Probabilistic deep learning model as a tool for supporting the fast simulation of a thermal–hydraulic code

•Reducing uncertainty in probabilistic safety assessment strengthens nuclear safety.•For massive simulations to reduce uncertainty, a fast-running model is necessary.•A deep learning-based surrogate model of thermal–hydraulic (TH) code is proposed.•The proposed eQRNN estimates the results of TH code with their uncertain boundary.•Fast and probabilistic estimation of TH code results can improve nuclear safety.