Fig 1.
The unfolding diagram of the forward propagation of the RNN.
Table 1.
Criteria of MAPE and RMSPE.
Fig 2.
Decomposition of the number of PTB cases in Urumqi from January 2014 to December 2018.
Fig 3.
ACF and PACF diagrams after first-order difference of PTB cases in Urumqi.
Table 2.
The evaluations of goodness-of-fit for plausible ARIMA models.
Table 3.
Parameters estimation for ARIMA (1,1,2)×(0,0,1)12 model.
Table 4.
White noise test of residuals for ARIMA (1,1,2)×(0,0,1)12 model.
Table 5.
The optimal models for each air pollutant.
Fig 4.
Cross-correlations between the pre-whitened PTB cases and air pollutants.
Table 6.
The residual and parameter tests of ARIMAX models.
Fig 5.
Spearman ranks correlation coefficients between the PTB cases and air pollutants with a lag of 1 to 12 months.
Notes *: P < 0.05 **: P < 0.01 ***: P < 0.001.
Fig 6.
Epoch-error plots of the RNN9 after three training cycles.
(A) First cycle, (B) Second cycle, (C) Third cycle.
Table 7.
Training results of RNN1-RNN5 models.
Table 8.
Training results of RNN models with incorporating air pollutants (O3, PM2.5, PM10, SO2, and NO2).
Fig 7.
Distances between OBS and simulation results by ARIMA, ARIMAX, and RNN models.
Fig 8.
The fitting results of ARIMA, ARIMAX, and RNN models.
Fig 9.
The fitting and predicting results of the ARIMAX(1,1,2)×(0,1,1)12+PM2.5(lag = 12)model.