Scenarios of future urban expansion are intended to be plausible: diverse to reflect future uncertainty, yet realistically depicting expansion processes. We investigated the plausibility of scenarios derived from a novel data-driven simulation approach. In a Turing-like test, experts completed a quiz which challenged them to identify the map showing true urban expansion amidst three model-generated scenarios. Across diverse expansion patterns, ranging from compact to dispersed, the experts had no significant ability to identify the true pattern. The results are supportive of the use of machine learning with dynamic models to produce convincing and wide-ranging scenarios of future urban expansion.