neuralpdr emulates the 3D-PDR photodissociation region code (ascl:1803.010) for one-dimensional uniform clouds. It uses augmented neural ordinary differential equations as surrogate models to reproduce the chemistry, heating, and cooling structure as a function of depth into a cloud (visual extinction). The emulator takes as inputs the gas density, cosmic-ray ionization rate, radiation field, and visual extinction and predicts chemical abundances and temperature.

PDFchem models the cold ISM at moderate and large scales using functions connecting the quantities of the local and the observed visual extinctions and the local number density with probability density functions. For any given observed visual extinction sampled with thousands of clouds, the algorithm instantly computes the average abundances of the most important species and performs radiative transfer calculations to estimate the average emission of the most commonly observed lines.