Yes, true. But the timescales involved, and the a priori improbability of the particular outcome we see before us is what is relevant here. Of all the ways a body of water and erosion could shape a landscape, we end up with the exact particular structure we call The Grand Canyon. What are the odds?
And we can’t go back in time to re-create the events that formed it. We are forced to infer from known causes that this a priori extremely unlikely, highly contingent geological formation is what resulted, and that the forces and durations and so on all were just right so as to produce this specific result:
We could do a “waiting time problem” for the Grand Canyon. How long would we have to wait on average, for a period of erosion starting with some arbitrarily picked geography, to produce our exact Grand Canyon? There are so many OTHER ways it could have played out.