Tunnel Settlement Prediction by Transfer Learning

Qicai Zhou, Hehong Shen, Jiong Zhao, Xiaolei Xiong


Tunnel settlement has a significant impact on property security and personal safety. Accurate tunnel-settlement predictions can quickly reveal problems that may be addressed to prevent accidents. However, each acquisition point in the tunnel is only monitored once daily for around two months. This paper presents a new method for predicting tunnel settlement via transfer learning. First, a source model is constructed and trained by deep learning, then parameter transfer is used to transfer the knowledge gained from the source model to the target model, which has a small dataset. Based on this, the training complexity and training time of the target model can be reduced. The proposed method was tested to predict tunnel settlement in the tunnel of Shanghai metro line 13 at Jinshajiang Road and proven to be effective. Artificial neural network and support vector machines were also tested for comparison. The results showed that the transfer-learning method provided the most accurate tunnel-settlement prediction.


deep neural network; gated recurrent unit; settlement prediction; tunneling; transfer learning

Full Text:



Wang, J.J. & Ma, Y.L., Deep Learning for Smart Manufacturing: Methods and Applications, Journal of Manufacturing Systems, 48, pp. 144-156, 2018.

Li, C., Sánchez, R.V., Zurita, G., Cerrada, M. & Cabrera, D., Fault Diagnosis for Rotating Machinery Using Vibration Measurement Deep Statistical Feature Learning, Sensors, 16(6), Article No. 895, 2016.

Obst, O., Distributed Fault Detection in Sensor Networks Using a Recurrent Neural Network, Neural Processing Letters, 40, pp. 261-273, 2014.

Wei, K., Gong, Q.M. & Zhou, S.H., Ant Colony Algorithms of Long-Term Uneven Settlement Prediction in Tunnel, Journal of Tongji University, 37, pp. 993-998, 2009.

Fan, S.X., Zhou, Q.C., Xiong, X.L. & Zhao, J., Settlement Prediction of Tunnel Based on Multiple Kernels Learning Mode, Rock and Soil Mechanics, 34, pp. 291-298, 2013.

Goh, A.T.C., Zhang, W.G., Zhang, Y.M., Xiao, Y. & Xiang Y.Z., Determination of Earth Pressure Balance Tunnel-related Maximum Surface Settlement: A Multivariate Adaptive Regression Splines Approach, Bulletin of Engineering Geology & the Environment, 77, pp. 489-500, 2018.

Maiedi, P., Akbulut, S. & Celik, S., The Experimental, Analytical and Numerical Estimation of Ground Surface Settlement Caused by Tunnel Excavation, 2nd International Conference on Advanced Engineering Technologies, pp. 21-23, 2017.

Pan, W.K., A Survey of Transfer Learning for Collaborative Recommendation with Auxiliary Data, Neurocomputing, 177, pp. 447-453, 2016.

Pan, S.J. & Yang, Q., A Survey on Transfer Learning, IEEE Transactions on Knowledge & Data Engineering, 22, pp. 1354-1359, 2010.

Hochreiter, S. & Schmidhuber, J., LSTM Can Solve Hard Long Time Lag Problems, Advances in Neural Information Processing Systems, 9, pp. 473-479, 2003.

Cho, K., Merrienboer, B.V., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H. & Bengio, Y. Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation, Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Association for Computational Linguistic, pp. 1724-1734, 2014.

Galanti, T., Wolf, L. & Hazan, T., A Theoretical Framework for Deep Transfer Learning, Information & Inference A Journal of the IMA, 5, pp. 159-209, 2016.

Bai, Y. & Tang, J., Experience and Lessons from Underground Construction in Shanghai, China Civil Engineering Journal, 40, pp. 105-110, 2007.

Bengio, Y., Deep Learning of Representations for Unsupervised and Transfer, MLR: Workshop and Conference Proceedings. Workshop on Unsupervised and Transfer Learning, 27, pp. 17-37, 2012.

DOI: http://dx.doi.org/10.5614%2Fitbj.ict.res.appl.2019.13.2.3


  • There are currently no refbacks.

Contact Information:


Center for Research and Community Services (CRCS) Building Floor 7th, 
Jl. Ganesha No. 10 Bandung 40132, Indonesia,

Tel. +62-22-86010080,

Fax.: +62-22-86010051;

e-mail: jictra@lppm.itb.ac.id.