BiLSTM for Predicting Post-Construction Subsoil Settlement under Embankment: Advancing Sustainable Infrastructure
Abstract
:1. Introduction
2. Methods
2.1. Traditional Approaches
2.2. Data-Driven Modeling
3. Field Observations
3.1. Site Overview and Monitoring Protocols
3.1.1. Case Study 1
3.1.2. Case Study 2
3.2. Data Preparation
4. BiLSTM Prediction Model
4.1. Model Construction
4.2. Model Evaluation
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Appendix A
3 Months after Construction | 4 Months after Construction | 5 Months after Construction | 6 Months after Construction | |||||
---|---|---|---|---|---|---|---|---|
(mm) | (%) | (mm) | (%) | (mm) | (%) | (mm) | (%) | |
Bi-LSTM models | 0.37 | 0.68 | −0.11 | 0.20 | 0.05 | 0.10 | −0.06 | 0.11 |
LSTM models | 0.45 | 0.83 | −0.32 | 0.58 | −0.21 | 0.42 | −0.09 | 0.17 |
Three-parameter curve-fitting | −0.59 | 1.10 | −0.79 | 1.48 | −0.39 | 0.72 | −0.23 | 0.43 |
Two-parameter curve-fitting 1 | −2.77 | 5.16 | −2.39 | 4.46 | −1.86 | 3.47 | −1.53 | 2.85 |
Two-parameter curve-fitting 2 | −4.85 | 9.05 | −4.23 | 7.90 | −3.45 | 6.44 | −2.93 | 5.47 |
3 Months after Construction | 4 Months after Construction | 5 Months after Construction | 6 Months after Construction | |||||
---|---|---|---|---|---|---|---|---|
(mm) | (%) | (mm) | (%) | (mm) | (%) | (mm) | (%) | |
Bi-LSTM models | −0.63 | 0.54 | 0.74 | 0.63 | 0.15 | 0.13 | −0.03 | 0.03 |
LSTM models | −0.52 | 0.45 | 1.2 | 1.02 | 0.54 | 0.47 | 0.11 | 0.10 |
Three-parameter curve-fitting | 0.32 | 0.27 | 1.57 | 1.33 | 1.17 | 0.99 | 0.26 | 0.22 |
Two-parameter curve-fitting 1 | −3.48 | 2.95 | −2.65 | 2.25 | −2.08 | 1.77 | −1.85 | 1.57 |
Two-parameter curve-fitting 2 | −5.52 | 4.68 | −4.66 | 3.95 | −3.94 | 3.34 | −3.50 | 2.97 |
3 Months after Construction | 4 Months after Construction | 5 Months after Construction | 6 Months after Construction | |||||
---|---|---|---|---|---|---|---|---|
(mm) | (%) | (mm) | (%) | (mm) | (%) | (mm) | ||
Bi-LSTM models | −2.28 | 1.83 | −2.85 | 2.28 | −1.64 | 1.31 | −0.49 | 0.40 |
LSTM models | −2.63 | 2.11 | −3.12 | 2.50 | −1.71 | 1.37 | 1.23 | 1.00 |
Three-parameter curve-fitting | −3.17 | 2.54 | −3.98 | 3.19 | −1.94 | 1.56 | 3.03 | 2.43 |
Two-parameter curve-fitting 1 | 9.51 | 7.63 | 5.89 | 4.72 | 3.80 | 3.05 | 4.61 | 3.70 |
Two-parameter curve-fitting 2 | 6.20 | 4.97 | 2.25 | 1.81 | 1.12 | 0.90 | 3.13 | 2.51 |
References
- Zhou, S.; Wang, B.; Shan, Y. Review of Research on High-Speed Railway Subgrade Settlement in Soft Soil Area. Railw. Eng. Sci. 2020, 28, 129–145. [Google Scholar] [CrossRef]
- Esen, A.F.; Woodward, P.K.; Laghrouche, O.; Connolly, D.P. Long-Term Performance Assessment of a Geosynthetic-Reinforced Railway Substructure. Sustainability 2023, 15, 9364. [Google Scholar] [CrossRef]
- Zhuang, Y.; Song, X.; Wang, K. Ground Reaction of Lightly Overconsolidated Subsoil in Reinforced Piled Embankment under Cyclic Loads. Sustainability 2023, 15, 619. [Google Scholar] [CrossRef]
- Wei, X.; Zhang, L.; Yang, H.Q.; Zhang, L.; Yao, Y.P. Machine Learning for Pore-Water Pressure Time-Series Prediction: Application of Recurrent Neural Networks. Geosci. Front. 2021, 12, 453–467. [Google Scholar] [CrossRef]
- Yu, F.; Li, S.; Dai, Z.; Li, J.; Chen, S. Stability Control of Staged Filling Construction on Soft Subsoil Using Hyperbolic Settlement Prediction Method: A Case Study of a Tidal Flat in China. Adv. Civ. Eng. 2020, 2020, 8899843. [Google Scholar] [CrossRef]
- Siddiqui, F.; Asce, S.M.; Sargent, P.; Montague, G. Data-Based Modeling Approaches for Short-Term Prediction of Embankment Settlement Using Magnetic Extensometer Time-Series Data. Int. J. Geomech. 2022, 22, 04021269. [Google Scholar] [CrossRef]
- Huang, C.; Li, Q.; Wu, S.; Li, J.; Xu, X. Application of the Richards Model for Settlement Prediction Based on a Bidirectional Difference-Weighted Least-Squares Method. Arab. J. Sci. Eng. 2018, 43, 5057–5065. [Google Scholar] [CrossRef]
- Park, H.I.; Kim, K.S.; Kim, H.Y. Field Performance of a Genetic Algorithm in the Settlement Prediction of a Thick Soft Clay Deposit in the Southern Part of the Korean Peninsula. Eng. Geol. 2015, 196, 150–157. [Google Scholar] [CrossRef]
- Chen, P.-Y.; Yu, H.-M. Foundation Settlement Prediction Based on a Novel NGM Model. Math. Probl. Eng. 2014, 2014, 242809. [Google Scholar] [CrossRef]
- Chai, J.C.; Miura, N.; Kirekawa, T.; Hino, T. Settlement Prediction for Soft Ground Improved by Columns. Proc. Inst. Civ. Eng.-Ground Improv. 2010, 163, 109–119. [Google Scholar] [CrossRef]
- Li, Z.; Luo, Z.; Wang, Q.; Du, J.; Lu, W.; Ning, D. A Three-Dimensional Fluid-Solid Model, Coupling High-Rise Building Load and Groundwater Abstraction, for Prediction of Regional Land Subsidence. Hydrogeol. J. 2019, 27, 1515–1526. [Google Scholar] [CrossRef]
- Shi, X.-Q.; Xue, Y.-Q.; Ye, S.-J.; Wu, J.-C.; Zhang, Y.; Yu, J. Characterization of Land Subsidence Induced by Groundwater Withdrawals in Su-Xi-Chang Area, China. Environ. Geol. 2006, 52, 27. [Google Scholar] [CrossRef]
- Michael, D.J. Limitations of Conventional Analysis of Consolidation Settlement. J. Geotech. Eng. 1993, 119, 1333–1359. [Google Scholar] [CrossRef]
- Mesri, G.; Choi, Y.K. Settlement Analysis of Embankments on Soft Clays. J. Geotech. Eng. 1985, 111, 441–464. [Google Scholar] [CrossRef]
- Raja, M.N.A.; Shukla, S.K. Predicting the Settlement of Geosynthetic-Reinforced Soil Foundations Using Evolutionary Artificial Intelligence Technique. Geotext. Geomembr. 2021, 49, 1280–1293. [Google Scholar] [CrossRef]
- Zhang, W.; Li, H.; Li, Y.; Liu, H.; Chen, Y.; Ding, X. Application of Deep Learning Algorithms in Geotechnical Engineering: A Short Critical Review. Artif. Intell. Rev. 2021, 54, 5633–5673. [Google Scholar] [CrossRef]
- Zhang, W.; Wu, C.; Li, Y.; Wang, L.; Samui, P. Assessment of Pile Drivability Using Random Forest Regression and Multivariate Adaptive Regression Splines. Georisk Assess. Manag. Risk Eng. Syst. Geohazards 2019, 15, 27–40. [Google Scholar] [CrossRef]
- Zhang, W.; Wu, C.; Zhong, H.; Li, Y.; Wang, L. Prediction of Undrained Shear Strength Using Extreme Gradient Boosting and Random Forest Based on Bayesian Optimization. Geosci. Front. 2021, 12, 469–477. [Google Scholar] [CrossRef]
- Goh, A.T.C.; Zhang, R.H.; Wang, W.; Wang, L.; Liu, H.L.; Zhang, W.G. Numerical Study of the Effects of Groundwater Drawdown on Ground Settlement for Excavation in Residual Soils. Acta Geotech. 2020, 15, 1259–1272. [Google Scholar] [CrossRef]
- Zhang, P.; Yin, Z.Y.; Jin, Y.F.; Sheil, B. Physics-Constrained Hierarchical Data-Driven Modelling Framework for Complex Path-Dependent Behaviour of Soils. Int. J. Numer. Anal. Methods Geomech. 2022, 46, 1831–1850. [Google Scholar] [CrossRef]
- Kirts, S.; Nam, B.H.; Panagopoulos, O.P.; Xanthopoulos, P. Settlement Prediction Using Support Vector Machine (SVM)-Based Compressibility Models: A Case Study. Int. J. Civ. Eng. 2019, 17, 1547–1557. [Google Scholar] [CrossRef]
- Zhang, G.; Xiang, X.; Tang, H. Time Series Prediction of Chimney Foundation Settlement by Neural Networks. Int. J. Geomech. 2011, 11, 154–158. [Google Scholar] [CrossRef]
- Zhu, M.; Li, S.; Wei, X.; Wang, P. Prediction and Stability Assessment of Soft Foundation Settlement of the Fishbone-Shaped Dike Near the Estuary of the Yangtze River Using Machine Learning Methods. Sustainability 2021, 13, 3744. [Google Scholar] [CrossRef]
- Wang, K.; Sun, W.C. A Multiscale Multi-Permeability Poroplasticity Model Linked by Recursive Homogenizations and Deep Learning. Comput. Methods Appl. Mech. Eng. 2018, 334, 337–380. [Google Scholar] [CrossRef]
- Zhang, P.; Yang, Y.; Yin, Z.-Y. BiLSTM-Based Soil–Structure Interface Modeling. Int. J. Geomech. 2021, 21, 04021096. [Google Scholar] [CrossRef]
- Yang, B.; Yin, K.; Lacasse, S.; Liu, Z. Time Series Analysis and Long Short-Term Memory Neural Network to Predict Landslide Displacement. Landslides 2019, 16, 677–694. [Google Scholar] [CrossRef]
- Li, L.; Gong, X.; Gan, X. Prediction of Maximum Ground Settlement Induced by Shield Tunneling Based on Recurrent Neural Network. China Civ. Eng. J. 2020, 51, 13–19. [Google Scholar]
- Zhang, N.; Zhou, A.; Pan, Y.; Shen, S.-L. Measurement and Prediction of Tunnelling-Induced Ground Settlement in Karst Region by Using Expanding Deep Learning Method. Measurement 2021, 183, 109700. [Google Scholar] [CrossRef]
- Siami-Namini, S.; Tavakoli, N.; Namin, A.S. The Performance of LSTM and BiLSTM in Forecasting Time Series. In Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA, 9–12 December 2019; pp. 3285–3292. [Google Scholar]
- Chen, D.Y.; Fan, H.G.; Shen, J.M.; Cheng, J.; Shen, X.L.; Chen, Z.P. Research of Curve Fitting Method on the Measured Settlement of Tanks. Procedia Eng. 2015, 130, 400–407. [Google Scholar] [CrossRef]
- NRA of China. TB 10001-2016 Code for Design of Railway Earth Structure; China Railway Publishing House Co., Ltd.: Beijing, China, 2017. [Google Scholar]
- Al-Shamrani, M.A. Applying the Hyperbolic Method and Cα/Cc Concept for Settlement Prediction of Complex Organic-Rich Soil Formations. Eng. Geol. 2005, 77, 17–34. [Google Scholar] [CrossRef]
- Sridharan, A.; Murthy, N.S.; Prakash, K. Rectangular Hyperbola Method of Consolidation Analysis. Geotechnique 1987, 37, 355–368. [Google Scholar] [CrossRef]
- Luo, Q.; Cheng, M.; Wang, T.; Zhu, J. Three-Parameter Power Function Model for Prediction of Post-Construction Settlement of Medium Compressive Soil Foundation. J. Beijing Jiaotong Univ. 2020, 44, 93–100. [Google Scholar]
- Wang, X.; Liu, X.; Chen, L.; Hu, H. Deep-Learning Damped Least Squares Method for Inverse Kinematics of Redundant Robots. Measurement 2021, 171, 108821. [Google Scholar] [CrossRef]
- Yin, J.; Ning, C.; Tang, T. Data-Driven Models for Train Control Dynamics in High-Speed Railways: LAG-LSTM for Train Trajectory Prediction. Inf. Sci. 2022, 600, 377–400. [Google Scholar] [CrossRef]
- Yang, M.; Wang, J. Adaptability of Financial Time Series Prediction Based on BiLSTM. Procedia Comput. Sci. 2022, 199, 18–25. [Google Scholar] [CrossRef]
- Zhu, Y.; Han, X. C2 Interpolation T-Splines. Comput. Methods Appl. Mech. Eng. 2020, 362, 112835. [Google Scholar] [CrossRef]
- Bergmeir, C.; Benítez, J.M. On the Use of Cross-Validation for Time Series Predictor Evaluation. Inf. Sci. 2012, 191, 192–213. [Google Scholar] [CrossRef]
- Zhang, P.; Wu, H.-N.; Chen, R.-P.; Chan, T.H.T. Hybrid Meta-Heuristic and Machine Learning Algorithms for Tunneling-Induced Settlement Prediction: A Comparative Study. Tunn. Undergr. Space Technol. 2020, 99, 103383. [Google Scholar] [CrossRef]
- Wang, S.; Wang, X.; Wang, S.; Wang, D. Bi-Directional Long Short-Term Memory Method Based on Attention Mechanism and Rolling Update for Short-Term Load Forecasting. Int. J. Electr. Power Energy Syst. 2019, 109, 470–479. [Google Scholar] [CrossRef]
- Li, G.; Wang, W.; Zhang, W.; Wang, Z.; Tu, H.; You, W. Grid Search Based Multi-Population Particle Swarm Optimization Algorithm for Multimodal Multi-Objective Optimization. Swarm Evol. Comput. 2021, 62, 100843. [Google Scholar] [CrossRef]
- Hou, S.; Liu, Y. Early Warning of Tunnel Collapse Based on Adam-Optimised Long Short-Term Memory Network and TBM Operation Parameters. Eng. Appl. Artif. Intell. 2022, 112, 104842. [Google Scholar] [CrossRef]
- Prechelt, L. Automatic Early Stopping Using Cross Validation: Quantifying the Criteria. Neural Netw. 1998, 11, 761–767. [Google Scholar] [CrossRef] [PubMed]
- Wang, Z.Z.; Xiao, C.; Goh, S.H.; Deng, M.-X. Metamodel-Based Reliability Analysis in Spatially Variable Soils Using Convolutional Neural Networks. J. Geotech. Geoenviron. Eng. 2021, 147, 04021003. [Google Scholar] [CrossRef]
- Chen, W.H.; Qu, S.J.; Lin, L.B.; Luo, Q.; Wang, T.F. Ensemble learning methods for shear strength prediction of fly ash-amended soils with lignin reinforcement. J. Mater. Civ. Eng. 2023, 35, 04023022. [Google Scholar] [CrossRef]
- Chen, W.H.; Luo, Q.; Liu, J.K.; Wang, T.F.; Wang, L.Y. Modeling of frozen soil-structure interface shear behavior by supervised deep learning. Cold Reg. Sci. Technol. 2022, 200, 103589. [Google Scholar] [CrossRef]
- Wang, T.; Ma, H.; Liu, J.; Luo, Q.; Wang, Q.; Zhan, Y. Assessing frost heave susceptibility of gravelly soils based on multivariate adaptive regression splines model. Cold Reg. Sci. Technol. 2021, 181, 103182. [Google Scholar] [CrossRef]
- Wang, T.F.; Chen, W.H.; Li, T.F.; Connolly, D.P.; Luo, Q.; Liu, K.W.; Zhang, W.S. Surrogate-assisted uncertainty modeling of embankment settlement. Comput. Geotech. 2023, 159, 105498. [Google Scholar] [CrossRef]
- Shi, C.; Fan, Z.; Connolly, D.P.; Jing, G.; Markine, V.; Guo, Y. Railway ballast performance: Recent advances in the understanding of geometry, distribution and degradation. Transp. Geotech. 2023, 41, 101042. [Google Scholar] [CrossRef]
- Chen, Y.; Tan, L.; Xiao, N.; Liu, K.; Jia, P.; Zhang, W. The hydro-mechanical characteristics and micro-structure of loess enhanced by microbially induced carbonate precipitation. Geomech. Energy Environ. 2023, 34, 100469. [Google Scholar] [CrossRef]
Sections | ||||
---|---|---|---|---|
A | 0.93 | 0.58 | 0.97 | 0.71 |
B | 0.90 | 0.55 | 0.96 | 0.71 |
C | 0.89 | 0.52 | 0.98 | 0.8 |
Configuration | Value |
---|---|
Architecture | 4-64(ReLU)-64(ReLU)-1(linear) |
Optimizer | Adam |
Batch size | 20 |
Epoch | 1500 (early stopping applied) |
Learning rate | 0.0001 |
Validation frequency | 1 |
Timestep | 5 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, L.; Li, T.; Wang, P.; Liu, Z.; Zhang, Q. BiLSTM for Predicting Post-Construction Subsoil Settlement under Embankment: Advancing Sustainable Infrastructure. Sustainability 2023, 15, 14708. https://doi.org/10.3390/su152014708
Wang L, Li T, Wang P, Liu Z, Zhang Q. BiLSTM for Predicting Post-Construction Subsoil Settlement under Embankment: Advancing Sustainable Infrastructure. Sustainability. 2023; 15(20):14708. https://doi.org/10.3390/su152014708
Chicago/Turabian StyleWang, Liyang, Taifeng Li, Pengcheng Wang, Zhenyu Liu, and Qianli Zhang. 2023. "BiLSTM for Predicting Post-Construction Subsoil Settlement under Embankment: Advancing Sustainable Infrastructure" Sustainability 15, no. 20: 14708. https://doi.org/10.3390/su152014708