Airport Arrival Flow Prediction considering Meteorological Factors Based on Deep-Learning Methods

Table 2

Selection of hyperparameters in the model.

Models	Description of hyperparameters	Input values	The selected optimal hyperparameter
LSTM	Hidden layers	{1, 2, 3, 5, 10}	3
	Number of neurons in each hidden layer	{2, 4, 6, 8, 10, 15, 20, 25, 30}	6
	Timestep	{6, 12, 18, 24, 30, 36, 42, 48}	36
XGBoost	Depth of the tree	{1, 2, 3, 5, 10}	3
	Learning rate	{0.01, 0.02, 0.05, 0.1, 0.15}	0.05
	Number of decision trees	{50, 100, 200, 300, 500}	100