Skip to main content
SpringerLink
Log in

A comparative study of random forests and multiple linear regression in the prediction of landslide velocity

  • Original Paper
  • Published:
Landslides Aims and scope Submit manuscript

Abstract

The monitoring of landslides has a practical application for the prevention of hazards, especially in the case of large deep-seated landslides. Monitoring data are necessary to understand the relationships between movement and triggers, to predict movement, and to establish an early warning system. This paper compares two phenomenological models for the prediction of the movement of the Kostanjek landslide, the largest landslide in the Republic of Croatia. The prediction models are based on a 4-year monitoring data series of landslide movement, groundwater level, and precipitation. The presented models for landslide movement prediction are divided into the model for the prediction of groundwater level from precipitation data and the model for the prediction of landslide velocity from groundwater level data. The statistical techniques used for prediction are multiple linear regression and random forests. For the prediction of groundwater level, 75 variables calculated from precipitation and evapotranspiration data were used, while for the prediction of landslide movement, 10 variables calculated from groundwater level data were used. The prediction results were mutually compared by k-fold cross-validation. The root mean square error analyses of k-fold cross-validation showed that the results obtained from random forests are just slightly better than those from multiple linear regression, in both, the groundwater level and the landslide velocity models, proofing that multiple linear regression has a potential for prediction of landslide movement.

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
Fig. 11
Fig. 12
Fig. 13

References

  • Abdul-Wahab SA, Bakheit CS, Al-Alawi SM (2005) Principle component and multiple regression analysis in modelling of ground-level ozone and factors affecting its concentrations. Environ Modelling Softwares 20:1263–1271

    Article  Google Scholar 

  • van Asch TWJ, van Beek LPH, Bogaard TA (2007) Problems in predicting the mobility of slow-moving landslides. Eng Geol 91:46–55

    Article  Google Scholar 

  • Barrero MA, Grimalt JO, Canton L (2005) Prediction of daily ozone concentration maxima in the urban atmosphere. Chemom Intell Lab Syst 80(1):67–76

    Article  Google Scholar 

  • Berti M, Martina MLV, Franceschini S, Pignone S, Simoni A, Pizziolo M (2012) Probabilistic rainfall thresholds for landslide occurrence using a Bayesian approach. J Geophys Res 117:1–20. https://doi.org/10.1029/2012JF002367

    Article  Google Scholar 

  • Bertini T, Cugusi F, D’Elia B, Rossi-Doria M (1984) Climatic conditions and slow movements of colluvial covers in Central Italy. In: Proceedings of the IV International Symposium on landslides, Vol 1. Canadian Geotechnical Society, Toronto, pp 367–376

  • Breiman L (2001) Random forests. Mach Learn 45: 5–32

  • Cai Z, Ofterdinger U (2016) Analysis of groundwater-level response to rainfall and estimation of annual recharge in fractured hard rock aquifers, NW Ireland. J Hydrol 535:71–84. https://doi.org/10.1016/j.jhydrol.2016.01.066

    Article  Google Scholar 

  • Caruana R, Niculescu-Mizil A (2006) An empirical comparison of supervised learning algorithms. Proceedings of the 23rd international conference on machine learning, pp 161–168. doi:https://doi.org/10.1145/1143844.1143865

  • Carvajal G, Maucec M, Cullick S (2017) Intelligent digital oil and gas fields: concepts, collaboration, and right-time decisions. Gulf Professional Publishing

  • Corominas J, Moya J, Ledesma A, Lloret A, Gili JA (2005): Prediction of ground displacements and velocities from groundwater level changes at the Vallcebre landslide (Eastern Pyrenees, Spain). Landslides 2: 83–96. doi https://doi.org/10.1007/s10346-005-0049-1

  • Gaalen JF van, Kruse S, Lafrenz WB, Burroughs SM (2013) Predicting water table response to rainfall events, Central Florida. Groundwater 51(3): 350–362. doi: https://doi.org/10.1111/j.1745-6584.2012.00970.x

  • Gajić-Čapka M, Zaninović K (2008) Climate of Croatia. In: Zaninović K (ed) Climate atlas of Croatia, 1961–-1990 and 1971-2000. Croatian Meteorological and Hydrological Service, Zagreb, pp 15–17

  • Gonzalez DA, Ledesma A, Corominas J (2008) The viscous component in slow moving landslides: a practical case. In: Chen Z, Zhang J, Li Z, Wu F, Ho K (eds) Proceedings of the 10th International Symposium on Landslides and Engineered Slopes. Taylor and Francis, London, pp 237–242

  • ISRM (2007) The complete ISRM suggested methods for rock characterization, testing and monitoring: 1974–2006. In: Ulsay R, Hudson J. (eds) Suggested methods prepared by the commission on testing methods. International Society for Rock Mechanics, Compilation arranged by the ISRM Turkish National Group, Ankara, 628 pp.

  • Jan C-D, Chen T-H, Lo W-C (2007) Effect of rainfall intensity and distribution on groundwater level fluctuations. J Hydrol 332:348–360. https://doi.org/10.1016/j.jhydrol.2006.07.010

    Article  Google Scholar 

  • James G, Witten D, Hastie T, Tibshirani R (2014) An introduction to statistical learning with applications in R. Springer, New York

    Google Scholar 

  • Kane MJ, Price N, Scotch M, Rabinowitz P (2014) Comparison of ARIMA and random forest time series models for prediction of avian influenza H5N1 outbreaks. BMC Bioinformatics 15:276. https://doi.org/10.1186/1471-2105-15-276

    Article  Google Scholar 

  • Khademi F, Jamal SM, Deshpande N, Londhe S (2016) Predicting strength of recycled aggregate concrete using artificial neural network, adaptive neuro-fuzzy inference system and multiple linear regression. Int J Sustain Built Environ 5:355–369. https://doi.org/10.1016/j.ijsbe.2016.09.003

    Article  Google Scholar 

  • Krkač M, Mihalić Arbanas S, Arbanas Ž, Bernat S, Špehar K, Watanabe N, Nagai O, Sassa K, Marui H, Furuya G, Wang C, Rubinić J, Matsunami K (2014a) Review of monitoring parameters of the Kostanjek landslide (Zagreb, Croatia). In: Sassa K, Canuti P, Yin Y (eds) Proceedings of the 3rd World Landslide Forum ‘Landslide Science for a Safer Geoenvironment’, Volume 2 ‘Methods of Landslide Studies’. Springer, Netherland, pp 637–645

  • Krkač M, Mihalić Arbanas S, Nagai O, Arbanas Ž, Špehar K (2014b): The Kostanjek landslide-monitoring system development and sensor network. In: Mihalić Arbanas S, Arbanas Ž (eds) Proceedings of the 1st Regional Symposium on Landslides in the Adriatic-Balkan Region: Landslide and Flood Hazard Assessment. Croatian Landslide Group, Zagreb, pp 27–32

  • Krkač M (2015) A phenomenological model of the Kostanjek landslide movement based on the landslide monitoring parameters [in Croatian]. Dissertation, University of Zagreb

  • Krkač M, Špoljarić D, Bernat S, Mihalić Arbanas S (2017) Method for prediction of landslide movements based on random forests. Landslides 14(3):947–960. https://doi.org/10.1007/s10346-016-0761-z

    Article  Google Scholar 

  • Kutner MH, Nachtsheim CJ, Neter J (2004) Applied linear regression models - 4th edition. McGraw-Hill Education

  • Livingstone DJ, Salt DW (2005) Judging the significance of multiple linear regression models. J Med Chem 48:661–663

    Article  Google Scholar 

  • Mansour MF, Morgenstern NR, Martin CD (2011) Expected damage from displacement of slow-moving slides. Landslides 8(1):117–131. https://doi.org/10.1007/s10346-010-0227-7

    Article  Google Scholar 

  • Massey CI, Petley DN, McSaveney MJ (2013) Patterns of movement in reactivated landslides. Eng Geol 159:1–19

  • Matsuura S, Asano S, Okamoto T (2008) Relationship between rain and/or meltwater, pore-water pressure and displacement of a reactivated landslide. Eng Geol 101:49–59. https://doi.org/10.1016/j.enggeo.2008.03.007

    Article  Google Scholar 

  • Micheletti N, Foresti L, Robert S, Leuenberger M, Pedrazzini A, Jaboyedoff M, Kanevski M (2014) Machine learning feature selection methods for landslide susceptibility mapping. Math Geosci 46:33–57. https://doi.org/10.1007/s11004-013-9511-0

    Article  Google Scholar 

  • Mihalić Arbanas S, Krkač M, Bernat S (2016) Application of advanced technologies in landslide research in the area of the City of Zagreb (Croatia, Europe). Geologia Croatica 69(2):231–243

    Article  Google Scholar 

  • Mihalić Arbanas S, Sečanj M, Bernat Gazibara S, Krkač M, Begić H, Džindo A, Zekan S, Arbanas Ž (2017) Landslides in the Dinarides and Pannonian Basin—from the largest historical and recent landslides in Croatia to catastrophic landslides caused by Cyclone Tamara (2014) in Bosnia and Herzegovina. Landslides 14(6):1861–1876. https://doi.org/10.1007/s10346-017-0880-1

    Article  Google Scholar 

  • Montgomery DC, Peck EA, Vining GG (2015) Introduction to linear regression analysis. John Wiley & Sons, New Jersey

    Google Scholar 

  • Ortolan Ž (1996) Development of 3D engineering geological model of deep landslide with multiple sliding surfaces (Example of the Podsused Landslide) [in Croatian]. Dissertation, University of Zagreb

  • Ortolan Ž, Pleško J (1992) Repeated photogrammetric measurements at shaping geotechnical models of multi-layer landslides. Rudarsko-geološko-naftni zbornik 4:51–58

    Google Scholar 

  • Pal R (2017) Predictive modeling of drug sensitivity. Academic Press. https://doi.org/10.1016/C2015-0-04656-1

  • Refaeilzadeh P, Tang L, Liu H (2009) Cross-Validation. In: Liu L, Özsu MT (eds) Encyclopedia of database systems. Springer, Boston

    Google Scholar 

  • Schulz WH, McKenna JP, Kibler JD, Biavati G (2009) Relations between hydrology and velocity of a continuously moving landslide—evidence of pore-pressure feedback regulating landslide motion? Landslides 6:181–190. https://doi.org/10.1007/s10346-005-0049-1

    Article  Google Scholar 

  • Stanić B, Nonveiller E (1996) The Kostanjek landslide in Zagreb. Eng Geol 42:269–283

    Article  Google Scholar 

  • Sullivan LM (2012) Essentials of biostatistics workbook. Statistical computing using Excel 2003. Jones & Bartlett Learning, Sudbury

  • Šikić K, Basch O, Šimunić A (1972) Basic geological map, scale 1:100,000, Zagreb, Sheet 33-80 [in Croatian]. Geological Bureau, Zagreb, Federal Geological Bureau, Beograd

  • Tabrizi SS, Sancar N (2017) Prediction of body mass index: a comparative study of multiple linear regression, ANN and ANFIS models. Procedia Computer Science 120:394–401. https://doi.org/10.1016/j.procs.2017.11.255

    Article  Google Scholar 

  • Veselić Bruvo J (2011) Annual statistics of Zagreb City [in Croatian]. City Office for the Strategic Planning and Development of the City, City of Zagreb

  • Vrsaljko D (2003) Biostratigraphy of Miocene deposits from Žumberačko and Samoborsko gorje Mts. of the basis of molluscs [in Croatian]. Dissertation, University of Zagreb

  • Vrsaljko D, Mihalić S, Bošnjak M, Krkač M (2012) Lithostratigraphical investigations of the Kostanjek landslide wider area: review of existing data and planned activities. In: Ožanić N, Arbanas Ž, Mihalić S, Marui H, Dragičević N (eds) Book of proceedings of the 2nd Project Workshop of the Croatia - Japan Project on Risk Identification and Land-use Planning for Disaster Mitigation of Landslides and Floods in Croatia. University of Rijeka, Rijeka, pp 17–20

  • Weinheimer A, Biondi F (2003) Varves. In: Holton JR, Curry JA, Pyle JA (eds) Encyclopedia of atmospheric sciences, vol 4. Academic Press, Oxford, pp 1680–1685

    Chapter  Google Scholar 

  • Wienhöfer J, Lindenmaier F, Zehe E (2011) Challenges in understanding the hydrologic controls on the mobility of slow-moving landslides. Vadose Zone J 10(2):496–511. https://doi.org/10.2136/vzj2009.0182

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb, Pierottijeva 6, 10000, Zagreb, Croatia

    Martin Krkač, Sanja Bernat Gazibara, Marin Sečanj & Snježana Mihalić Arbanas

  2. Faculty of Civil Engineering, University of Rijeka, Radmile Matejčić 3, 51000, Rijeka, Croatia

    Željko Arbanas

Authors
  1. Martin Krkač
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sanja Bernat Gazibara
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Željko Arbanas
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Marin Sečanj
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Snježana Mihalić Arbanas
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Željko Arbanas.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Krkač, M., Bernat Gazibara, S., Arbanas, Ž. et al. A comparative study of random forests and multiple linear regression in the prediction of landslide velocity. Landslides 17, 2515–2531 (2020). https://doi.org/10.1007/s10346-020-01476-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10346-020-01476-6

Keywords

Search

Navigation