Presumably there are two different contour sources: the model fit on the historical data initialized at the beginning of the historical data, and the model fit on the historical data initialized at the end of the historical data. The ‘background’ lets you see how the actual history compared to what the model predicts, and the ‘foreground’ lets you see what the model predicts for the future.
And so the black line that zooms off the infinity somewhere around 1950 is the “singularity that got cancelled”, or the left line on this simplistic graph.
Yes, though as a nitpick I don’t think the black line is the singularity that got cancelled; that one was supposed to happen in 2020 or so, and as you can see the black line diverges from history well before 1950.
Presumably there are two different contour sources: the model fit on the historical data initialized at the beginning of the historical data, and the model fit on the historical data initialized at the end of the historical data. The ‘background’ lets you see how the actual history compared to what the model predicts, and the ‘foreground’ lets you see what the model predicts for the future.
And so the black line that zooms off the infinity somewhere around 1950 is the “singularity that got cancelled”, or the left line on this simplistic graph.
Yes, though as a nitpick I don’t think the black line is the singularity that got cancelled; that one was supposed to happen in 2020 or so, and as you can see the black line diverges from history well before 1950.