In this paper, we present the control of batch processes using model predictive control (MPC) and iterative learning control (ILC). Existing combinations of MPC and ILC are based on learning of the inputs of the process from previous batches for a fixed linear time-invariant model (LTI). However, batch processes are inherently time varying; therefore, LTI models are limited in capturing the relevant dynamic behavior. An attractive alternative is to use linear parameter varying (LPV) models because of their ability to capture nonlinearities in the control of batch processes. Therefore, in this work we propose a novel method combining MPC and ILC based on LPV models, and we call this method model learning predictive control (ML-MPC). Basically, the idea behind the method is to update the LPV model of the MPC iteratively, by using the repetitive behavior of the batch process. To this end, three different application-dependent options to estimate the parameters and disturbances of the model are proposed and are compared in simulation on a nonlinear batch reactor. Finally, the ML-MPC with one of the estimation methods is applied to an industrial reactive batch distillation column (RBD) in simulation.