Rainfall-induced instability mechanism of high-altitude gravelly soil slopes and machine learning surrogate modeling

  • Jianli Jin orcid

    College of Water Conservancy and Civil Engineering, Xizang Agricultural and Animal Husbandry University, Linzhi 860000, China; Research Center of Civil, Hydraulic and Power Engineering of Xizang, Xizang Agricultural and Animal Husbandry University, Linzhi 860000, China; Key Laboratory of Transport Industry of Wind Resistant Technology for Bridge Structures, Tongji University, Shanghai 200092, China
  • Yuhao Zheng orcid

    College of Water Conservancy and Civil Engineering, Xizang Agricultural and Animal Husbandry University, Linzhi 860000, China; Research Center of Civil, Hydraulic and Power Engineering of Xizang, Xizang Agricultural and Animal Husbandry University, Linzhi 860000, China
  • Yongchen Zong orcid

    College of Water Conservancy and Civil Engineering, Xizang Agricultural and Animal Husbandry University, Linzhi 860000, China; Research Center of Civil, Hydraulic and Power Engineering of Xizang, Xizang Agricultural and Animal Husbandry University, Linzhi 860000, China
  • Baoliang Wang orcid

    Nuclear Industry Southwest Geotechnical Investigation & Design Institute Co., Ltd., Chengdu 610052, China
  • Qiang He orcid

    College of Water Conservancy and Civil Engineering, Xizang Agricultural and Animal Husbandry University, Linzhi 860000, China; Research Center of Civil, Hydraulic and Power Engineering of Xizang, Xizang Agricultural and Animal Husbandry University, Linzhi 860000, China; Key Laboratory of Transport Industry of Wind Resistant Technology for Bridge Structures, Tongji University, Shanghai 200092, China
Article ID: 4621
DOI: https://doi.org/10.59400/adecp4621
Keywords: high-altitude cold region slope; gravelly soil; rainfall-induced instability; fully coupled analysis; transient saturated zone; machine learning surrogate model

Abstract

This study investigates the distinctive instability mechanism of high-altitude gravelly-soil slopes driven by particle gradation, weak clayey characteristics and intense rainfall. Soil parameters were obtained from laboratory tests on a typical high-steep bedding gravelly-soil slope in the Parlung Zangbo Basin, southeastern Tibet. A fully coupled stress-pore-pressure finite-element model was built in ABAQUS to simulate seepage-deformation responses under six rainfall intensities and multiple durations. An infiltration threshold of 1.9 × 10−4 cm/s is determined. This threshold, a near-surface transient saturated zone, develops rapidly and impedes infiltration. Pore-water-pressure at the slope toe responds roughly 12 h earlier than at the crest. Every 10 cm increase in cumulative infiltration produces approximately 15 mm extra toe horizontal displacement (R2 = 0.93, 95% confidence interval (CI): 1.43–1.61). A 32-h deformation lag is observed post-rainfall, representing the period required for displacement to attain 90% of its stable value. Random-forest surrogate models for toe displacement and pore-water pressure are trained on 1,296 spatiotemporal finite-element samples, yielding test-set R2 > 0.96. Comparisons with Gaussian process regression, support vector regression and eXtreme Gradient Boosting (XGBoost) reveal that XGBoost achieves optimal accuracy (horizontal-displacement root mean square error (RMSE) = 0.42 mm), while random forest provides competitive performance (mean absolute percentage error (MAPE) = 7.8%) and better interpretability. A classification model detects transient saturated zones at 92.3% accuracy. This coupled numerical-simulation and machine-learning framework provides a new tool for rapid early-warning and parameter-sensitivity analysis of similar high-altitude rainfall-induced slope hazards.

Published
2026-08-28
How to Cite
Jin, J., Zheng, Y., Zong, Y., Wang, B., & He, Q. (2026). Rainfall-induced instability mechanism of high-altitude gravelly soil slopes and machine learning surrogate modeling. Advances in Differential Equations and Control Processes, 33(3). https://doi.org/10.59400/adecp4621
Issue
Vol. 33 No. 3 (2026): In Progress
Section
Articles

Copyright (c) 2026 Jianli Jin, Yuhao Zheng, Yongchen Zong, Baoliang Wang, Qiang He

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

[1]Nury AH, Sharma A, Mehrotra R, et al. Projected changes in the Tibetan Plateau snowpack resulting from rising global temperatures. Journal of Geophysical Research: Atmospheres. 2022; 127(6): e2021JD036201. doi: 10.1029/2021JD036201

[2]Sun Y, Liu S, Liu Y, et al. Effects of the interaction among climate, terrain and human activities on biodiversity on the Qinghai–Tibet Plateau. Science of the Total Environment. 2021; 794: 148497. doi: 10.1016/j.scitotenv.2021.148497

[3]Tian P, Lu H, Feng W, et al. Large decrease in streamflow and sediment load of Qinghai–Tibetan Plateau driven by future climate change: A case study in Lhasa River Basin. Catena. 2020; 187: 104340. doi: 10.1016/j.catena.2019.104340

[4]Tang L, Duan X, Kong F, et al. Influences of climate change on area variation of Qinghai Lake on Qinghai–Tibetan Plateau since 1980s. Scientific Reports. 2018; 8(1): 7331. doi: 10.1038/s41598-018-25683-3

[5]Kunwar RM, Subedi BP, Baral SR, et al. Ethnobotany of the Himalayas: The Nepal, Bhutanese, and Tibetan Himalayas. In: Kunwar RM, Sher H, Bussmann RW (editors). Ethnobotany of the Himalayas. Springer; 2021. pp. 65–103. doi: 10.1007/978-3-030-57408-6_5

[6]Yao M, Shao D, Lv C, et al. Evaluation of arable land suitability based on the suitability function—A case study of the Qinghai–Tibet Plateau. Science of the Total Environment. 2021; 787: 147414. doi: 10.1016/j.scitotenv.2021.147414

[7]Zhou MD, Lü TY, Zhang YS, et al. The geological structure background and the crustal structure in the northeastern margin of the Qinghai–Tibetan Plateau. Acta Seismologica Sinica. 2000; 13(6): 687–697. doi: 10.1007/s11589-000-0071-2

[8]Pan G, Wang L, Li R, et al. Tectonic evolution of the Qinghai–Tibet Plateau. Journal of Asian Earth Sciences. 2012; 53: 3–14. doi: 10.1016/j.jseaes.2011.12.018

[9]Wang F, Xu P, Wang C, et al. Application of a GIS-based slope unit method for landslide susceptibility mapping along the Longzi River, southeastern Tibetan Plateau, China. ISPRS International Journal of Geo-Information. 2017; 6(6): 172. doi: 10.3390/ijgi6060172

[10]Wu GQ, Xie YL, Wei J, et al. Water migration in subgrade soil under seasonal freeze–thaw cycles in an alpine meadow on the Qinghai–Tibet Plateau. Journal of Mountain Science. 2022; 19(6): 1767–1781. doi: 10.1007/s11629-021-7270-9

[11]Qu Y, Ni W, Niu F, et al. Shear properties and mechanism of freeze–thaw interface in unsaturated coarse-grained soil from Qinghai–Tibet Plateau. Advances in Civil Engineering. 2021; 2021(1): 6688724. doi: 10.1155/2021/6688724

[12]Zhang YZ, Zhu XD, Liu WL, et al. Macro- and mesoscopic experimental study of the effects of water content on moisture migration in coarse-grained fillings under freeze–thaw cycles and loads. Cold Regions Science and Technology. 2022; 196: 103491. doi: 10.1016/j.coldregions.2022.103491

[13]Zhang D, Li Q, Liu E, et al. Dynamic properties of frozen silty soils with different coarse-grained contents subjected to cyclic triaxial loading. Cold Regions Science and Technology. 2019; 157: 64–85. doi: 10.1016/j.coldregions.2018.09.010

[14]Zhao M, Xie Q, Ren X, et al. Experimental research on the deformation and failure characteristics of coarse-grained soil slopes in seasonal frozen region along Sichuan–Tibet Railway. IOP Conference Series: Earth and Environmental Science. 2020; 455(1): 012135. doi: 10.1088/1755-1315/455/1/012135

[15]Zhao W, Wang X, Xu Z, et al. Experimental study on natural evolution characteristics of coarse-grained soil slope in seasonal frozen soil region. Journal of Engineering Geology. 2021; 29(5): 1497–1506. doi: 10.13544/j.cnki.jeg.2020-174 (in Chinese)

[16]Chen L, Mei L, Zeng B, et al. Failure probability assessment of landslides triggered by earthquakes and rainfall: A case study in Yadong County, Tibet, China. Scientific Reports. 2020; 10: 16531. doi: 10.1038/s41598-020-73727-4

[17]Liu Y, Yao X, Gu Z, et al. Study of the automatic recognition of landslides by using InSAR images and the improved Mask R-CNN model in the Eastern Tibet Plateau. Remote Sensing. 2022; 14(14): 3362. doi: 10.3390/rs14143362

[18]Gong Y, Yao A, Li Y, et al. Classification and distribution of large-scale high-position landslides in southeastern edge of the Qinghai–Tibet Plateau, China. Environmental Earth Sciences. 2022; 81(11): 311. doi: 10.1007/s12665-022-10433-6

[19]Zeng Q, Yang Z, Shang Y, et al. Study on the bedrock-cover interface of the 102 landslide group on the Sichuan–Tibet Highway. Hydrogeology & Engineering Geology. 2008; 35(3): 1–6. (in Chinese)

[20]Yuan G, Shang Y, Lin D. Engineering geological characteristics and stability evaluation of accumulation slopes in the Palongzangbu River Basin. Journal of Engineering Geology. 2009; 17(2): 188–194. (in Chinese)

[21]Wei T. Stability and Rainfall Threshold Study of Typical Sandy Soil Slopes along the G318 Bolin Section [Master's Thesis]. Tibet University; 2022. (in Chinese)

[22]Li J, Wang C, Wang G, et al. Analysis of influencing factors and coupling strength of landslide development based on quantitative theory III. Chinese Journal of Rock Mechanics and Engineering. 2010; 29(6): 1206–1213. (in Chinese)

[23]Mei G. Review of slope stability analysis methods: From deterministic analysis to intelligent prediction. Journal of Engineering Research and Reports. 2026; 28(3): 189–197. doi: 10.9734/jerr/2026/v28i31830

[24]Ghimire S, Guéguen P, Giffard-Roisin S, et al. Testing machine learning models for seismic damage prediction at a regional scale using building-damage dataset compiled after the 2015 Gorkha Nepal earthquake. Earthquake Spectra. 2022; 38(4): 2970–2993. doi: 10.1177/87552930221106495

[25]Liu Y, Gong B, Su H. Study on soil-water characteristic curves of unsaturated soils. Geotechnical Investigation & Surveying. 2002; 30(3): 8–11. Available online: https://kns.cnki.net/kcms2/article/abstract?v=jXpGf_Tis3C-DFH2MQF6A9auVqmL5UQ_GTcDKB0R0yecvW2cSL1JEH4rvggHbFAW0J5M9ysX-pLIvHHZiS-291_ohDKiLE-jrkf7VGP4OhtDHE6srsXah4pL_gWTFati9z5J9krogXOb8HPZPcfmvwEbLCYiXiio&uniplatform=NZKPT (in Chinese)

[26]Ahmad H, Zhang Y, Alam M, et al. An efficient reliability assessment of coupled FDM-DEM slope stability using physics-informed feature-based surrogate machine learning techniques. Computers and Geotechnics. 2026; 196: 108185. doi: 10.1016/j.compgeo.2026.108185