An Empirical Study for Adopting Machine Learning Approaches for Gas Pipeline Flow Prediction

Table 3

The details of each performance measure of GBDT models when using the different learning rates.

Learning rate	0.05	0.1	0.15	0.2	0.25
MSE	9.8 × 10^2	7.9 × 10^2	7.3 × 10^2	7.2 × 10^2	7 × 10^2
MRE	0.000950502	0.000748058	0.000688089	0.000653405	0.000625291
	5.227 × 10^−6	4.178 × 10^−60−6	3.899 × 10^−6	3.817 × 10^−6	3.738 × 10^−6