Evaluation of Key Parameters Using Deep Convolutional Neural Networks for Airborne Pollution (PM10) Prediction

Table 2

Metrics used to evaluate the results.

Metric	Formula	Range ofvalues	Preferredvalues
Root mean squared error (RMSE)		0 ≤ x ≤ ∞	Lower
Mean absolute percentage error (MAPE)		0 ≤ x ≤ 1	Higher
Index of agreement (IOA)		0 ≤ x ≤ 1	Higher
Coefficient of determination (R^2)		0 ≤ x ≤ 1	Higher