The process is known as Cascaded classification/regression or Multi-stage classification/regression. It is a type of ensemble learning with some differences. You can find more in Wikipedia.
Autocorrelation lags are created by taking a pair of values at a given lag, multiplying the pair and summing across all pairs. Because your signal has a finite length, large autocorrelation lags have fewer and fewer pairs summed together, and thus are smaller values. You can compensate for this by using an "unbiased" autocorrelation. Statsmodels acf has an option to return an unbiased estimate: http://statsmodels.sourceforge.net/stable/generated/statsmodels.tsa.stattools.acf.html
Best Answer
I would say so...plateau does, however, seems to imply relatively high flat territory. One might call this a 'bottom' or 'floor'.