Skip to main content
SpringerLink
Log in

Establishing a shallow-landslide prediction method by using machine-learning techniques based on the physics-based calculation of soil slope stability

  • Technical Note
  • Published:
Landslides Aims and scope Submit manuscript

Abstract

This study intends to investigate the influence of the rainfall condition and the stability state of the soil layer on the possible time of occurring shallow landslides by building a prediction model which combines a neural network algorithm with a clustering method based on geomorphological characteristics. Therefore, the periods of shallow landslides for different local areas with various geomorphological features in a watershed can be determined. A classification method according to ground slope, soil characteristic, and drainage area is advocated to divide the watershed into multiple local regions before training the landslide prediction model. In this study, to understand the temporal and spatial variation of unstable areas, a seepage flow model and a slope stability model are jointly adopted. The physical meaning of the machine-learning-based model for predicting the duration and the start time of shallow landslides can be preserved because the model input, namely, the dynamic cumulative unstable area, is provided by conducting the theoretical seepage flow model and analyzing the soil slope stability. The proposed approach can effectively determine the periods when shallow landslides are likely to occur for different regions suggested in this study. Present results also indicate that only some specified regions, prone to induce a significant change of total unstable grids during rains, are required to be tracked and analyzed by the proposed prediction model. According to the results of analyzing the predicted errors of the shallow landslide period (Ps) and the initial time of occurring landslide (Ts), the mean relative error can be controlled within 5.19%, and the R2 can be consistently larger than 0.889 overall. Research findings also demonstrate that the predicted periods in which shallow landslides may occur can predict approximately 82.2% of the observed landslide events in the study watershed.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

References

  • Bordoni M, Meisina C, Valentino R, Luc N, Bittelli M, Chersich S (2015) Hydrological factors affecting rainfall-induced shallow landslides: from the field monitoring to a simplified slope stability analysis. Eng Geol 193:19–37

    Article  Google Scholar 

  • Brooks RH, Corey AT (1964) Hydraulic properties of porous media. Colorado State University (Fort Collins). Hydrol Paper 3

  • Ester M, Kriegel H-P, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD-96). AAAI Press 226–231

  • Fredlund DG, Rahardjo H (1993) Soil mechanics for unsaturated soils. John Wiley & Sons, New York, NY, USA

    Book  Google Scholar 

  • Gariano SL, Melillo M, Peruccacci S, Brunetti MT (2020) How much does the rainfall temporal resolution affect rainfall thresholds for landslide triggering? Nat Hazards 100:655–670

    Article  Google Scholar 

  • Green WH, Ampt GA (1991) Studies on soil physics: part I. The flow of air and water through soils. J Agric Sci 4:1–24

    Google Scholar 

  • Ho J-Y, Lee KT (2017) Performance evaluation of a physically based model for shallow landslide prediction. Landslides 14(3):961–980

    Article  Google Scholar 

  • Ho JY, Lee KT, Chang TC, Wang ZY, Liao YH (2012) Influences of spatial distribution of soil thickness on shallow landslide prediction. Eng Geol 124:38–46

    Article  Google Scholar 

  • Johnson KA, Sitar N (1990) Hydrologic conditions leading to debris-flow initiations. Can Geotech J 27:789–801

    Article  Google Scholar 

  • Kavzoglu T, Colkesen I, Sahin EK (2019) Machine learning techniques in landslide susceptibility mapping: a survey and a case study. Landslides: Theory Pract Model 283–301

  • Koloski JW, Schwarz SD, Tubbs DW (1989) Geotechnical properties of geologic materials. Engineering Geology in Washington. Washington Div Geol Earth Res Bull 78(1)

  • Lee KT, Ho J-Y (2009) Prediction of landslide occurrence based on slope-instability analysis and hydrological model simulation. J Hydrol 375:489–497

    Article  Google Scholar 

  • Matsushi Y, Hattanji T, Matsukura Y (2006) Mechanisms of shallow landslides on soil-mantled hillslopes with permeable and impermeable bedrocks in the Boso Peninsula. Japan Geomorphology 76(1–2):92–108

    Article  Google Scholar 

  • Merghadi A, Yunus AP, Dou J, Whiteley J, ThaiPham B, Bui DT, Abderrahmane B (2020) Machine learning methods for landslide susceptibility studies: a comparative overview of algorithm performance. Earth-Sci Rev 207:103225

  • Montrasio L, Valentino R (2008) A model for triggering mechanisms of shallow landslides. Nat Hazard 8(5):1149–1159

    Article  Google Scholar 

  • Persichillo MG, Bordoni M, Meisina C (2017) The role of land use changes in the distribution of shallow landslides. Sci Total Environ 574:924–937

    Article  Google Scholar 

  • Phillips C, Hales T, Smith H, Basher L (2021) Shallow landslides and vegetation at the catchment scale: a perspective. Ecol Eng 173:106436

    Article  Google Scholar 

  • Ran Q, Hong Y, Li W, Gao J (2018) A modelling study of rainfall-induced shallow landslide mechanisms under different rainfall characteristics. J Hydrol 563:790–801

    Article  Google Scholar 

  • Richards LA (1931) Capillary conduction of liquids through porous mediums. Physics 1:318–333

    Article  Google Scholar 

  • Rickli C, Graf F (2009) Effects of forests on shallow landslides - case studies in Switzerland. Forest Snow and Landscape Research 82(1):33–44

    Google Scholar 

  • Salvatici T, Tofani V, Rossi G, D’Ambrosio M, Stefanelli CT, Masi EB, Rosi A, Pazzi V, Vannocci P, Petrolo M, Catani F, Ratto S, Stevenin H, Casagli N (2018) Application of a physically based model to forecast shallow landslides at a regional scale. Nat Hazard 18:1919–1935

    Article  Google Scholar 

  • Schmidhuber J, Hochreiter S (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  • Selby MJ (1993) Hillslope materials and processes. Oxford University Press, Oxford

    Google Scholar 

  • Sidle RC, Bogaard TA (2016) Dynamic earth system and ecological controls of rainfall-initiated landslides. Earth Sci Rev 159:275–291

    Article  Google Scholar 

  • Sörensen R, Zinko U, Seibert J (2006) On the calculation of the topographic wetness index: evaluation of different methods based on field observations. Hydrol Earth Syst Sci 10(1):101–112

    Article  Google Scholar 

  • Tehrani FS, Calvello M, Liu Z, Zhang L, Lacasse S (2022) Machine learning and landslide studies: recent advances and applications. Nat Hazards 114(2):1197–1245

    Article  Google Scholar 

  • Tofani V, Dapporto S, Vannocci P, Casagli N (2006) Infiltration, seepage and slope instability mechanisms during the 20–21 November 2000 rainstorm in Tuscany, central Italy. Nat Hazard 6:1025–1033

    Article  Google Scholar 

  • Wieczorek GF (1996) Landslide triggering mechanisms, in: Landslides Investigation and Mitigation, edited by: Turner, A.K. and Schuster, R.L., special report 247, National Academy Press, Washington D.C

Download references

Author information

Authors and Affiliations

  1. Department of Harbor and River Engineering, National Taiwan Ocean University, Keelung City, Taiwan

    Pin-Chun Huang

Authors
  1. Pin-Chun Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pin-Chun Huang.

Ethics declarations

Competing interests

The author declares no competing interests.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Huang, PC. Establishing a shallow-landslide prediction method by using machine-learning techniques based on the physics-based calculation of soil slope stability. Landslides 20, 2741–2756 (2023). https://doi.org/10.1007/s10346-023-02139-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10346-023-02139-y

Keywords

Search

Navigation