Abstract
Natural terrain landslides are mainly triggered by rainstorms in Hong Kong, which pose great threats to life and property. To mitigate landslide risk, building a prediction model which could provide information on both spatial and temporal probabilities of landslide occurrence is essential but challenging. In this paper, real-time rainfall conditions are incorporated into landslide prediction through a unique rainstorm-based database of reported landslides. Other landslide controlling factors related to topography, geology, and land cover are also considered. Five machine learning methods, including logistic regression, random forest, adaboost tree, support vector machine, and multilayer perceptron, are utilized and compared. Validated against historical rainstorms, the machine learning powered landslide prediction model could reasonably forecast the occurrence of landslides in a spatiotemporal context. Moreover, the effects of different rainstorm characteristics in terms of distinct rainfall spatial distribution and intensity on landslide susceptibility could also be captured by this model. For the landslide controlling factors investigated, rolling rainfall factors are proven to play a more important role than antecedent rainfall factors for landslide prediction. Among the five machine learning methods, the random forest model yields the most promising results in terms of all performance indicators (i.e., classification accuracy, recall, precision, area under curve, and overall accuracy).
Similar content being viewed by others
References
Abbas S, Nichol JE, Wong MS (2021) Trends in vegetation productivity related to climate change in China’s Pearl River Delta. PLoS One 16:e0245467. https://doi.org/10.1371/journal.pone.0245467
AECOM, Lin B (2015) 24-hour probable maximum precipitation updating study. GEO Report No. 314. Geotechnical Engineering Office, Hong Kong Special Administration Region
Ayalew L, Yamagishi H (2005) The application of GIS-based logistic regression for landslide susceptibility mapping in the Kakuda-Yahiko Mountains, central Japan. Geomorphology 65(1-2):15–31
Baum RL, Godt JW (2010) Early warning of rainfall-induced shallow landslides and debris flows in the USA. Landslides 7(3):259–272
Baum RL, Savage WZ, Godt JW (2008) TRIGRS: a Fortran program for transient rainfall infiltration and grid-based regional slope-stability analysis, version 2.0. Reston VA: US Geological Survey
Breiman L (2001) Random forests. Mach Learning 45(1):5–32
Budimir MEA, Atkinson PM, Lewis HG (2015) A systematic review of landslide probability mapping using logistic regression. Landslides 12(3):419–436
Bui DT, Pradhan B, Lofman O, Revhaug I, Dick OB (2012) Landslide susceptibility assessment in the Hoa Binh province of Vietnam: a comparison of the Levenberg–Marquardt and Bayesian regularized neural networks. Geomorphology 171:12–29
Chan RKS, Pang PLR., Pun WK (2003) Recent developments in the landslip warning system in Hong Kong. In Proceedings of the 14th Southeast Asian Geotechnical Conference. Balkema, Lisse, the Netherlands, pp 137-151
Chen W, Xie X, Wang J, Pradhan B, Hong H, Bui DT, Zhou D, Ma J (2017) A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility. Catena 151:147–160
Corder GW, Foreman DI (2014) Nonparametric statistics: a step-by-step approach. Wiley, Hoboken
Cortes C, Vapnik V (1995) Support-vector networks. Machine Learning 20(3):273–297
Dai FC, Lee CF (2002) Landslide characteristics and slope instability modeling using GIS, Lantau Island, Hong Kong. Geomorphology 42(3-4):213–228
Dai FC, Lee CF (2003) A spatiotemporal probabilistic modelling of storm-induced shallow landsliding using aerial photographs and logistic regression. Earth Surf Process Landf 28(5):527–545
Dai FC, Lee CF, Ngai YY (2002) Landslide risk assessment and management: an overview. Eng Geol 64(1):65–87
Fowler J, Cohen L, Jarvis P (2013) Practical statistics for field biology. Wiley, Hoboken
Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 28(2):337–407
Gao L, Zhang LM, Lu M (2017) Characterizing the spatial variations and correlations of large rainstorms for landslide study. Hydrol Earth Syst Sci 21(9):4573–4589
Gao L, Zhang LM, Cheung RWM (2018) Relationships between natural terrain landslide magnitudes and triggering rainfall based on a large landslide inventory in Hong Kong. Landslides 15(4):727–740
Garg A, Tai K (2013) Comparison of statistical and machine learning methods in modelling of data with multicollinearity. Int J Model Identif Control 18(4):295–312
Geotechnical Engineering Office (GEO) (2020a). Publications: GEO Reports. https://www.cedd.gov.hk/eng/publications/geo/geo-reports/index.html
Geotechnical Engineering Office (GEO) (2020b). Landslide potential index. Information Note 15/2020, Civil Engineering and Development Department
Gholamy A, Kreinovich V, Kosheleva O (2018) Why 70/30 or 80/20 relation between training and testing sets: a pedagogical explanation. Departmental Technical Reports (CS). 1209
Guzzetti F, Peruccacci S, Rossi M, Stark CP (2008) The rainfall intensity–duration control of shallow landslides and debris flows: an update. Landslides 5(1):3–17
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction. Springer, New York
Hencher SR, Lee SG (2010) Landslide mechanisms in Hong Kong. Geological Society, London, Engineering Geology Special Publications 23(1): 77-103
Hong H, Ilia I, Tsangaratos P, Chen W, Xu C (2017) A hybrid fuzzy weight of evidence method in landslide susceptibility analysis on the Wuyuan area, China. Geomorphology 290:1–16
Hong H, Liu J, Bui DT, Pradhan B, Acharya TD, Pham BT, Zhu A, Chen W, Ahmad BB (2018) Landslide susceptibility mapping using J48 Decision Tree with AdaBoost, Bagging and Rotation Forest ensembles in the Guangchang area (China). Catena 163:399–413
Huang F, Yin K, Huang J, Gui L, Wang P (2017) Landslide susceptibility mapping based on self-organizing-map network and extreme learning machine. Eng Geol 223:11–22
James G, Witten D, Hastie T, Tibshirani R (2013) An introduction to statistical learning. Springer, New York
Kavzoglu T, Sahin EK, Colkesen I (2014) Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression. Landslides 11(3):425–439
Ko FW (2005) Correlation between rainfall and natural terrain landslide occurrence in Hong Kong. GEO Report No. 168. Geotechnical Engineering Office, Hong Kong Special Administration Region
Ko FW, Lo FL (2016) Rainfall-based landslide susceptibility analysis for natural terrain in Hong Kong-A direct stock-taking approach. Eng Geol 215:95–107
Kong HSW, Ng AFH (2006) Factual report on Hong Kong rainfall and landslides in 2005. GEO Report No. 223, Geotechnical Engineering Office, Hong Kong Special Administration Region
Kong VWW, Kwan JSH, Pun WK (2020) Hong Kong’s landslip warning system—40 years of progress. Landslides:1–11
Lam CC, Leung YK (1994) Extreme rainfall statistics and design rainstorm profiles at selected locations in Hong Kong. HKO Technical Note No. 86, Hong Kong Observatory, Hong Kong Special Administration Region
Leung JCW, Lam HWK, Chan HW (2011) Factual report on Hong Kong rainfall and landslides in 2010. GEO Report No. 296, Geotechnical Engineering Office, Hong Kong Special Administration Region
Liao Z, Hong Y, Kirschbaum D, Liu C (2012) Assessment of shallow landslides from Hurricane Mitch in central America using a physically based model. Environ Earth Sci 66(6):1697–1705
Liu Z, Gilbert G, Cepeda JM, Lysdahl AOK, Piciullo L, Hefre H, Lacasse S (2020) Modelling of shallow landslides with machine learning algorithms. Geosci Front 12:385–393. https://doi.org/10.1016/j.gsf.2020.04.014
Montrasio L, Valentino R (2007) Experimental analysis and modelling of shallow landslides. Landslides 4(3):291–296
Ng A (2017) Machine learning yearning. http://www.mlyearning.org/
Ng CWW, Shi Q (1998) Influence of rainfall intensity and duration on slope stability in unsaturated soils. Q J Eng Geol Hydrogeol 31(2):105–113
Ng CWW, Choi CE, Song D, Kwan JHS, Koo RCH, Shiu HYK, Ho KKS (2015) Physical modeling of baffles influence on landslide debris mobility. Landslides 12(1):1–18
Ng CWW, Song D, Choi CE, Liu LHD, Kwan JSH, Koo RCH, Pun WK (2017) Impact mechanisms of granular and viscous flows on rigid and flexible barriers. Can Geotech J 54(2):188–206
Ng CWW, Liu H, Choi CE, Kwan JSH, Pun WK (2020) Impact dynamics of boulder-enriched debris flow on a rigid barrier. J Geotech Geoenviron Eng, ASCE (accepted)
Osanai N, Shimizu T, Kuramoto K, Kojima S, Noro T (2010) Japanese early-warning for debris flows and slope failures using rainfall indices with Radial Basis Function Network. Landslides 7(3):325–338
Peng L, Niu R, Huang B, Wu X, Zhao Y, Ye R (2014) Landslide susceptibility mapping based on rough set theory and support vector machines: a case of the Three Gorges area, China. Geomorphology 204:287–301
Pradhan AMS, Lee SR, Kim YT (2019) A shallow slide prediction model combining rainfall threshold warnings and shallow slide susceptibility in Busan, Korea. Landslides 16(3):647–659
Quinlan JR (1993) C4.5 Programs for machine learning. Morgan Kaufmann Publishers
Rosi A, Segoni S, Canavesi V, Monni A, Gallucci A, Casagli N (2021) Definition of 3D rainfall thresholds to increase operative landslide early warning system performances. Landslides 18:1045–1057
Segoni S, Battistini A, Rossi G, Rosi A, Lagomarsino D, Catani F, Moretti S, Casagli N (2015) An operational landslide early warning system at regional scale based on space-time-variable rainfall thresholds. Nat Hazards Earth Syst Sci 15(4):853–861
Segoni S, Tofani V, Rosi A, Catani F, Casagli N (2018) Combination of rainfall thresholds and susceptibility maps for dynamic landslide hazard assessment at regional scale. Front Earth Sci 6:85. https://doi.org/10.3389/feart.2018.00085
Song D, Ng CWW, Choi CE, Zhou GG, Kwan JSH, Koo RCH (2017) Influence of debris flow solid fraction on rigid barrier impact. Can Geotech J 54(10):1421–1434
Song D, Choi CE, Ng CWW, Zhou GGD (2018) Geophysical flows impacting a flexible barrier: effects of solid-fluid interaction. Landslides 15(1):99–110
Sun D, Wen H, Wang D, Xu J (2020) A random forest model of landslide susceptibility mapping based on hyperparameter optimization using Bayes algorithm. Geomorphology. 362:107201. https://doi.org/10.1016/j.geomorph.2020.107201
Thiebes B, Glade T (2016) Landslide early warning systems—fundamental concepts and innovative applications. In: Aversa S, Cascini L, Picarelli L, Scavia C (eds) Landslides and engineered slopes: experience, theory and practice. Proceedings of the 12th International Symposium on Landslides, Napoli, pp 12-19
Tsangaratos P, Ilia I (2016) Landslide susceptibility mapping using a modified decision tree classifier in the Xanthi Perfection, Greece. Landslides 13(2):305–320
Wang H, Zhang LM, Yin K, Luo H, Li J (2020) Landslide identification using machine learning. Geosci Front 12:351–364. https://doi.org/10.1016/j.gsf.2020.02.012
Wu Y, Ke Y, Chen Z, Liang S, Zhao H, Hong H (2020) Application of alternating decision tree with AdaBoost and bagging ensembles for landslide susceptibility mapping. Catena 187:104396
Yao X, Tham LG, Dai FC (2008) Landslide susceptibility mapping based on support vector machine: a case study on natural slopes of Hong Kong, China. Geomorphology 101(4):572–582
Yi Y, Zhang Z, Zhang W, Jia H, Zhang J (2020) Landslide susceptibility mapping using multiscale sampling strategy and convolutional neural network: a case study in Jiuzhaigou region. Catena 195:104851
Acknowledgements
The authors would like to acknowledge the Geotechnical Engineering Office of Civil Engineering and Development Department of HKSAR for providing the landslide inventory data.
Funding
The Research Grants Council (RGC) of the Hong Kong Special Administrative Region (HKSAR) provided the research grant (Project No. AoE/E-603/18). The second author received the support of the Hong Kong Ph.D. Fellowship Scheme (HKPFS) provided by the RGC of the HKSAR.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ng, C.W.W., Yang, B., Liu, Z.Q. et al. Spatiotemporal modelling of rainfall-induced landslides using machine learning. Landslides 18, 2499–2514 (2021). https://doi.org/10.1007/s10346-021-01662-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10346-021-01662-0