Code and data for Machine-learning-boosted ab-initio study of the thermal conductivity of Janus PtSTe van der Waals heterostructures Contents: neuralil.tar.xz: version used in the manuscript of the force-field code described in the articles A Differentiable Neural-Network Force Field for Ionic Liquids and Deep ensembles vs committees for uncertainty estimation in neural-network force fields: Comparison and application to active learning. General-purpose releases can be found here. DFT_data.tar.xz: first-principles data created for training and validating the force field, stored as ASE databases in JSON format. model_params_plain_ensemble_DEEP_413E12A9.pkl: saved parameters of the fully trained force field. 0001-Use-equipartition-occupancies.patch: patch for Phono3py to use classical (equipartition) occupations instead of Bose-Einstein values.