Prediction of open stope hangingwall stability using random forests

Abstract

The prediction of open stope hangingwall (HW) stability is a crucial task for underground mines. In this paper, a relatively novel technique, the random forest (RF) algorithm, is introduced for the prediction of HW stability. The objective of this study is to verify the feasibility of the RF algorithm on HW stability prediction and investigate the relative importance of influencing variables. The training and verification of RF models were conducted on a dataset from the literature and a total of 115 HW cases were analysed. Thirteen influencing variables were selected as the inputs with the HW stability being selected as the output. The dataset was randomly divided into the training set and the testing set. Fivefold cross-validation was used as the validation method, and the grid search method was used for the hyper-parameters tuning. Performance measures were chosen to be the confusion matrix, the receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC). The results show that the RF algorithm had great potential for the prediction of HW stability. AUC values achieved by the optimum RF model on the training set and the testing set were 0.884 and 0.873, respectively, indicating that the optimum RF model was excellent at predicting HW stability. The stope design method was found to be the most sensitive variable among all variables evaluated, with an importance score of 0.168 out of 1. The RQD and HW height also had a strong influence on the stability of an open stope HW.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

References

  1. Amedjoe CG, Agyeman J (2015) Assessment of effective factors in performance of an open stope using cavity monitoring system data: a case study. J Geol Min Res 7:19–30

    Article  Google Scholar 

  2. Barton N, Lien R, Lunde J (1974) Engineering classification of rock masses for the design of tunnel support. Rock Mech 6:189–236

    Article  Google Scholar 

  3. Brady T, Pakalnis R, Clark L (2006) Design in weak rock masses: Nevada underground mining operations. Trans Soc Min Metall Exp Inc 318:182

    Google Scholar 

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

    Article  Google Scholar 

  5. Breiman L, Friedman J, Stone CJ, Olshen RA (1984) Classification and regression trees. CRC Press, Boca Raton

    Google Scholar 

  6. Brokamp C, Jandarov R, Rao MB, LeMasters G, Ryan P (2017) Exposure assessment models for elemental components of particulate matter in an urban environment: a comparison of regression and random forest approaches. Atmos Environ 151:1–11. https://doi.org/10.1016/j.atmosenv.2016.11.066

    Article  Google Scholar 

  7. Capes GW (2009) Open stope hangingwall design based on general and detailed data collection in unfavourable hangingwall conditions. Dissertation, University of Saskatchewan

  8. Caruana R, Karampatziakis N, Yessenalina A (2008) An empirical evaluation of supervised learning in high dimensions. In: Proceedings of the 25th international conference on Machine learning, ACM, pp 96–103

  9. Cepuritis P, Villaescusa E, Beck D, Varden R (2010) Back analysis of over-break in a longhole open stope operation using non-linear elasto-plastic numerical modelling. In: 44th US rock mechanics symposium and 5th US-Canada rock mechanics symposium, American rock mechanics association

  10. Clark LM (1998) Minimizing dilution in open stope mining with a focus on stope design and narrow vein longhole blasting. Dissertation, University of British Columbia

  11. Clark L, Pakalnis R (1997) An empirical design approach for estimating unplanned dilution from open stope hangingwalls and footwalls. In: Proceedings of the 99th annual general meeting, 1997. Canadian Institute of Mining, Metallurgy and Petroleum Vancouver

  12. Deere DU (1962) Technical description of rock cores for engineering purposes. University of Illinois, Illinois

    Google Scholar 

  13. Diederichs M, Kaiser P (1999) Tensile strength and abutment relaxation as failure control mechanisms in underground excavations. Int J Rock Mech Min Sci 36:69–96

    Article  Google Scholar 

  14. Friedman J, Hastie T, Tibshirani R (2001) The elements of statistical learning, vol 1. Springer, New York

    Google Scholar 

  15. Henning JG, Mitri HS (2007) Numerical modelling of ore dilution in blasthole stoping. Int J Rock Mech Min Sci 44:692–703

    Article  Google Scholar 

  16. Henning JG, Mitri HS (2008) Assessment and control of ore dilution in long hole mining: case studies. Geotech Geol Eng 26:349–366

    Article  Google Scholar 

  17. Hong H, Pourghasemi HR, Pourtaghi ZS (2016) Landslide susceptibility assessment in Lianhua County (China): a comparison between a random forest data mining technique and bivariate and multivariate statistical models. Geomorphology 259:105–118

    Article  Google Scholar 

  18. Hosmer DW Jr, Lemeshow S, Sturdivant RX (2013) Applied logistic regression, vol 398. Wiley, Hoboken

    Book  Google Scholar 

  19. Jang HD (2014) Unplanned dilution and ore-loss optimisation in underground mines via cooperative neuro-fuzzy network. Dissertation, Curtin University

  20. Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Ijcai, vol 2. Stanford, pp 1137–1145

  21. Kohestani V, Hassanlourad M, Ardakani A (2015) Evaluation of liquefaction potential based on CPT data using random forest. Nat Hazards 79:1079–1089

    Article  Google Scholar 

  22. Kuhn M, Johnson K (2013) Applied predictive modeling, vol 810. Springer, Berlin

    Book  Google Scholar 

  23. Kuhnert PM, Henderson AK, Bartley R, Herr A (2010) Incorporating uncertainty in gully erosion calculations using the random forests modelling approach. Environmetrics 21:493–509

    Google Scholar 

  24. Lagomarsino D, Tofani V, Segoni S, Catani F, Casagli N (2017) A tool for classification and regression using random forest methodology: applications to landslide susceptibility mapping and soil thickness modeling. Environ Model Assess 22:201–214

    Article  Google Scholar 

  25. Liaw A, Wiener M (2002) Classification and regression by randomForest. R News 2(3):18–22

    Google Scholar 

  26. Mawdesley C, Trueman R, Whiten W (2001) Extending the Mathews stability graph for open–stope design. Min Technol 110:27–39

    Article  Google Scholar 

  27. Nateghi R, Guikema SD, Quiring SM (2014) Forecasting hurricane-induced power outage durations. Nat Hazards 74:1795–1811. https://doi.org/10.1007/s11069-014-1270-9

    Article  Google Scholar 

  28. Nickson SD (1992) Cable support guidelines for underground hard rock mine operations. Dissertation, University of British Columbia

  29. Potvin Y (1988) Empirical open stope design in Canada. Dissertation, University of British Columbia

  30. Potvin Y, Hadjigeorgiou J (2001) The stability graph method for open-stope design In: Underground mining methods: engineering fundamentals and international case studies society of mining, metallurgy and exploration, 8307 Shaffer Parkway, Littleton, CO 80127, USA, pp 513–520

  31. Qi C, Tang X (2018) Slope stability prediction using integrated metaheuristic and machine learning approaches: a comparative study. Comput Ind Eng. https://doi.org/10.1016/j.cie.2018.02.028

    Google Scholar 

  32. Qi C, Fourie A, Ma G, Tang X, Du X (2017) Comparative study of hybrid artificial intelligence approaches for predicting hangingwall stability. J Comput Civ Eng 32:04017086

    Article  Google Scholar 

  33. Qi C, Fourie A, Chen Q (2018a) Neural network and particle swarm optimization for predicting the unconfined compressive strength of cemented paste backfill. Constr Build Mater 159:473–478

    Article  Google Scholar 

  34. Qi C, Fourie A, Chen Q, Zhang Q (2018b) A strength prediction model using artificial intelligence for recycling waste tailings as cemented paste backfill. J Clean Prod 183:566–578

    Article  Google Scholar 

  35. Rodriguez-Galiano V, Chica-Olmo M (2012) Land cover change analysis of a Mediterranean area in Spain using different sources of data: multi-seasonal Landsat images, land surface temperature, digital terrain models and texture. Appl Geogr 35:208–218

    Article  Google Scholar 

  36. Rodriguez-Galiano V, Sanchez-Castillo M, Chica-Olmo M, Chica-Rivas M (2015) Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geol Rev 71:804–818

    Article  Google Scholar 

  37. Shimada H, Sasaoka T, Wattimena RK, Matsui K (2013) Influence of stope design on stability of hanging wall decline in cibaliung underground gold mine. Int J Geosci 4:1

    Google Scholar 

  38. Stewart S, Forsyth W (1995) The Mathew’s method for open stope design. CIM Bull 88:45–53

    Google Scholar 

  39. Wang J (2004) Influence of stress, undercutting, blasting and time on open stope stability and dilution. Dissertation, University of Saskatchewan 279

  40. Wang J, Milne D, Wegner L, Reeves M (2007) Numerical evaluation of the effects of stress and excavation surface geometry on the zone of relaxation around open stope hanging walls. Int J Rock Mech Min Sci 44:289–298

    Article  Google Scholar 

  41. Wanik DW, Anagnostou EN, Hartman BM, Frediani MEB, Astitha M (2015) Storm outage modeling for an electric distribution network in Northeastern USA. Nat Hazards 79:1359–1384. https://doi.org/10.1007/s11069-015-1908-2

    Article  Google Scholar 

  42. Youden WJ (1950) Index for rating diagnostic tests. Cancer 3(1):32–35

    Article  Google Scholar 

  43. Zhang K, Wu X, Niu R, Yang K, Zhao L (2017) The assessment of landslide susceptibility mapping using random forest and decision tree methods in the Three Gorges Reservoir area, China. Environ Earth Sci 76:405

    Article  Google Scholar 

  44. Zhou J, Li X, Mitri HS (2015) Comparative performance of six supervised learning methods for the development of models of hard rock pillar stability prediction. Nat Hazards 79:291–316

    Article  Google Scholar 

  45. Zhou J, Shi X, Du K, Qiu X, Li X, Mitri HS (2016) Feasibility of random-forest approach for prediction of ground settlements induced by the construction of a shield-driven tunnel. Int J Geomech 17:04016129

    Article  Google Scholar 

Download references

Acknowledgements

The first author was funded by China Scholarship Council (Grant No. 201606420046). The authors would like to thank Joanne Edmondston from Graduate Research school of The University of Western Australia for her valuable comments and suggestions which improved a previous version of this manuscript.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Chongchong Qi.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Qi, C., Fourie, A., Du, X. et al. Prediction of open stope hangingwall stability using random forests. Nat Hazards 92, 1179–1197 (2018). https://doi.org/10.1007/s11069-018-3246-7

Download citation

Keywords

  • Hangingwall stability
  • Random forest algorithm
  • Fivefold cross-validation
  • Hyper-parameters tuning
  • Performance measures
  • Variables importance