Figures (5)  Tables (3)

    • Figure 1. 

      Airport layout structure diagram. (a) MAN. (b) MUC. (c) HKG.

    • Figure 2. 

      Comparison of optimal and original solutions for different airports under three metrics.

    • Figure 3. 

      Initial ranking of factors affecting aircraft taxi time. (a) MAN. (b) MUC. (c) HKG.

    • Figure 4. 

      Analysis of key influencing factors for HKG airport. (a) MAN airport OperationType feature. (b) MAN airport EuclideanDistance feature. (c) MAN airport TaxiDistance feature. (d) MAN airport TurnCount feature. (e) MUC airport OperationType feature. (f) MUC airport TaxiDistance feature. (g) MUC airport TurnCount feature. (h) MUC airport EuclideanDistance feature. (i) HKG airport TaxiDistance feature. (j) HKG airport OperationType feature. (k) HKG airport RunwayConfig feature. (l) HKG airport EuclideanDistance feature.

    • Figure 5. 

      Variation in accurate values and error values based on the NSGA-RF model recursive feature elimination method. (a) Changes in prediction accuracy at MAN airport. (b) Variations in the error at MAN airport. (c) Changes in prediction accuracy at MUC airport. (d) Variations in the error at MUC airport. (e) Changes in prediction accuracy at HKG airport. (f) Variations in the error at HKG airport.

    • Airport Metric SVR XGBoost MLR RF BLR
      MAN Accuracy (%) 79.59 79.29 77.39 80.16 77.41
      MAE (s) 109.50 109.97 118.07 105.09 117.76
      RMSE (s) 151.39 148.62 157.85 146.03 157.77
      R2 0.75 0.76 0.73 0.77 0.73
      ±60 (%) 39.64 39.39 36.32 41.94 36.83
      ±180 (%) 80.82 79.28 78.52 82.82 78.77
      ±300 (%) 93.86 93.86 92.84 94.37 92.84
      MUC Accuracy (%) 74.40 79.29 71.41 74.64 71.56
      MAE (s) 112.33 109.97 119.54 105.92 119.20
      RMSE (s) 159.68 154.62 165.02 152.33 164.96
      R2 0.64 0.71 0.62 0.68 0.62
      ±60 (%) 46.25 39.39 41.89 46.25 41.89
      ±180 (%) 76.03 79.28 74.58 80.63 74.09
      ±300 (%) 93.22 93.86 91.53 93.46 91.28
      HKG Accuracy (%) 84.78 84.75 84.09 85.23 83.96
      MAE (s) 109.16 112.21 116.83 107.58 117.17
      RMSE (s) 139.03 143.90 146.98 134.97 147.23
      R2 0.66 0.64 0.62 0.68 0.62
      ±60 (%) 35.39 33.51 30.83 34.85 31.10
      ±180 (%) 82.31 81.50 80.43 80.97 79.89
      ±300 (%) 96.51 96.51 95.71 96.78 95.71
      The optimal values for each metric are highlighted in bold.

      Table 1. 

      Prediction performance results of different models across different airports.

    • Airport Accuracy rates for
      different error ranges      		 Accuracy R2 MAE (s) RMSE (s)
      ±60 s ±180 s ±300 s
      MAN 43.99% 82.86% 95.40% 80.46% 0.78 103.42 142.72
      MUC 48.18% 81.11% 93.95% 74.85% 0.67 105.78 152.37
      HKG 36.19% 83.65% 97.05% 85.70% 0.69 104.01 133.06

      Table 2. 

      Runway taxiing time prediction results based on the NSGA-RF model.

    • MAE/RMSE Acc60 Acc180 Acc300
      OperationType OperationType OperationType OperationType
      TaxiDistance TaxiDistance TaxiDistance TaxiDistance
      Euclidean
      Distance      		 Euclidean
      Distance      		 Euclidean
      Distance      		 Euclidean
      Distance
      TurnCount TurnCount TurnCount TurnCount
      FlightCode FlightCode FlightCode FlightCode
      FlightsSameHour Relative
      Humidity_2m      		 Relative
      Humidity_2m
      FlightsSameHour FlightsSameHour
      FlightsWithin15Min FlightsWithin15Min

      Table 3. 

      Common importance features of airports under different metrics.