Soft rock within embankments is prone to continuous particle breakage, migration, and rearrangement due to rain infiltration and traffic loads, leading to uneven subsidence. subsidence deformation is a key indicator of embankment stability and safety, making accurate prediction essential for preventing road defects and instability. However, traditional single prediction models often lack generalizability and are not suitable for varying conditions in embankment engineering. This study collected and analyzed subsidence data from 18 soft rock embankments in highways and railways, which exhibited distinct subsidence patterns, including wave-like, broken line, and parabolic trends. Based on these data, using the Stacked Generalization (SG) ensemble algorithm, an SG fusion model predicting soft rock embankment subsidence was developed combining the prediction models from three different fields. The model avoided the hyperparameter tuning process, allowing for direct application in engineering practices. Besides, a Blocked K-Fold training strategy was employed to improve robustness. In comparison with traditional models, under conditions of limited monitoring data, the SG fusion model demonstrated significantly lower error rates and higher prediction accuracy across various projects. The findings suggest that the SG model is more applicable and robust for predicting soft rock embankment subsidence. This research provides theoretical and technical support for evaluating the service performance and post-construction maintenance of soft rock embankments.
ZENGL, YUH C, GAOQ F,et al .Road performance and modification mechanisms of disintegrated carbonaceous mudstone modified with gum Arabic[J]. China Journal of Highway and Transport,2023,36(10): 42-54.(in Chinese)
FUH Y, YANGH T, ZENGL,et al .Study on compaction characteristics and particle breakage of carbonaceous mudstone fill material[J].China Civil Engineering Journal,2025,58(3):113-124.(in Chinese)
[5]
RAHMANIH, PANAHA K. Influence of particle size on particle breakage and shear strength of weak rockfill[J]. Bulletin of Engineering Geology and the Environment, 2021, 80(1):473-489.
YANGG L, DUANJ Y, YANGX, et al. Vibration characteristics of subgrade in expansive soil area under simulated rainfall and natural conditions[J]. Journal of Zhejiang University (Engineering Science), 2016,50(12): 2319-2327.(in Chinese)
SUQ, ZHANGQ, ZHANGZ Y,et al .Settlement prediction of high-filled embankment based on collaborative denoising and IGWO-SVR[J]. Journal of the China Railway Society, 2024, 46(3): 87-98.(in Chinese)
[10]
WANGH Y, SHEH, XUJ, et al. A three-point hyperbolic combination model for the settlement prediction of subgrade filled with construction and demolition waste[J]. Materials, 2020, 13(8): 1959.
[11]
ZENGL, LIUC, WUW Z .A novel discrete GM(2,1) model with a polynomial term for forecasting electricity consumption[J].Electric Power Systems Research,2023,214:108926.
DINGJ W, WEIX, GAOP J,et al .Prediction of settlement of soft soil subgrade during operation based on GA-BP neural network[J]. Journal of Southeast University (Natural Science Edition), 2023, 53(4): 585-591.(in Chinese)
[14]
BISCHLB, LANGM, KOTTHOFFL, et al. Mlr: machine learning in R[J]. Journal of Machine Learning Research, 2016, 17(170): 1-5.
MAG, LIUK. Prediction of compressive strength of CFRP-confined concrete columns based on BP neural network[J].Journal of Hunan University (Natural Sciences),2021,48(9):88-97.(in Chinese)
[17]
BUIK T, TORRESJ F, GUTIÉRREZ-AVILÉSD, et al .Deformation forecasting of a hydropower dam by hybridizing a long short-term memory deep learning network with the coronavirus optimization algorithm[J]. Computer-Aided Civil and Infrastruc- ture Engineering, 2022, 37(11): 1368-1386.
LIUK H, ZHENGJ K, XIEW L,et al .Mixture design method of recycled aggregate concrete based on machine learning[J].Journal of Hunan University (Natural Sciences), 2023, 50(9):88-96.(in Chinese)
HEN, XIK, GAOF,et al .Predictive control parameter tuning algorithm based on FCM-ELM-BBPS[J].Journal of Hunan University (Natural Sciences),2023,50(12):168-177.(in Chinese)
[22]
SUY, WANGX Q, FUY Y, et al. Research on surface settlement prediction based on the combination prediction model of S-shaped growth curves[J]. Geosystem Engineering, 2018, 21(4): 236-241.
ZHAOY H, WANGJ X, ZHANGL H,et al .Study on weighted combination model based on IOWHA operator in prediction of subgrade settlement[J]. Journal of Railway Science and Engineering, 2018, 15(10): 2529-2534.(in Chinese)
LIUG X, CAOH Y, LIY G. Application of grey and Gompertz combination model in settlement prediction of soft soil subgrade[J]. China Sciencepaper, 2016, 11(13):1488-1491.(in Chinese)
XUM M, XUB, ZENGH Z .Research on weighted combination prediction method for subgrade settlement[J].Journal of Railway Science and Engineering,2016,13(3):463-468.(in Chinese)
[29]
WOLPERTD H .Stacked generalization[J].Neural Networks,1992,5(2): 241-259.
CHANGZ, CHENGX Q, ZHANGL J,et al .Prediction of settlement of soft rock high-filled embankment based on three-point modified curve model[J]. Journal of Highway and Transportation Research and Development,2022,39(5):33-40.(in Chinese)
[32]
LIUB, JIANGX G .Consolidation and deformation characteristics of soft rock foundation in hydrological wetland environment[J].Earth Sciences Research Journal,2020,24(2):183-190.
CHENX L, WANGY H, ZHOUT Y,et al .Long-term dynamic stability analysis on argillaceous siltstone physical improved soil subgrade of high-speed railway[J].Journal of Central South University (Science and Technology), 2012, 43(9): 3619-3624.(in Chinese)
ZHAOM H, LIUX M, SUY H. Experimental studies on engineering properties of red bed material containing slaking rock[J]. Chinese Journal of Geotechnical Engineering, 2005, 27(6):667-671.(in Chinese)
LIAOC C, LIUX X, ZHOUQ .The study on deformation property of carbon shale slope in highway[J].Western China Communications Science & Technology,2011(5):37-41.(in Chinese)
[39]
赵丽娜 .泥质软岩弃渣填筑路堤沉降分析[J].山东交通科技,2021(6):96-97.
[40]
ZHAOL N .Settlement analysis of embankment filled with muddy soft rock spoil[J]. Shandong Transportation Science and Techno- logy, 2021(6):96-97.(in Chinese)
[41]
鞠兴华 .高速公路泥质软岩路堤沉降特性研究[D].西安:长安大学,2019.
[42]
JUX H .Study on settlement characteristics of muddy soft rock embankment of expressway[D]. Xi’an:Chang’an University,2019.(in Chinese)
[43]
杨梁 .衡桂高速红砂岩路基填筑技术及沉降变形研究[D].长沙:长沙理工大学,2013.
[44]
YANGL .Study on filling technology and settlement deformation of red sandstone subgrade in Henggui expressway[D].Changsha:Changsha University of Science & Technology,2013.(in Chinese)
[45]
张哲 .柞小高速公路变质软岩路堤沉降分析及工后沉降预测[D].西安:长安大学,2010.
[46]
ZHANGZ .Settlement analysis and post-construction settlement prediction of metamorphic soft rock embankment in Zhaxiao Expressway[D].Xi’an:Chang’an University,2010.(in Chinese)
FENGZ J, CAOW H .Observation and numerical analysis of settlement of high filled embankment on soft subgrade[J].Journal of Lanzhou University of Technology,2013,39(2):126-129.(in Chinese)
[49]
杨凌云 .秦岭山区风化变质软岩作为高速公路路堤填料的研究及应用[D].西安:长安大学,2011.
[50]
YANGL Y .Research and application of weathered and metamorphic soft rock as expressway embankment filler in Qinling Mountain area[D].Xi’an:Chang’an University,2011.(in Chinese)
[51]
卿三惠 .红层软岩地区高速铁路软基路堤沉降控制研究[D].成都:成都理工大学,2007.
[52]
QINGS H .Study on settlement control of soft foundation embankment of high-speed railway in red bed soft rock area[D].Chengdu:Chengdu University of Technology,2007.(in Chinese)
[53]
郑良飞 .恩施地区软岩填料的路用性能研究[D].西安:长安大学, 2008.
[54]
ZHENGL F .Study on road performance of soft rock filler in Enshi area[D].Xi’an:Chang’an University,2008.(in Chinese)
[55]
袁伟 .软岩填料在高速铁路中的适用性分析与沉降研究[D].长沙:中南大学, 2009.
[56]
YUANW .Applicability analysis and settlement study of soft rock filler in high-speed railway[D].Changsha:Central South University,2009.(in Chinese)
CAOZ Y. Study on road performance and vibration compaction technology of metamorphic soft rock embankment filler in Qinba Mountain area[D]. Xi’an:Chang’an University,2013.(in Chinese)
[59]
王意明 .炭质页岩路堤沉降特性及填筑技术研究[D].长沙:长沙理工大学,2011.
[60]
WANGY M .Study on settlement characteristics and filling technology of carbonaceous shale embankment[D]. Changsha:Changsha University of Science & Technology,2011.(in Chinese)
ZHAOZ A, ZHANGS S, YANGX H. Analysis on the construction method of mudstone waste slag for subgrade filler and its stability for Chengxian-Wudu expressway[J]. Highway,2014, 59(9): 48-51.(in Chinese)
[63]
RENY Y, WANGJ .Analysis of settling character and prediction result of the red sandstone dynamic compaction embankment[J].Applied Mechanics and Materials,2014,587/588/589:1084-1090.
[64]
CERQUEIRAV, TORGOL, MOZETIČI .Evaluating time series forecasting models:an empirical study on performance estimation methods[J].Machine Learning,2020,109(11):1997-2028.