In this talk, we introduce a machine learning approach that combines reduced-order models data assimilation in order to create a operation digital twin to predict the power distribution over the core in the operation stage. The operational digital twin is designed to solve forward problems given input operation parameters, as well as to solve inverse problems given some observations of the power field. The forward model is a non-intrusive reduced order model realized with different machine learning methods. For parameter estimation, different inverse models are introduced. The effectiveness in the sense of accuracy and real-time solver of the operation digital twin is illustrated through a real engineering problem in nuclear reactor physics — reactor core simulation in the life cycle of HPR1000 affected by input parameters, i.e., control rod inserting step, burnup, power level and inlet temperature of the coolant, which shows potential applications for on-line monitoring purpose.