Table 6 Comparison of prediction accuracies of different models under major subsidence regions.

From: SHAP-enhanced interpretive MGTWR-CNN-BILSTM-AM framework for predicting surface subsidence: a case study of Shanghai municipality

Models

MAE (mm)

RMSE (mm)

sMAPE (%)

\(R^{2}\)

BL

4.7258

5.0267

33.21

0.91956

CNN-BL

4.6558

4.8954

30.25

0.92594

C-B-A

4.5210

4.7565

28.21

0.93868

GCB

3.6745

4.0795

24.63

0.96684

MGCB

3.2555

3.6758

23.15

0.97209

MGCBA

2.6698

2.8956

22.14

0.97515

Back to article page