In a collaborative effort researchers at the University of Hawaiʻi Institute for Astronomy (IfA), the NSF funded National Solar Observatory and NSF NCAR’s High Altitude Observatory developed a new artificial intelligence based method to reconstruct the magnetic field in the solar atmosphere. The method uses a physics informed neural network to combine observations with physical constraints on the connectivity of magnetic fields to reconstruct a 3D volume of the solar atmosphere. The performance of the method was assessed with the help of synthetic data provided by the MURaM radiative MHD code, which is a joint development by NSF NCAR and the Max Planck Institute for Solar System Research in Germany.