Thermal recovery techniques, such as steam-assisted gravity drainage (SAGD), are used to recover the majority of the crude bitumen, in Western Canada. However, suboptimal production techniques have led to a large carbon footprint and a subsequent search for more efficient extraction techniques, than open loop manual control. This article summarizes research on the comparison of performance of a novel multi-input multioutput (MIMO) model predictive controller (MPC) with steam trap and oil rate controls with a multi-input single output (MISO) MPC with only steam trap control. An appropriate system identification technique was also used for periodic model update in compliance with changing system behavior. The real-time control study was made possible by establishing a bidirectional communication between computer modeling group STARS (TM) (virtual reservoir) and MATLAB (onsite controller) software. The results show a 171% improvement in oil recovery for the novel MIMO MPC over the MISO MPC. (C) 2018 American Institute of Chemical Engineers