Machine Learning-Based Probabilistic Seismic Demand Model of Continuous Girder Bridges

Table 2

Coefficients of determination of traditional and various ML demand models.

	Methods
Traditional method	Only PGV	0.81	0.80	0.81	0.79	0.81	0.80	0.80	0.80
	Only PSV	0.81	0.81	0.82	0.80	0.82	0.82	0.81	0.82
Linear regression	RR	0.86	0.85	0.86	0.85	0.86	0.86	0.86	0.86
	LR	0.47	0.31	0.46	0.31	0.46	0.40	0.44	0.40
	EN	0.65	0.57	0.63	0.59	0.66	0.61	0.65	0.62
	SVR	0.88	0.87	0.88	0.87	0.88	0.87	0.87	0.87
Bayesian regression	BRR	0.86	0.85	0.86	0.86	0.86	0.86	0.85	0.86
	ARD	0.85	0.85	0.86	0.85	0.86	0.86	0.86	0.84
Tree-based model	RF	0.89	0.88	0.89	0.87	0.88	0.87	0.88	0.88
	GBDT	0.88	0.86	0.89	0.86	0.88	0.86	0.87	0.87
	AdaBoost	0.87	0.86	0.87	0.86	0.88	0.85	0.87	0.87
	LightGBM	0.89	0.86	0.88	0.86	0.88	0.86	0.87	0.85