Dynamic prediction for attitude and position of shield machine in tunneling: A hybrid deep learning method considering dual attention

•A novel approach for adjusting the shield’s attitude and position during tunneling was proposed.•A hybrid deep learning prediction framework including comprehensive feature evaluation method, EEMD, CA-CNN and GRU-TA is established.•The test is carried out with the field data collected from the railway in Shanghai, China.•The proposed model is significantly superior to other models in prediction accuracy and prediction efficiency.•The contributions of CA and TA in the model are revealed.