Modelling the complex physics of the Interstellar Medium (ISM) in the context of large-scale numerical simulations is a challenging task. A number of methods have been proposed to embed a description of the ISM into different codes. We propose a new way to achieve this task: Artificial Neural Networks (ANNs). The ANN has been trained on a pre-compiled model database, and its predictions have been compared to the expected theoretical ones, finding good agreement both in static and in dynamical tests run using the Padova Tree-SPH code \textsc{EvoL}. A neural network can reproduce the details of the interstellar gas evolution, requiring limited computational resources. We suggest that such an algorithm can replace a real-time calculation of mass elements chemical evolution in hydrodynamical codes.
@article{arxiv.1103.0509,
title = {MaNN: Multiple Artificial Neural Networks for modelling the Interstellar Medium},
author = {T. Grassi and E. Merlin and L. Piovan and U. Buonomo and C. Chiosi},
journal= {arXiv preprint arXiv:1103.0509},
year = {2011}
}