A workflow to update the time-lapse low-frequency model in a data-driven manner in time-lapse inversion studies is applied to a heavy-oil reservoir produced using the steam-assisted gravity drainage (SAGD) method. The base seismic survey and the difference between the base and monitor surveys are inverted in two separate inversion runs, and no assumptions are made regarding the reservoir changes or the relationships between elastic or reservoir parameters. The effects of production are estimated from the inversion of the difference between the base and monitor surveys. This information is used to update the low-frequency model in the time-lapse sense. A good match can be observed between the inversion results and other available information from the field, confirming the validity of the method.