MODELING GEOLOGICAL BRINES IN SALT-DOME HIGH-LEVEL NUCLEAR WASTE ISOLATION REPOSITORIES BY ARTIFICIAL NEURAL NETWORKS

In order to study the influence of various parameters on the acidity of simulated geological brines, an artificial intelligence technique based on neural network modeling has been developed. It has been found that the pH of simulated salt repository brines lies within the range of 3.2-5 as the temperature of the brine decays from 250 degrees to 125 degrees C. This environment might cause severe corrosion damage to canisters fabricated from carbon steel, particularly under slightly oxidizing conditions because of autocatalytical attack. It has also been demonstrated that artificial neural networks are efficient tools for analysing complex chemical systems, especially when conventional modeling is precluded by a lack of knowledge of the species and equilibria involved in the system.