PREDICTING VAPOR-PRESSURES USING NEURAL NETWORKS

Calculating surface vapor pressures of volatile inorganic components, nitric acid, hydrochloric acid and ammonia, is essential for modeling condensation and evaporation processes occurring in atmospheric aeroso ls. The vapor pressure of these compounds depends on temperature, rela tive humidity, phase state, and particle composition, and their calcul ation consumes an enormous amount of computer time in Eulerian photoch emical/aerosol models. Here we use a thermodynamic model to generate a large set of vapor pressure data as a function of aerosol composition , relative humidity, and temperature. These data are then used as a tr aining set for neural networks. Once the networks memorize the data, i nterpolation of vapor pressures for intermediate compositions, tempera tures and relative humidities is automatic. The neural network models are able to reproduce the values predicted by the thermodynamic models accurately and are 4-1200 times faster depending on atmospheric condi tions and the assumptions employed in the thermodynamic calculations. Copyright (C) 1996 Elsevier Science Ltd.