Abstract
Avalanche forecasting is carried out using physical as well as statistical models. All these models have certain limitations associated with their mathematical formulation that enable them to perform variably with respect to forecast of an avalanche event and associated danger. To overcome limitations of each individual model, a multi-model decision support system (MM-DSS) has been developed for forecasting of avalanche danger in Chowkibal–Tangdhar (C-T) region of North-West Himalaya. The MM-DSS has been developed for two different altitude zones of the C-T region by integrating four avalanche forecasting models-Hidden Markov model (HMM), nearest neighbour (NN), artificial neural network (ANN) and snow cover model-HIM-STRAT to deliver avalanche forecast with a lead time of three days. Weather variables for these models have been predicted using ANN. Root mean square error of predicted weather variables is computed by using leave one out cross-validation method. Snow and meteorological data of 22 winters (1992–2014) of the lower C-T region and 8 winters (2008–2016) of the higher C-T region have been used to develop avalanche forecasting models for these two sub-regions. All the avalanche forecasting models have been validated by true skill score (TSS), Heidke skill score (HSS), per cent correct (PC), probability of detection (POD), bias and false alarm rate (FAR) using data of five winters (2014–19) for the lower C-T region and three winters (2016–19) for the upper C-T region. In both the C-T regions, for day-1, day-2 and day-3, the HSS of MM-DSS lies between 0.26 and 0.4 and the POD between 0.64 and 0.86.
Similar content being viewed by others
References
Akaike H (1973) Information theory and an extension of the maximum likelihood principle. In: Proceedings of the 2nd international symposium on information theory, Budapest, Akademiai Kiado, pp 267–281
Blumenthal L (1953) Theory and applications of distance geometry. Oxford University Press, Oxford
Bodo B, Unny TE (1976) Model uncertainty in flood frequency analysis and frequency-based design. Water Resour Res 12(6):1109–1117
Bolognesi R (1998) NivoLog: An avalanche forecasting support system. In: International Snow Science Workshop (ISSW), Sunriver, Oregon, pp 412–418
Bolognesi R, Buser O, Good W (1992) The NX-LOG project. In: Proceedings of the international snow science workshop, Beckenridge USA
Bolognesi R, Buser O, Good W (1994) Local avalanche forecasting in Switzerland: strategy and tools, a new approach. In: International Snow Science Workshop, pp 463–472
Brabec B, Meister R (2001) A nearest-neighbor model for regional avalanche forecasting. Ann Glaciol 32:130–134
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140
Buser O (1983) Avalanche forecast with the method of nearest neighbours: an interactive approach. Cold Reg Sci Technol 8(2):155–163
Buser O (1989) Two years’ experience of operational avalanche forecasting using the nearest neighbours method. Ann Glaciol 13:31–34
CAA (2016) Technical aspects of snow avalanche risk management—Resources and Guidelines for Avalanche Practitioners in Canada. In: Campbell C, Conger S, Gould B, Haegeli P, Jamieson B and Statham G (eds) Canadian Avalanche Association, Revelstoke, BC, Canada
Chamberlain TC (1965) The method of multiple working hypotheses (reprint of 1890 science article). Science 148:754–759
Chandra B, Singh A, Singh D, Ganju A (2010) Features ranking for avalanche forecasting: method and results for north-western Himalaya. In: Proceedings of the international snow science workshop, Lake Tahoe, Canada, 17–22, October, pp 196–203
Choubin B, Borji M, Mosavi A, Sajedi-Hosseini F, Singh VP, Shamshirband S (2019) Snow avalanche hazard prediction using machine learning methods. J Hydrol 577:123929
Clemen RT (1989) Combining forecasts: a review and annotated bibliography. Int J Forecast 5(4):559–583
Cordy P, McClung DM, Hawkins CJ, Tweedy J, Weick T (2009) Computer assisted avalanche prediction using electronic weather sensor data. Cold Reg Sci Technol 59(2–3):227–233
Dekanová M, Duchoň F, Dekan M, Kyzek F and Biskupič M (2018) Avalanche forecasting using neural network. In: 2018 ELEKTRO, IEEE pp 1–5
Dimri AP, Mohanty UC, Madan OP, Ravi N (2002) Statistical model-based forecast of minimum and maximum temperatures at Manali. Curr Sci 82:997–1003
Dimri AP, Niyogi D, Barros AP, Ridley J, Mohanty UC, Yasunari T, Sikka DR (2015) Western disturbances: a review. Rev Geophys 53(2):225–246
Floyer JA, McClung DM (2003) Numerical avalanche prediction: bear pass, British Columbia. Can Cold Reg Sci Technol 37(3):333–342
Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. ICML 96:148–156
Fromm R, Forest NH (2009) Estimating the forecasting success of artificially triggering of avalanches with the combination of cluster and discriminant analysis. In: Proceedings of the international snow science workshop, Davos, Switzerland, pp 366–370
Gassner M, Brabec B (2002) Nearest neighbour models for local and regional avalanche forecasting. Nat Hazard 2:247–253
Gassner M, Etter HJ, Birkeland K, Leonard T (2000) NXD2000: an improved avalanche forecasting program based on the nearest neighbor method. In: Proceedings of the international snow science workshop 2000, pp 52–59
Hansen LK, Salamon P (1990) Neural network ensembles. IEEE Trans Pattern Anal Mach Intell 12(10):993–1001
Hashem S (1997) Optimal linear combinations of neural networks. Neural Netw 10(4):599–614
Heck M, Hammer C, Herwijnen AV, Schweizer J, Fäh D (2018) Automatic detection of snow avalanches in continuous seismic data using hidden Markov models. Nat Hazard 18(1):383–396
Joshi JC, Srivastava S (2014) A hidden Markov model for avalanche forecasting on Chowkibal–Tangdhar road axis in Indian Himalayas. J Earth Syst Sci 123(8):1771–1779
Joshi JC, Kumar T, Srivastava S, Sachdeva D (2017a) Optimisation of hidden Markov model using Baum–Welch algorithm for prediction of maximum and minimum temperature over Indian Himalaya. J Earth Syst Sci 126(1):3–11
Joshi JC, Kumar T, Srivastava S (2017b) Hidden Markov model for quantitative prediction of snowfall and analysis of hazardous snowfall events over Indian Himalaya. J Earth Syst Sci 126(3):33–44
Joshi JC, Kumar T, Srivastava S, Sachdeva D, Ganju A (2018) Application of hidden Markov model for avalanche danger simulations for road sectors in North-West Himalaya. Nat Hazards 93(3):1127–1143
Joshi JC (2018) Development of hidden markov model (HMM) based avalanche forecasting system for north-west Himalayas (Published Doctoral Dissertation). Panjab University, India
Joshi JC, Kaur P, Kumar B, Singh A, Satyawali PK (2020) HIM-STRAT: a neural network-based model for snow cover simulation and avalanche hazard prediction over North-West Himalaya. Nat Hazards 103:1239–1260
Kleemayr K, Moser A (1998) NAFT new avalanche forecasting technologies (neue Lawinenprognosemodelle). Forschung im Verbund 40.
Kotsianti SB, Dimitris K (2007) Combining bagging, boosting and bagging for classification problems. In: International conference on knowledge-based and intelligent information and engineering systems, Springer, Berlin, Heidelberg, pp 493–500
Kristensen K, Larsson C (1994) An avalanche forecasting program based on a modified nearest neighbour method. In: Proceedings of the international snow science workshop, pp 22–30
Krogh A, Vedelsby J (1995) Neural network ensembles, cross validation, and active learning. In: Advances in neural information processing systems, pp 231–238
Laio F, Di Baldassarre G, Montanari A (2009) Model selection techniques for frequency analysis of hydrological extremes. Water Resour Res 45(7):W07416. https://doi.org/10.1029/2007WR006666
Lorentz GG (1963) The degree of approximation by polynomials with positive coefficients. Math Ann 151(3):239–251
Mahalanobis PC (1936) On the generalised distance in statistics (PDF). Proc Natl Inst Sci India 2(1):49–55 (Retrieved 2016-09-27)
McClung DM, Schaerer P (2006) The Avalanche Handbook. The Mountaineers, Seattle, WA, USA
McClung DM, Tweedy J (1994) Numerical avalanche prediction: Kootenay Pass, British Columbia. Can J Glaciol 40(135):350–358
McCollister C, Birkeland K, Hansen K, Aspinall R, Comey R (2003) Exploring multi-scale spatial patterns in historical avalanche data, Jackson Hole Mountain Resort. Wyo Cold Reg Sci Technol 37(3):299–313
McLachlan GJ (1992) Discriminant analysis and statistical pattern recognition. Chapter 13. Wiley, New York
Molteni F, Buizza R, Palmer TN, Petroliagis T (1996) The ECMWF ensemble prediction system: methodology and validation. Q J R Meteorol Soc 122(529):73–119
Najafi MR, Moradkhani H (2015) Multi-model ensemble analysis of runoff extremes for climate change impact assessments. J Hydrol 525:352–361
Najafi MR, Moradkhani H, Jung IW (2011) Assessing the uncertainties of hydrologic model selection in climate change impact studies. Hydrol Process. https://doi.org/10.10002/hyp.8043
Naresh P, Pant LM (1999) Knowledge-based system for forecasting snow avalanches of Chowkibal–Tangdhar Axis (J&K). Def Sci J 49(5):381
Okoli K, Breinl K, Brandimarte L, Botto A, Volpi E, Di Baldassarre G (2018) Model averaging versus model selection: estimating design floods with uncertain river flow data. Hydrol Sci J 63(13–14):1913–1926
Opitz D, Maclin R (1999) Popular ensemble methods: an empirical study. J Artif Intell Res 11:169–198
Opitz DW, Shavlik JW (1996) Actively searching for an effective neural network ensemble. Connect Sci 8(3–4):337–354
Opitz DW, Shavlik JW (1996b) Generating accurate and diverse members of a neural-network ensemble. In: Advances in neural information processing systems, pp 535–541
Perrone MP (1993) Improving regression estimation: averaging methods for variance reduction with extensions to general convex measure optimization (Doctoral dissertation, Brown University)
Pozdnoukhov A, Matasci G, Kanevski M, Purves RS (2011) Spatio-temporal avalanche forecasting with Support Vector Machines. Nat Hazard 11(2):367–382
Purves RS, Morrison KW, Moss G, Wright DSB (2003) Nearest neighbours for avalanche forecasting in Scotland—development, verification and optimisation of a model. Cold Reg Sci Technol 37(3):343–355
Rahmati O, Ghorbanzadeh O, Teimurian T, Mohammadi F, Tiefenbacher JP, Falah F, Pirasteh S, Ngo PT, Bui DT (2019) Spatial modeling of snow avalanche using machine learning models and geo-environmental factors: comparison of effectiveness in two mountain regions. Remote Sens 11(24):2995
Schapire RE (1990) The strength of weak learnability. Mach Learn 5(2):197–227
Schweizer J, Bartlet P, van Herwijnen A (2015) Snow avalanches. In: Haeberli W, Whiteman C (eds) Snow and ice-related hazards, risks, and disasters. Elsevier, Amsterdam, pp 346–395
Sen Gupta A, Tarboton DG (2016) A tool for downscaling weather data from large-grid reanalysis products to finer spatial scales for distributed hydrological applications. Environ Model Softw 84:50–69
Singh A, Ganju A (2004) A supplement to nearest-neighbour method for avalanche forecasting. Cold Reg Sci Technol 39(2–3):105–113
Singh A, Ganju A (2008) Artificial Neural Networks for Snow Avalanche Forecasting in Indian Himalaya. In: Proceedings of 12th international conference of international association for computer methods and advances in geomechanics IACMAG, vol 16
Singh A, Damir B, Deep K, Ganju A (2015) Calibration of nearest neighbors model for avalanche forecasting. Cold Reg Sci Technol 109:33–42
Singh A, Deep K, Grover P (2017) A novel approach to accelerate calibration process of a k-nearest neighbours classifier using GPU. J Parallel Distrib Comput 104:114–129
Singh A, Srinivasan K, Ganju A (2005) Avalanche forecast using numerical weather prediction in Indian Himalaya. Cold Reg Sci Technol 43(1–2):83–92
Skamarock WC, Klemp JB, Dudhia J, Gill DO, Barker DM, Wang W, Powers JG (2005) A description of the advanced research WRF version 2. National Center for Atmospheric Research Boulder Colorado, Mesoscale and Microscale Meteorology Division. Tech. Note
Spencer Neil H (2013) 5.4.5 Squared Euclidean distances, essentials of multivariate data analysis. CRC Press, p 95 (ISBN 978-1-4665-8479-2)
Statham G, Haegeli P, Greene E, Birkeland K, Israelson C, Tremper B, Stethem C, McMahon B, White B, Kelly J (2018) A conceptual model of avalanche hazard. Nat Hazards 90:663–691
Thirel G, Regimbeau F, Martin E, Noilhan J, Habets F (2010) Short and medium range hydrological ensemble forecasts over France. Atmos Sci Lett 11(2):72–77
Thirel G, Rousset-Regimbeau F, Martin E, Habets F (2008) On the impact of short-range meteorological forecasts for ensemble stream flow predictions. J Hydrometeorol 9(6):1301–1317
Toth Z, Kalnay E (1997) Ensemble forecasting at NCEP and the breeding method. Mon Weather Rev 125(12):3297–3319
Tung YK, Mays LW (1981a) Risk models for flood levee design. Water Resour Res 17(4):833–841
Tung YK, Mays LW (1981b) Optimal risk based design for flood levee systems. Water Resour Res 17(4):842–852
Venables WN, Ripley BD (2002) Modern applied statistics with S, 4th edn. Springer, New York (ISBN 0-387-95457-0)
Vernay M, Lafaysse M, Mérindol L, Giraud G, Morin S (2015) Ensemble forecasting of snowpack conditions and avalanche hazard. Cold Reg Sci Technol 120:251–262
Voisin N, Pappenberger F, Lettenmaier DP, Buizza R, Schaake JC (2011) Application of a medium-range global hydro-logic probabilistic forecast scheme to the Ohio River Basin. Weather Forecast 26:425–446
Wolpert DH (1992) Stacked generalization. Neural Netw 5(2):241–259
Yan H, Moradkhani H (2016) Toward more robust extreme flood prediction by Bayesian hierarchical and multi-modeling. Nat Hazards 81(1):203–225
Zhang ZHAN, Krishnamurti TN (1997) Ensemble forecasting of hurricane tracks. Bull Am Meteor Soc 78(12):2785–2796
Acknowledgements
The authors acknowledge Director SASE for his approval to initiate this work under DRDO-funded project—Him Sandesh. The authors also acknowledge reviewers of this paper for valuable suggestions and positive criticism. Dr. SB Roy, Department of Atmospheric Science, IIT Delhi, is duly acknowledged for generating WRF data for project—Him Sandesh. The technical staff of SASE is also acknowledged for their valuable contribution in the collection of manual field data.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kaur, P., Joshi, J.C. & Aggarwal, P. A multi-model decision support system (MM-DSS) for avalanche hazard prediction over North-West Himalaya. Nat Hazards 110, 563–585 (2022). https://doi.org/10.1007/s11069-021-04958-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11069-021-04958-5