Abstract
Accurate prediction on geological hazards can prevent disaster events in advance and greatly reduce property losses and life casualties. Glacial debris flows are the most serious hazards in southeastern Tibet in China due to their complexity in formation mechanism and the difficulty in prediction. Data collected from 102 glacier debris flow events from 31 gullies since 1970 and regional meteorological data from 1970 to 2019 in ParlungZangbo River Basin in southeastern Tibet were used for Artificial Neural Network (ANN)-based prediction of glacial debris flows. The formation mechanism of glacial debris flows in the ParlungZangbo Basin was systematically analyzed, and the calculations involving the meteorological data and disaster events were conducted by using the statistical methods and two layers fully connected neural networks. The occurrence probabilities and scales of glacial debris flows (small, medium, and large) were predicted, and promising results have been achieved. Through the proposed model calculations, a prediction accuracy of 78.33% was achieved for the scale of glacial debris flows in the study area. The prediction accuracy for both large- and medium-scale debris flows are higher than that for small-scale debris flows. The debris flow scale and the probability of occurrence increase with increasing rainfall and temperature. In addition, the K-fold cross-validation method was used to verify the reliability of the model. The average accuracy of the model calculated under this method is about 93.3%, which validates the proposed model. Practices have proved that the combination of ANN and disaster events can provide sound prediction on geological hazards under complex conditions.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Anandharajan TR, Hariharan GA, Vignajeth KK, et al. (2016) Weather monitoring using artificial intelligence. 2016 2nd International Conference on Computational Intelligence and Networks (CINE). https://doi.org/10.1109/CINE.2016.26
Bilgili M (2010) Prediction of soil temperature using regression and artificial neural network models. Meteorol Atmos Phys 110: 59–70. https://doi.org/10.1007/s00703-010-0104-x
Cannon SH, Boldt EM, Laber JL, et al. (2011) Rainfall intensity-duration thresholds for postfire debris-flow emergency-response planning. Nat Hazards 59 (1): 209–236. https://doi.org/10.1007/s11069-011-9747-2
Chen S H, Jakeman A J, Norton JP, et al. (2008) Artificial intelligence techniques: An introduction to their use for modelling environmental systems. Math Comput Simul 78 (2): 379–400. https://doi.org/10.1016/j.matcom.2008.01.028
Chen NS, Yang CL, Zhou W, et al. (2011). Investigation technology for debris flows. Science Press, Beijing. (In Chinese)
Chen C, Zhang L M, Xiao T, et al. (2018) Barrier lake bursting and flood routing in the YarlungTsangporand Canyon in October 2018. J Hydrol 124603. https://doi.org/10.1016/j.jhydrol.2020.124603
Chen N, Yang CL, Zhou W, et al. (2009). The critical rainfall characteristics for torrents and debris flows in the Wenchuan earthquake stricken area. J Mt Sci 6 (4): 362–372. https://doi.org/10.1007/s11629-009-1064-9
Cui Peng. (2005) The forecasting of debris flow. Bull Chin Acad Sci 5 (5): 363–369. (In Chinese)
Deng M, Chen N, Liu M, et al. (2016) Meteorological factors driving glacial till variation and the associated periglacial debris flows in Tianmo Valley, south-eastern Tibetan Plateau. Nat Hazards Earth Syst Sci 17 (3): 345–356. https://doi.org/10.5194/nhess-17-345-2017
Esteves JT, Rolim GD, Ferraudo AS, et al. (2019) Rainfall prediction methodology with binary multilayer perceptron neural networks. Clim Dyn 52 (3): 2319–2331. https://doi.org/10.1007/s00382-018-4252-x
Fei XY, Liu JB, Qu BQ et al. (2017) Meteorologic early-warning model for rainfall-induced landslide disasters in Sichuan province. Bull Soil Water Conserv 37 (5): 315–321, 327.
Fischer L, Purves RS, Huggel C, et al. (2012) On the influence of topographic, geological and cryospheric factors on rock avalanches and rockfalls in high-mountain areas. Nat Hazards Earth Syst Sci 12: 241–254. https://doi.org/10.5194/nhess-12-241-2012
Hattanji T, Matsushi Y, Matsuzaki H, et al. (2019) The role of debris flow on total denudation in small basins of the Ashio Mountains, Japan. Geomorphology 329: 129–137. https://doi.org/10.1016/j.geomorph.2018.12.022
Huang L (2020) Research on meteorological early-warning model of landslides in Wenchuan earthquake area based on machine learning. Acta Geod et Cartogr Sin 49 (2): 267. (In Chinese)
Hu GS, Chen NS, Deng MF, et al. (2011) Classification and initiation conditions of debris flows in Linzhi Area, Tibet. Bull Soil Water Conserv 31 (2): 193–197. (In Chinese)
Huang Y (2010) Prediction of debris flow based on IBRF neural network. J Cent South Univ Technol 30 (03): 159–163. (In Chinese)
Lyu RR, Tang BX, Zhu PY, et al. (1999) Debris flow and environment in Tibet. Press of Chengdu University of Science and Technology, Chengdu. (In Chinese)
Lu XB, Li DJ (1996) Debris flow prediction based on neural network. J Nat Disasters (03): 49–52 (In Chinese)
Ni HY, Wang DW (2010) Present status, problem and advice on the research of prediction and forecasting of debris flow based on rainfall condition. J Catastroph 25 (1):124–128. (In Chinese) https://doi.org/10.1016/S1876-3804(11)60004-9
Stoffel M, Huggel C (2012) Effects of climate change on mass movements in mountain environments. Prog Phys Geogr 36:421–439. https://doi.org/10.1177/0309133312441010
Tang BX, Zhou BF, Wu JS, et al. (2000) Debris flows in China. The Commercial Press, Beijing.
Tang W, Ma SC (2019) Application of regression and artificial neural network in ground temperature processing. 2019 International Conference on Meteorology Observations (ICMO), Chengdu, China. pp 1–4. https://doi.org/10.1109/ICMO49322.2019.9026084
Weesakul U, Kaewprapha P, Boonyuen K, et al. (2018) Deep learning neural network: A machine learning approach for monthly rainfall forecast, case study in eastern region of Thailand. Eng Appl Sci Res 45: 203–211. https://doi.org/10.14456/easr.2018.24
Wei FQ, Cui P, Zhong DL (2004) Classification of debris flow forecast and its present status and development in research. J Nat Disasters 13 (5): 10–15. (In Chinese)
Wang X, Li G, Zheng BG, et al. (2009) Debris flow prediction in Panshi city based on artificial neural network. Renmin Changjiang River 40 (03): 46–48. (In Chinese)
Yang W, Guo X, Yao T, et al. (2016) Recent accelerating mass loss of southeast Tibetan glaciers and the relationship with changes in macroscale atmospheric circulations, Climatic. Dynamic 47: 805–815. https://doi.org/10.1007/s00382-015-2872-y
Zhang MX (2019) Construction of geological disaster prevention and control system based on AI. Northwest Geol 52 (2):103–116. (In Chinese)
Zhou W, Tang C. (2014) Rainfall thresholds for debris flow initiation in the Wenchuan earthquake-stricken area, southwestern China. Landslides 11 (5): 877–887. https://doi.org/10.1007/s10346-013-0421-5
Acknowledgements
This research was supported by the National Natural Science Foundation of China (Grant No. 41671112), the Sichuan Province Science and Technology Plan Project Key research and development projects (Grant No. 18ZDYF0329) and the National Natural Science Foundation of China (Grant No. 41861134008).
Author information
Authors and Affiliations
Corresponding author
Additional information
Data availability
Daily, monthly and annual meteorological data was downloaded from http://data.cma.cn/ and other meteorological data was provided by Bomi Geological Hazards Observation and Research Station, Chinese Academic of Sciences. The remote sensing image was downloaded from Google Earth. Any other processed data files are also available on request from the first or corresponding author.
Rights and permissions
About this article
Cite this article
Tang, W., Ding, Ht., Chen, Ns. et al. Artificial Neural Network-based prediction of glacial debris flows in the ParlungZangbo Basin, southeastern Tibetan Plateau, China. J. Mt. Sci. 18, 51–67 (2021). https://doi.org/10.1007/s11629-020-6414-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11629-020-6414-7