groundwater contaminant transport, advection-dispersion.
- The performance assessment of an engineered solution for the disposal of radioactive wastes is based on mathematical models of the disposal system response to predefined accidental scenarios, within a probabilistic approach to account for the involved uncertainties. As the most significant potential pathway for the return of radionuclides to the biosphere is groundwater flow, intensive computational efforts are devoted to simulating the behaviour of the groundwater system surrounding the waste deposit, for different values of its hydrogeological parameters and for different evolution scenarios. In this paper, multilayered neural networks are trained to simulate the transport of contaminants in monodimensional and bidimensional aquifers. The results obtained in two case studies indicate that the approximation errors are within the uncertainties which characterize the input data.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - JOUR AU - Enrico Zio PY - 2009 DA - 2009/10 TI - Neural Networks Simulation of the Transport of Contaminants in Groundwater JO - International Journal of Computational Intelligence Systems SP - 267 EP - 276 VL - 2 IS - 3 SN - 1875-6883 UR - https://doi.org/10.2991/ijcis.2009.2.3.8 DO - https://doi.org/10.2991/ijcis.2009.2.3.8 ID - Zio2009 ER -